Difference between revisions of "User:Shawndouglas/sandbox/sublevel4"

From LIMSWiki
Jump to navigationJump to search
 
(14 intermediate revisions by the same user not shown)
Line 8: Line 8:
==Sandbox begins below==
==Sandbox begins below==


[[File:Lion Lab Technician2 (16279873861).jpg|right|500px]]This buyer's guide is based off the [[LIMS Buyer's Guide]], a former publication of the [[LabLynx, Inc.#Community history|Laboratory Informatics Institute]] (LII), an open trade association that was associated with [[LabLynx, Inc.]]<ref name="LII">{{cite web |url=http://www.limsfinder.com/BlogDetail.aspx?id=31049_0_3_0_C |archiveurl=https://web.archive.org/web/20130924062254/http://www.limsfinder.com/BlogDetail.aspx?id=31049_0_3_0_C |title=Laboratory Informatics Institute Established |publisher=Laboratory Informatics Institute, Inc |date=17 July 2006 |archivedate=24 September 2013 |accessdate=31 January 2023}}</ref><ref name="LBGOrig">{{cite web |url=http://limsbook.com/ |archiveurl=https://web.archive.org/web/20130602164430/https://www.limsbook.com/ |title=The LIMSbook ...everything about LIMS |publisher=Laboratory Informatics Institute, Inc |archivedate=02 Junw 2013 |accessdate=31 January 2023}}</ref> In late 2013, the LII and LabLynx discontinued publishing a copyrighted version and chose to release future guides to the public domain via this wiki. Per the [https://creativecommons.org/licenses/by-sa/4.0/ Creative Commons license] and the [[LIMSWiki:Copyrights|copyright terms of this site]], you are free to copy, adapt, distribute, and transmit this guide as long as you 1. give proper attribution and 2. distribute the work only under the same or a similar license.
*Discussion and practical use of [[artificial intelligence]] (AI) in the [[laboratory]] is, perhaps to the surprise of some, not a recent phenomena. In the mid-1980s, researchers were developing computerized AI systems able "to develop automatic decision rules for follow-up analysis of &#91;[[clinical laboratory]]&#93; tests depending on prior information, thus avoiding the delays of traditional sequential testing and the costs of unnecessary parallel testing."<ref>{{Cite journal |last=Berger-Hershkowitz |first=H. |last2=Neuhauser |first2=D. |date=1987 |title=Artificial intelligence in the clinical laboratory |url=https://www.ccjm.org/content/54/3/165 |journal=Cleveland Clinic Journal of Medicine |volume=54 |issue=3 |pages=165–166 |doi=10.3949/ccjm.54.3.165 |issn=0891-1150 |pmid=3301059}}</ref> In fact, discussion of AI in general was ongoing even in the mid-1950s.<ref name="MinskyHeuristic56">{{cite book |url=https://books.google.com/books?hl=en&lr=&id=fvWNo6_IZGUC&oi=fnd&pg=PA1 |title=Heuristic Aspects of the Artificial Intelligence Problem |author=Minsky, M. |publisher=Ed Services Technical Information Agency |date=17 December 1956 |accessdate=16 February 2023}}</ref><ref>{{Cite journal |last=Minsky |first=Marvin |date=1961-01 |title=Steps toward Artificial Intelligence |url=http://ieeexplore.ieee.org/document/4066245/ |journal=Proceedings of the IRE |volume=49 |issue=1 |pages=8–30 |doi=10.1109/JRPROC.1961.287775 |issn=0096-8390}}</ref>


*Hiring demand for laboratorians with AI experience (2015–18) has historically been higher in non-healthcare industries, such as manufacturing, mining, and agriculture, shedding a light on how AI adoption in the clinical setting may be lacking. According to the Brookings Institute, "Even for the relatively-skilled job postings in hospitals, which includes doctors, nurses, medical technicians, research lab workers, and managers, only approximately 1 in 1,250 job postings required AI skills." They add: "AI adoption may be slow because it is not yet useful, or because it may not end up being as useful as we hope. While our view is that AI has great potential in health care, it is still an open question."<ref name=":11">{{Cite web |last=Goldfarb, A.; Teodoridis, F. |date=09 March 2022 |title=Why is AI adoption in health care lagging? |work=Series: The Economics and Regulation of Artificial Intelligence and Emerging Technologies |url=https://www.brookings.edu/research/why-is-ai-adoption-in-health-care-lagging/ |publisher=Brookings Institute |accessdate=17 February 2023}}</ref>


==1. Introduction==
*Today, AI is being practically used in not only clinical diagnostic laboratories but also clinical research labs, life science labs, and research and development (R&D) labs, and more. Practical uses of AI can be found in:
What exactly is a [[laboratory information management system]] (LIMS) or [[laboratory information system]] (LIS) anyway? Do I need one? What options are available and how do I compare them? Where does a user requirements specification (USR), [[request for information]] (RFI), request for proposal (RFP), or request for quotation (RFQ) come into play, and how does it fit into acquiring a [[laboratory informatics]] solution? These are questions [[laboratory]] professionals typically ponder upon finding themselves charged with the mission of finding software for their lab. It can be a daunting
proposition, and there are few at least partially objective references to help with it all. This brief guide exists to, in part, meet that need.


At the core of this buyer's guide are several elements, including core information about evaluating, acquiring, and implementing laboratory software that fits your lab's needs. Also included here are laboratory informatics vendors who actually make their pricing partially or fully public, through one means or another. That pricing may be fully transparent and posted on the company website, or it may be a partial representation of the lowest possible price offered, as with those vendors who have a publicly viewable contract with the U.S. General Services Administration. While in the past vendors have refrained from providing public pricing, a more open information process may have its merits (particularly for potential buyers), though also not without its own set of caveats.<ref name="OOaLOpen">{{cite web |url=http://outonalims.com/2011/08/15/understanding-openness-and-other-marketing-tactics-in-laboratory-informatics-and-other-industries/ |title=Understanding Openness and Other Marketing Tactics in Laboratory Informatics and Other Industries |author=Metrick, Gloria |publisher=GeoMetrick Enterprises |date=15 August 2011 |accessdate=06 September 2013}}{{Dead link |fix-attempted=yes}}</ref> The theory—at least on paper—has been that prices should decrease as LIMS become commodities that labs can compare and contrast in a more competitive fashion. However, it remains to be seen if that will ever be the case.
:clinical research labs<ref name=":0">{{Cite journal |last=Damiani |first=A. |last2=Masciocchi |first2=C. |last3=Lenkowicz |first3=J. |last4=Capocchiano |first4=N. D. |last5=Boldrini |first5=L. |last6=Tagliaferri |first6=L. |last7=Cesario |first7=A. |last8=Sergi |first8=P. |last9=Marchetti |first9=A. |last10=Luraschi |first10=A. |last11=Patarnello |first11=S. |date=2021-12-07 |title=Building an Artificial Intelligence Laboratory Based on Real World Data: The Experience of Gemelli Generator |url=https://www.frontiersin.org/articles/10.3389/fcomp.2021.768266/full |journal=Frontiers in Computer Science |volume=3 |pages=768266 |doi=10.3389/fcomp.2021.768266 |issn=2624-9898}}</ref>
:hospitals<ref name=":0" /><ref name=":1">{{Cite journal |last=University of California, San Francisco |last2=Adler-Milstein |first2=Julia |last3=Aggarwal |first3=Nakul |last4=University of Wisconsin-Madison |last5=Ahmed |first5=Mahnoor |last6=National Academy of Medicine |last7=Castner |first7=Jessica |last8=Castner Incorporated |last9=Evans |first9=Barbara J. |last10=University of Florida |last11=Gonzalez |first11=Andrew A. |date=2022-09-29 |title=Meeting the Moment: Addressing Barriers and Facilitating Clinical Adoption of Artificial Intelligence in Medical Diagnosis |url=https://nam.edu/meeting-the-moment-addressing-barriers-and-facilitating-clinical-adoption-of-artificial-intelligence-in-medical-diagnosis |journal=NAM Perspectives |volume=22 |issue=9 |doi=10.31478/202209c |pmc=PMC9875857 |pmid=36713769}}</ref>
:medical diagnostics labs<ref name=":1" /><ref name=":12">{{Cite web |last=Government Accountability Office (GAO); National Academy of Medicine (NAM) |date=September 2022 |title=Artificial Intelligence in Health Care: Benefits and Challenges of Machine Learning Technologies for Medical Diagnostics |url=https://www.gao.gov/assets/gao-22-104629.pdf |format=PDF |publisher=Government Accountability Office |accessdate=16 February 2023}}</ref><ref name=":13">{{Cite journal |last=Wen |first=Xiaoxia |last2=Leng |first2=Ping |last3=Wang |first3=Jiasi |last4=Yang |first4=Guishu |last5=Zu |first5=Ruiling |last6=Jia |first6=Xiaojiong |last7=Zhang |first7=Kaijiong |last8=Mengesha |first8=Birga Anteneh |last9=Huang |first9=Jian |last10=Wang |first10=Dongsheng |last11=Luo |first11=Huaichao |date=2022-09-24 |title=Clinlabomics: leveraging clinical laboratory data by data mining strategies |url=https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-022-04926-1 |journal=BMC Bioinformatics |language=en |volume=23 |issue=1 |pages=387 |doi=10.1186/s12859-022-04926-1 |issn=1471-2105 |pmc=PMC9509545 |pmid=36153474}}</ref><ref name=":7">{{Cite journal |last=DeYoung |first=B. |last2=Morales |first2=M. |last3=Giglio |first3=S. |date=2022-08-04 |title=Microbiology 2.0–A “behind the scenes” consideration for artificial intelligence applications for interpretive culture plate reading in routine diagnostic laboratories |url=https://www.frontiersin.org/articles/10.3389/fmicb.2022.976068/full |journal=Frontiers in Microbiology |volume=13 |pages=976068 |doi=10.3389/fmicb.2022.976068 |issn=1664-302X |pmc=PMC9386241 |pmid=35992715}}</ref><ref name=":5">{{Cite web |last=Schut, M. |date=01 December 2022 |title=Get better with bytes |url=https://www.amsterdamumc.org/en/research/news/get-better-with-bytes.htm |publisher=Amsterdam UMC |accessdate=16 February 2023}}</ref><ref name="AlbanoCal19">{{cite web |url=https://physicianslab.com/calculations-to-diagnosis-the-artificial-intelligence-shift-thats-already-happening/ |title=Calculations to Diagnosis: The Artificial Intelligence Shift That’s Already Happening |author=Albano, V.; Morris, C.; Kent, T. |work=Physicians Lab |date=06 December 2019 |accessdate=16 February 2023}}</ref>
:chromatography labs<ref name="AlbanoCal19" />
:biology and life science labs<ref name=":6">{{Cite journal |last=de Ridder |first=Dick |date=2019-01 |title=Artificial intelligence in the lab: ask not what your computer can do for you |url=https://onlinelibrary.wiley.com/doi/10.1111/1751-7915.13317 |journal=Microbial Biotechnology |language=en |volume=12 |issue=1 |pages=38–40 |doi=10.1111/1751-7915.13317 |pmc=PMC6302702 |pmid=30246499}}</ref>
:medical imaging centers<ref name="Brandao-de-ResendeAIWeb22">{{cite web |url=https://siim.org/page/22w_clinical_adoption_of_ai |title=AI Webinar: Clinical Adoption of AI Across Image Producing Specialties |author=Brandao-de-Resende, C.; Bui, M.; Daneshjou, R. et al. |publisher=Society for Imaging Informatics in Medicine |date=11 October 2022}}</ref>
:ophthalmology clinics<ref>{{Cite journal |last=He |first=Mingguang |last2=Li |first2=Zhixi |last3=Liu |first3=Chi |last4=Shi |first4=Danli |last5=Tan |first5=Zachary |date=2020-07 |title=Deployment of Artificial Intelligence in Real-World Practice: Opportunity and Challenge |url=https://journals.lww.com/10.1097/APO.0000000000000301 |journal=Asia-Pacific Journal of Ophthalmology |language=en |volume=9 |issue=4 |pages=299–307 |doi=10.1097/APO.0000000000000301 |issn=2162-0989}}</ref>
:reproduction clinics<ref name=":9">{{Cite journal |last=Trolice |first=Mark P. |last2=Curchoe |first2=Carol |last3=Quaas |first3=Alexander M |date=2021-07 |title=Artificial intelligence—the future is now |url=https://link.springer.com/10.1007/s10815-021-02272-4 |journal=Journal of Assisted Reproduction and Genetics |language=en |volume=38 |issue=7 |pages=1607–1612 |doi=10.1007/s10815-021-02272-4 |issn=1058-0468 |pmc=PMC8260235 |pmid=34231110}}</ref><ref name="ESHREArti22">{{cite web |url=https://www.focusonreproduction.eu/article/ESHRE-News-22AI |title=Annual Meeting 2022: Artificial intelligence in embryology and ART |author=European Society of Human Reproduction and Embryology |work=Focus on Reproduction |date=06 July 2022 |accessdate=16 February 2023}}</ref><ref name="HinckleyApply21">{{cite web |url=https://rscbayarea.com/blog/applying-ai-for-better-ivf-success |title=Applying AI (Artificial Intelligence) in the Lab for Better IVF Success |author=Hinckley, M. |work=Reproductive Science Center Blog |publisher=Reproductive Science Center of the Bay Area |date=17 March 2021 |accessdate=16 February 2023}}</ref>
:digital pathology labs<ref name="YousifArt21">{{cite web |url=https://clinlabint.com/artificial-intelligence-is-the-key-driver-for-digital-pathology-adoption/ |title=Artificial intelligence is the key driver for digital pathology adoption |author=Yousif, M.; McClintock, D.S.; Yao, K. |work=Clinical Laboratory Int |publisher=PanGlobal Media |date=2021 |accessdate=16 February 2023}}</ref>
:material testing labs<ref name=":2">{{Cite journal |last=MacLeod |first=B. P. |last2=Parlane |first2=F. G. L. |last3=Morrissey |first3=T. D. |last4=Häse |first4=F. |last5=Roch |first5=L. M. |last6=Dettelbach |first6=K. E. |last7=Moreira |first7=R. |last8=Yunker |first8=L. P. E. |last9=Rooney |first9=M. B. |last10=Deeth |first10=J. R. |last11=Lai |first11=V. |date=2020-05-15 |title=Self-driving laboratory for accelerated discovery of thin-film materials |url=https://www.science.org/doi/10.1126/sciadv.aaz8867 |journal=Science Advances |language=en |volume=6 |issue=20 |pages=eaaz8867 |doi=10.1126/sciadv.aaz8867 |issn=2375-2548 |pmc=PMC7220369 |pmid=32426501}}</ref><ref name=":3">{{Cite journal |last=Chibani |first=Siwar |last2=Coudert |first2=François-Xavier |date=2020-08-01 |title=Machine learning approaches for the prediction of materials properties |url=http://aip.scitation.org/doi/10.1063/5.0018384 |journal=APL Materials |language=en |volume=8 |issue=8 |pages=080701 |doi=10.1063/5.0018384 |issn=2166-532X}}</ref><ref name="MullinTheLab21">{{Cite journal |last=Mullin, R. |date=28 March 2021 |title=The lab of the future is now |url=http://cen.acs.org/business/informatics/lab-future-ai-automated-synthesis/99/i11 |journal=Chemical & Engineering News |volume=99 |issue=11 |archiveurl=https://web.archive.org/web/20220506192926/http://cen.acs.org/business/informatics/lab-future-ai-automated-synthesis/99/i11 |archivedate=06 May 2022 |accessdate=16 February 2023}}</ref>
:chemical experimentation and molecular discovery labs<ref name="MullinTheLab21" /><ref name=":4">{{Cite journal |last=Burger |first=Benjamin |last2=Maffettone |first2=Phillip M. |last3=Gusev |first3=Vladimir V. |last4=Aitchison |first4=Catherine M. |last5=Bai |first5=Yang |last6=Wang |first6=Xiaoyan |last7=Li |first7=Xiaobo |last8=Alston |first8=Ben M. |last9=Li |first9=Buyi |last10=Clowes |first10=Rob |last11=Rankin |first11=Nicola |date=2020-07-09 |title=A mobile robotic chemist |url=https://www.nature.com/articles/s41586-020-2442-2.epdf?sharing_token=HOkIS6P5VIAo2_l3nRELmdRgN0jAjWel9jnR3ZoTv0Nw4yZPDO1jBpP52iNWHbb8TakOkK906_UHcWPTvNxCmzSMpAYlNAZfh29cFr7WwODI2U6eWv38Yq2K8odHCi-qwHcEDP18OjAmH-0KgsVgL5CpoEaQTCvbmhXDSyoGs6tIMe1nuABTeP58z6Ck3uULcdCtVQ66X244FsI7uH8GnA%3D%3D&tracking_referrer=cen.acs.org |journal=Nature |language=en |volume=583 |issue=7815 |pages=237–241 |doi=10.1038/s41586-020-2442-2 |issn=0028-0836}}</ref><ref name="LemonickExplore20">{{Cite journal |last=Lemonick, S. |date=06 April 2020 |title=Exploring chemical space: Can AI take us where no human has gone before? |url=https://cen.acs.org/physical-chemistry/computational-chemistry/Exploring-chemical-space-AI-take/98/i13 |journal=Chemical & Engineering News |volume=98 |issue=13 |archiveurl=https://web.archive.org/web/20200729004137/https://cen.acs.org/physical-chemistry/computational-chemistry/Exploring-chemical-space-AI-take/98/i13 |archivedate=29 July 2020 |accessdate=16 February 2023}}</ref>
:quantum physics labs<ref name="DoctrowArti19">{{cite web |url=https://www.pnas.org/post/podcast/artificial-intelligence-laboratory |title=Artificial intelligence in the laboratory |author=Doctrow, B. |work=PNAS Science Sessions |date=16 December 2019 |accessdate=16 February 2023}}</ref>


Laboratories are, by their very nature, in the business of producing analytical data and reports, essentially [[information]].<ref name="IFlowJourn">{{cite journal |journal=Administrative Science Quarterly |year=1969 |volume=14 |issue=1 |pages=12–19 |title=Information Flow in Research and Development Laboratories |author=Allen, Thomas J.; Cohen, Stephen I. |url=http://www.jstor.org/stable/2391357 |doi=10.2307/2391357}}</ref> Everything else that occurs in the laboratory is largely just a means towards that central goal of producing timely, accurate, and unbiased information. As such, in a very real sense, [[information management]] is, by extension, also at the core of any lab. In a world where we use the latest technology for most of our daily tasks and pleasures, why do so many labs still rely on hand-written notes and spreadsheets? Why do they still spend thousands of dollars on a sophisticated analytical instrument yet hesitate when faced with purchasing an information management system? The primary reason has traditionally been the cost associated with acquiring an informatics solution, as well as not having the information technology resources to properly implement it.<ref name="CHCFELINCS14">{{cite web |url=https://www.chcf.org/project/elincs-the-national-lab-data-standard-for-electronic-health-records/ |title=ELINCS: The National Lab Data Standard for Electronic Health Records |author=California Health Care Foundation |date=19 March 2014 |accessdate=31 January 2023}}</ref><ref name="JapsenDespite14">{{cite web |url=https://www.forbes.com/sites/brucejapsen/2014/03/29/despite-stimulus-dollars-hundreds-of-hospitals-still-use-mostly-paper-records/?sh=25c7b0364c19 |title=Despite Stimulus Dollars, Hundreds Of Hospitals Still Use Mostly Paper Records |author=Japsen, B. |work=Forbes |date=29 March 2014 |accessdate=31 January 2023}}</ref><ref name="ColangeliSILAB19">{{Cite journal |last=Colangeli |first=Patrizia |last2=Del Negro |first2=Ercole |last3=Molini |first3=Umberto |last4=Malizia |first4=Sara |last5=Scacchia |first5=Massimo |date=2019-12-01 |title=“SILAB for Africa”: An Innovative Information System Supporting the Veterinary African Laboratories |url=https://www.liebertpub.com/doi/10.1089/tmj.2018.0208 |journal=Telemedicine and e-Health |language=en |volume=25 |issue=12 |pages=1216–1224 |doi=10.1089/tmj.2018.0208 |issn=1530-5627}}</ref>
*What's going on in these labs?


Software solutions like LIMS are increasingly becoming commodities, and potential buyers don't need to find the acquisition process as daunting as it used to be. As technology has improved, smaller LIMS companies have emerged, along with affordable [[Cloud computing|cloud-based]] [[software as a service|SaaS]] options that are flexible and reliable. This means any lab can put their resources where they belong: into its analytical information and its management.
:'''Materials science''': The creation of "a modular robotic platform driven by a model-based optimization algorithm capable of autonomously optimizing the optical and electronic properties of thin-film materials by modifying the film composition and processing conditions ..."<ref name=":2" />
:'''Materials science''': "Most of the applications of [machine learning (ML)] in chemical and materials sciences, as we have said, feature supervised learning algorithms. The goal there is to supplement or replace traditional modeling methods, at the quantum chemical or classical level, in order to predict the properties of molecules or materials directly from their structure or their chemical composition ... Our research group was applying the same idea on a narrower range of materials, trying to confirm that for a given chemical composition, geometrical descriptors of a material’s structure could lead to accurate predictions of its mechanical features."<ref name=":3" />
:'''Life science''': "In biological experiments, we generally cannot as easily declare victory, but we can use the systems biology approach of cycling between experimentation and modelling to see which sequences, when tested, are most likely to improve the model. In artificial intelligence, this is called active learning, and it has some similarity to the way in which we as humans learn as infants: we get some help from parents and teachers, but mainly model the world around us by exploring it and interacting with it. Ideally then, we would recreate such an environment for our machine learning algorithms in the laboratory, where we start with an initial ‘infant’ model of a certain regulatory system or protein function and let the computer decide what sequence designs to try out – a deep learning version of the ‘robot scientist’. Microbes are ideal organisms for such an approach, given the ease and speed with which they can be grown and genetically manipulated. Combined with laboratory automation, many microbial experiments can (soon) be performed with minimal human intervention, ranging from strain construction and screening, such as operated by Amyris, Gingko, Transcriptic, etc., to full-genome engineering or even the design of microbial ecologies."<ref name=":6" />
:'''Digital pathology''': "The collaboration combines two AI solutions, VistaPath’s Sentinel, the world’s first automated tissue grossing platform, and Gestalt’s AI Requisition Engine (AIRE), a leading-edge AI algorithm for accessioning, to raise the bar in AI-driven pathology digitization. Designed to make tissue grossing faster and more accurate, VistaPath’s Sentinel uses a high-quality video system to assess specimens and create a gross report 93% faster than human technicians with 43% more accuracy. It not only improves on quality by continuously monitoring the cassette, container, and tissue to reduce mislabeling and specimen mix-up, but also increases traceability by retaining original images for downstream review."<ref>{{Cite web |last=VistaPath |date=28 July 2022 |title=VistaPath Launches New Collaboration with Gestalt Diagnostics to Further Accelerate Pathology Digitization |work=PR Newswire |url=https://www.prnewswire.com/news-releases/vistapath-launches-new-collaboration-with-gestalt-diagnostics-to-further-accelerate-pathology-digitization-301594718.html |publisher=Cision US Inc |accessdate=17 February 2023}}</ref>
:'''Chemistry and molecular science''': "The benefits of combining automated experimentation with a layer of artificial intelligence (AI) have been demonstrated for flow reactors, photovoltaic films, organic synthesis, perovskites and in formulation problems. However, so far no approaches have integrated mobile robotics with AI for chemical experiments. Here, we built Bayesian optimization into a mobile robotic workflow to conduct photocatalysis experiments within a ten-dimensional space."<ref name=":4" />
:'''Chemistry and immunology''': "Chemistry and immunology laboratories are particularly well-suited to leverage machine learning because they generate large, highly structured data sets, Schulz and others wrote in a separate review paper. Labor-intensive processes used for interpretation and quality control of electrophoresis traces and mass spectra could benefit from automation as the technology improves, they said. Clinical chemistry laboratories also generate digital images—such as urine sediment analysis—that may be highly conducive to semiautomated analyses, given advances in computer vision, the paper noted."<ref name=":8">{{Cite web |last=Blum, K. |date=01 January 2023 |title=A Status Report on AI in Laboratory Medicine |work=Clinical Laboratory News |url=https://www.aacc.org/cln/articles/2023/janfeb/a-status-report-on-ai-in-laboratory-medicine |publisher=American Association for Clinical Chemistry |accessdate=17 February 2023}}</ref>
:'''Clinical research''': "... retrospective analysis of existing patient data for descriptive and clustering purposes [and] automation of knowledge extraction, ranging from text mining, patient selection for trials, to generation of new research hypotheses ..."<ref name=":0" />
:'''Clinical research''': "AI ... offers a further layer to the laboratory system by analyzing all experimental data collected by experiment devices, whether it be a sensor or a collaborative robot. From data collected, AI is able to produce hypotheses and predict which combination of materials or temperature is desired for the experiment. In short, this system will allow scientists to be aided by a highly intelligent system which is constantly monitoring and analyzing the experimental output. In this way, AI will help an experiment from its inception to conclusion."<ref>{{Cite web |last=Chubb, P. |date=03 November 2020 |title=How disruptive technology is helping laboratories combat COVID-19 |url=https://datafloq.com/read/disruptive-technologies-lab-help-us-prepare-future-pandemics/ |publisher=Datafloq |accessdate=16 February 2023}}</ref>
:'''Clinical research/medical diagnostics''': "Artificial intelligence (AI) in the laboratory is primarily used to make sense of big data, the almost impossibly large sets of data that biologists and pharmaceutical R&D teams are accustomed to working with. AI algorithms can parse large amounts of data in a short amount of time and turn that data into visualizations that viewers can easily understand. In certain data-intensive fields, such as genomic testing and virus research, AI algorithms are the best way to sort through the data and do some of the pattern recognition work."<ref>{{Cite web |last=Stewart, B. |date=18 March 2021 |title=Using LIMS for Data Visualization |work=CSols Insights |url=https://www.csolsinc.com/insights/published-articles/using-lims-for-data-visualization/ |publisher=CSols, Inc |accessdate=17 February 2023}}</ref>
:'''Medical diagnostics''': Development and implementation of [[Clinical decision support system|clinical decision support systems]] <ref name=":0" /><ref name=":1" />
:'''Medical diagnostics''': "Finally, in the laboratory, AI reduces the number of unnecessary blood samples when diagnosing infection. Instead of the 'gold standard blood sample' that takes 24-72 hours, the algorithm can predict the outcome of the blood sample with almost 80% accuracy based on demographics, vital signs, medications, and laboratory and radiology results. These are all examples of how Artificial Intelligence can be used to test better and faster with information that already exists. This saves time and costs."<ref name=":5" />
:'''Medical diagnostics''': "Chang sees two overarching classes of AI models: those that tackle internal challenges in the lab, such as how to deliver more accurate results to clinicians; and those that seek to identify cohorts of patients and care processes to close quality gaps in health delivery systems. The lab, however, 'isn’t truly an island,' said Michelle Stoffel, MD, PhD, associate chief medical information officer for laboratory medicine and pathology at M Health Fairview and the University of Minnesota in Minneapolis. 'When other healthcare professionals are working with electronic health records or other applications, there could be AI-driven tools, or algorithms used by an institution’s systems that may draw on laboratory data.'"<ref name=":8" />
:'''Medical diagnostics''': AI is used for the formulation of reference ranges, improvement of quality control, and automated interpretation of results. "Continuous monitoring of specimen acceptability, collection and transport can result in the prompt identification and correction of problems, leading to improved patient care and a reduction in unnecessary redraws and delays in reporting results."<ref name=":13" />
:'''Reproduction science''': "The field of AI is the marriage of humans and computers while reproductive medicine combines clinical medicine and the scientific laboratory of embryology. The application of AI has the potential to disconnect healthcare professionals from patients through algorithms, automated communication, and clinical imaging. However, in the embryology laboratory, AI, with its focus on gametes and embryos, can avoid the same risk of distancing from the patient. Areas of application of AI in the laboratory would be to enhance and automate embryo ranking through analysis of images, the ultimate goal being to predict successful implantation. Might such a trend obviate the need for embryo morphological assessment, time-lapse imaging and preimplantation genetic testing for aneuploidy (PGT-A), including mosaicism. Additionally, AI could assist with automation through analysis of testicular sperm samples searching for viable gametes, embryo grading uniformity."<ref name=":9" />
:'''Chromatography-heavy sciences''': " A great example of this is AI in the Liquid Chromatography Mass Spectrometry (LC-MS) field. LC-MS is a great tool used to measure various compounds in the human body, including everything from hormone levels to trace metals. One of the ways AI has already integrated with LC-MS is how it cuts down on the rate limiting steps of LC-MS, which more often than not are sample prep and LC separations. One system that Physicians Lab has made use of is parallel processing using SCIEX MPX 2.0 High Throughput System. This system can couple parallel runs with one LCMS instrument, resulting in twice the speed with no loss to accuracy. It can do this by staggering two runs either using the same method, or different methods entirely. What really makes this system great is its ability to automatically detect carryover and inject solvent blanks to clean the instrument. The system will then continue its analyzing, while automatically reinjecting samples that may be affected by the carryover. It will also flag high concentration without user input, allowing for easy detection of possibly faulty samples. This allows it to operate without users from startup to shut down. Some of the other ways that it can be used to increase efficiency are by using integrated network features to work on anything from streamlining management to increased throughput."<ref name="AlbanoCal19" />
:'''Most any lab''': "Predictive analytics, for example, is one tool that the Pistoia Alliance is using to better understand laboratory instruments and how they might fail over time... With the right data management strategies and careful consideration of metadata, how to best store data so that it can be used in future AI and ML workflows is essential to the pursuit of AI in the laboratory. Utilizing technologies such as LIMS and ELN enables lab users to catalogue data, providing context and instrument parameters that can then be fed into AI or ML systems. Without the correct data or with mismatched data types, AI and ML will not be possible, or at the very least, could provide undue bias trying to compare data from disparate sources."<ref>{{Cite web |date=29 January 2021 |title=Data Analytics |work=Scientific Computing World - Building a Smart Laboratory 2020 |url=https://www.scientific-computing.com/feature/data-analytics-0 |publisher=Europa Science Ltd |accessdate=17 February 2023}}</ref>
:'''Most any lab''': "When the actionable items are automatically created by Optima, the 'engine' starts working. An extremely sophisticated algorithm is able to assign the tasks to the resources, both laboratory personnel and instruments, according to the system configuration. Optima, thanks to a large amount of time dedicated to research the best way to automate this critical process, is able to automate most of the lab resource scheduling."<ref>{{Cite web |last=Optima Team |date=15 December 2020 |title=The concept of machine learning applied to lab resources scheduling |work=Optima Blog |url=https://www.optima.life/blog/the-concept-of-machine-learning-applied-to-lab-resources-scheduling/ |publisher=Optima PLC Tracking Tools S.L |accessdate=17 February 2023}}</ref>


This brief buyer's guide is here to help you take the first steps towards acquiring a laboratory informatics solution. Use these vendor profiles and recommendations to get a feel for what's out there and what makes the most sense. This guide contains information on a little bit of everything, from discovering what a LIMS is to maintaining and supporting that system. While the LIMS is the stand-out solution among the crowd for laboratories, this guide may also reference other systems like a LIS or [[electronic laboratory notebook]] (ELN).  
*A number of challenges exist in the realm of effectively and securely implementing AI in the laboratory. This includes:


:Ethical and privacy challenges<ref name=":0" /><ref name=":8" /><ref name=":10" />
:Algorithmic limitations<ref name=":11" />
:Data access limitations, including "where to get it, how to share it, and how to know when you have enough to train a machine-learning system that will produce good results"<ref name=":11" /><ref name=":8" /><ref name=":14">{{Cite web |last=Sherwood, L. |date=10 February 2022 |title=SLAS 2022: Barriers remain to AI adoption in life sciences |work=LabPulse.com Showcasts |url=https://www.labpulse.com/showcasts/slas/2022/article/15300130/slas-2022-barriers-remain-to-ai-adoption-in-life-sciences |publisher=Science and Medicine Group |accessdate=17 February 2023}}</ref><ref name=":15">{{Cite journal |last=Bellini |first=Claudia |last2=Padoan |first2=Andrea |last3=Carobene |first3=Anna |last4=Guerranti |first4=Roberto |date=2022-11-25 |title=A survey on Artificial Intelligence and Big Data utilisation in Italian clinical laboratories |url=https://www.degruyter.com/document/doi/10.1515/cclm-2022-0680/html |journal=Clinical Chemistry and Laboratory Medicine (CCLM) |language=en |volume=60 |issue=12 |pages=2017–2026 |doi=10.1515/cclm-2022-0680 |issn=1434-6621}}</ref>
:Data integration and transformation issues<ref name=":0" /><ref name=":15" />
:Regulatory barriers<ref name=":11" /><ref name=":12" />
:Misaligned incentives<ref name=":11" />
:Lack of knowledgeable/skilled talent<ref name=":0" /><ref name=":8" /><ref name=":14" /><ref name=":15" />
:Cost of skilled talent and infrastructure for maintaining and updating AI systems<ref name=":8" />
:Legacy systems running outdated technologies<ref name=":14" />
:Lack of IT systems or specialized software systems<ref name=":15" />
:Lack of standardized, best practices-based methods of validating algorithms<ref name=":8" />
:Failure to demonstrate real-world performance<ref name=":12" />
:Failure to meet the needs of the professionals using it<ref name=":12" />


==2. How does laboratory software benefit the lab?==
*Given those challenges, some considerations should be made about implementing AI-based components in the laboratory. Examples include:
Laboratory, scientific, and healthcare informatics solutions can improve laboratory [[workflow]]s while enhancing safety, quality, and compliance in a number of ways. A LIMS, for example, is often adopted to eliminate manual processes, improve sample management, increase productivity, and improve regulatory conformance.<ref name="Astrix2020LIMS">{{cite web |url=https://astrixinc.com/wp-content/uploads/2021/03/Astrix-2020-LIMS-Market-Research-Report.pdf |format=PDF |title=Astrix 2020 LIMS Market Research Survey Report |publisher=Astrix Technology, LLC |date=March 2021 |accessdate=01 February 2023}}</ref> The adoption of LIMS and other such systems to eliminate deficiencies and improve operations is often based in the disadvantages of paper-based processes—particularly in regulatory environments—and their inability at making their contents rapidly findable, searchable, modifiable, and secure.<ref name="LiscouskiLabTech20">{{cite web |url=https://www.limswiki.org/index.php/LII:Laboratory_Technology_Planning_and_Management:_The_Practice_of_Laboratory_Systems_Engineering |title=Laboratory Technology Planning and Management: The Practice of Laboratory Systems Engineering |author=Liscouski, J. |work=LIMSwiki |date=December 2020 |accessdate=01 February 2023}}</ref><ref name="LiscouskiTheApp21">{{cite web |url=https://www.limswiki.org/index.php/LII:The_Application_of_Informatics_to_Scientific_Work:_Laboratory_Informatics_for_Newbies |title=The Application of Informatics to Scientific Work: Laboratory Informatics for Newbies |author=Liscouski, J. |work=LIMSwiki |date=April 2021 |accessdate=01 February 2023}}</ref>


Even a fragmented mix of paper-based and electronic information sources can be a detriment to the traceability of or rapid accessibility to quality control samples, standard operating procedures (SOPs), calibration data, chain of custody data, and other vital aspects of analytical, sampling, and calibration testing in the lab. A well-implemented LIMS can reduce the silos of data and information, while at the same time make that information and data more secure and readily accessible. Given the demands placed on laboratories—by [[ISO/IEC 17025]] and clients seeking labs certified to that standard, for example—to provide rapid proof of traceable sample movement and relevant quality control data, integrating a LIMS into the laboratory makes sense. The LIMS can act as the central integrator and audit trail for all that laboratory data and information.<ref name="SmithInteg19">{{cite web |url=https://foodsafetytech.com/feature_article/integrated-informatics-optimizing-food-quality-and-safety-by-building-regulatory-compliance-into-the-supply-chain/ |title=Integrated Informatics: Optimizing Food Quality and Safety by Building Regulatory Compliance into the Supply Chain |author=Smith, K. |work=Food Safety Tech |date=02 July 2019 |accessdate=20 January 2023}}</ref><ref name="McDermottHowDig18">{{cite web |url=https://foodsafetytech.com/column/how-digital-solutions-support-supply-chain-transparency-and-traceability/ |title=How Digital Solutions Support Supply Chain Transparency and Traceability |author=McDermott, P. |work=Food Safety Tech |date=31 July 2018 |accessdate=20 January 2023}}</ref><ref name="EvansTheDig19">{{cite web |url=https://foodsafetytech.com/feature_article/the-digital-transformation-of-global-food-security/ |title=The Digital Transformation of Global Food Security |author=Evans, K. |work=Food Safety Tech |date=15 November 2019 |accessdate=20 January 2023}}</ref> Because the LIMS improves traceability—including through its automated interfaces with instruments and other data systems—real-time monitoring of supply chain issues, quality control data, instrument use, and more is further enabled, particularly when paired with configurable dashboards and alert mechanisms. By extension, labs can more rapidly act on insights gained from those real-time dashboards.<ref name="SmithInteg19" />  
:'''Clinical diagnostics''': "From an industry and regulatory perspective, however, only the intended uses supported from the media manufacturer can be supported from AI applications, unless otherwise justified and substantive evidence is presented for additional claims support. This means strict adherence to specimen type and incubation conditions. Considering that the media was initially developed for human assessment using the well-trained microbiologist eye, and not an advanced imaging system with or without AI, this paradigm should shift to allow advancements in technology to challenge the status-quo of decreasing media read-times especially, as decreased read-times assist with laboratory turnaround times and thus patient management. Perhaps with an increasing body of evidence to support any proposed indications for use, either regulatory positions should be challenged, or manufacturers of media and industry AI-development specialists should work together to advance the field with new indications for use.
 
:While the use of AI in the laboratory setting can be highly beneficial there are still some issues to be addressed. The first being phenotypically distinct single organism polymorphisms that may be interpreted by AI as separate organisms, as may also be the case for a human assessment, as well as small colony variant categorization. As detailed earlier, the broader the inputs, the greater the generalization of the model, and the higher the likelihood of algorithm accuracy. In that respect, understanding and planning around these design constraints is critical for ultimate deployment of algorithms. Additionally, expecting an AI system to correctly categorize “contamination” is a difficult task as often this again seemingly innocuous decision is dependent on years of experience and understanding the specimen type and the full clinical picture with detailed clinical histories. In this respect, a fully integrated AI-LIS system where all data is available may assist, but it is currently not possible to gather this granular detail needed to make this assessment reliable."<ref name=":7" />
There is a growing variety of laboratory informatics software providing these and other benefits to labs, allowing them to more rapidly adapt and remain competitive. Arguably, the most common solutions are the LIMS and LIS. The LIMS and LIS are similar, in that they focus on the entire laboratory process and improving the various aspects of it. Traditionally, the LIMS has been used in more non-clinical environments and the LIS in more clinical environments, but that distinction has been fading for well over a decade. These distinctions have blurred even more with the age of modular and platformed software solutions that are able to adapt to most any industry. For now, just know that these systems are a bit more holistic, placing the focus on improving your lab's workflows, which in turn strengthens traceability, analytical outcomes, and—in the case of clinical settings—patient outcomes. Outside of that, there are other more specialized solutions, including:
:'''Clinical diagnostics and pathology''': "Well, if I’ve learned anything in my research into this topic, it’s that AI implementation needs to be a two-way street. First, any company who is active in this space must reach out to pathologists and laboratory medicine professionals to understand their daily workflows, needs, and pain points in as much detail as possible. Second, pathologists, laboratory medicine professionals, and educators must all play their important part – willingly offering their time and expertise when it is sought or proactively getting involved. And finally, it’s clear that there is an imbalanced focus on certain issues – with privacy, respect, and sustainability falling by the wayside."<ref name=":10">{{Cite web |last=Lee, G.F. |date=10 October 2022 |title=The Robot May See You Now: It’s time to stop and think about the ethics of artificial intelligence |work=The Pathologist |url=https://thepathologist.com/outside-the-lab/the-robot-may-see-you-now |accessdate=17 February 2023}}</ref>
 
:'''Healthcare''': "While we are encouraged by the promise shown by AI in healthcare, and more broadly welcome the use of digital technologies in improving clinical outcomes and health system productivity, we also recognize that caution must be exercised when introducing any new healthcare technology. Working with colleagues across the NHS Transformation Directorate, as well as the wider AI community, we have been developing a framework to evaluate AI-enabled solutions in the health and care policy context. The aim of the framework is several-fold but is, at its core, a tool with which to highlight to healthcare commissioners, end users, patients and members of the public the considerations to be mindful when introducing AI to healthcare settings."<ref>{{Cite journal |last=Chada |first=Bharadwaj V |last2=Summers |first2=Leanne |date=2022-10-10 |title=AI in the NHS: a framework for adoption |url=https://www.rcpjournals.org/lookup/doi/10.7861/fhj.2022-0068 |journal=Future Healthcare Journal |language=en |pages=fhj.2022–0068 |doi=10.7861/fhj.2022-0068 |issn=2514-6645 |pmc=PMC9761451 |pmid=36561823}}</ref>
* the ELN, which is used in many research and development environments (among others) as a means to securely and collaboratively document experiments and their results;
:'''Most any lab''': A code of AI ethics should address objectivity, privacy, transparency, accountability, and sustainability in any AI implementation.<ref name=":10" />
* the [[laboratory execution system]] (LES), which is used in production-based environments to ensure the rigidity of a method and and the process' end result;
:'''Most any lab''': "Another approach is to implement an AI program alongside a manual process, assessing its performance along the way, as a means to ease into using the program. 'I think one of the most impactful things that laboratorians can do today is to help make sure that the lab data that they’re generating is as robust as possible, because these AI tools rely on new training sets, and their performance is really only going to be as good as the training data sets they’re given,' Stoffel said."<ref name=":8" />
* the [[chromatography data system]] (CDS), which is used to accurately collect, process, and visualize [[chromatography]] data; and
* the [[scientific data management system]] (SDMS), which is used to collect disparate silos of data and information across the laboratory enterprise and make it more actionable.
 
While these systems can be found in many types of labs, some tendencies appear. LIMS, LIS, and ELN are top-level solutions that help the lab manage workflows, as well as aggregate and organize data and information, including analytical- and experiment-based results. In services labs, the ELN is less likely to appear. However, in the case of research labs, the ELN may function more top-level, with the LIMS acting as a supplementary system for managing test workflows before associated test results are loaded into the ELN. Support systems like the LES, CDS, and SDMS may also appear, filling specialized roles. The LES will appear in more regulated environments where laboratory procedures must be executed precisely, before then feeding results to a LIMS or ELN. The CDS will appear in labs doing heavy chromatography work, and it too may feed data into a LIMS or ELN. The SDMS appears in contexts where data and information produced by the lab don't fit in the structure of what a LIMS or ELN handles.
 
 
==3. How do I find the right solution for my needs?==
As indicated above, the type of solution you choose is based on your lab type (e.g., service, research, production), the tests predominately run (e.g., chromatography work, requiring a CDS), and the type of data and information generated and stored (e.g., non-standard files, requiring an SDMS). However, finding the right system to fit your labs needs isn't a straightforward process. While your lab may know its [[Regulatory compliance|regulatory]]-, workflow-, and standard-driven requirements, perhaps critical personnel don't know much about [[Information management|data management]] solutions like LIMS, leaving a lab's key stakeholders intimidated by all the options. You'll first need to gauge your lab's informatics needs in order to determine which products are worth investigating further. Of course your lab's analysis requirements, reporting and data sharing constraints, instrument interfacing needs, [[Barcode|barcoding]] and tracking requirements, quality assurance processes, etc. are certainly important factors. But vendors' systems vary in numerous ways, and other important factors exist. Of course, price is one consideration, although value is ultimately more important than a low price. Other important questions that get asked include:
 
*Should we purchase software licenses or "rent" the software via a subscription-based model?
*Does the software need to be on-site, or is a [[Software as a service|SaaS]] hosted option more practical?
*Is a modular or complete system better for us?
*What is the best licensing/rental scheme for us? Should we consider site, named user, concurrent user, or workstation licenses?
*Is the company qualified and trustworthy?
*What functionality is available to help our lab remain compliant with the a variety of standards and regulations?
 
===3.1 Technology considerations===
Your laboratory's workflow, instruments, data management requirements, budget, technological expertise, business goals, and [[Risk management|risk tolerances]] will all play a role in deciding what technology to invest in. Your lab will also be interested in how that technology not only helps with workflow requirements but also better assists the lab with meeting the requirements placed upon them by various standards and regulations, as well as management.
 
As part of this discovery process, many questions may arise. Chief among them may be how to best match the laboratory's goals with one or more informatics solutions. Does the laboratory envision a small investment and modest goals, taking in a slow but steady flow of analytical requests, or do they envision expansive growth, expanding into multiple testing domains? If the lab is starting small but is confidently expecting to grow, technological investments early on may want to take into account future technologies that may shape data management and security processes. The lab will also want to account for how potential changes in standards and regulations may affect future expansion and technology needs.
 
Second, ask what kind of work will the lab be doing, and what regulatory responsibilities will guide hardware and software investment at the lab. If your lab will be conducting extractable and leachable testing, you'll be considering [[chromatography]] and [[spectroscopy]] instruments and software systems, as well as requirements for retaining analytical results for regulators. Those labs accredited to standards such as ISO/IEC 17025 will have additional needs for instruments and software systems; such labs' data management system will likely need to be sufficiently robust to meet the needs of the standard. For those labs in more regulated spaces, the system will even need to interface to government systems, or at a minimum report in the regulatory body's specific format. These and other considerations will need to be made.
 
Third, your laboratory's budget is always important. Does the budget allow for on-site hardware and software systems, with the personnel to maintain them? Is it easier to pay up-front or find a vendor willing to work with you on leasing or rental terms? Is their more value to be had from a slightly more expensive system able to provide the functionality that makes regulatory compliance more painless for the lab?
 
Finally, will the lab have someone on-site or on-call to resolve technology issues, including set-up and maintenance of software systems? If your lab will have little in the way of available tech help locally, you'll want to consider the distribution model you want to use for any installed software, i.e., you may want to consider [[software as a service]] (SaaS). An increasing number of software services are hosted using cloud computing, which when done well is an increasingly reliable option.<ref name="IzrailevskyCloud18">{{cite journal |title=Cloud Reliability |journal=IEEE Cloud Computing |author=Izrailevsky, Y.; Bell, C. |volume=5 |issue=3 |pages=39–44 |year=2018 |doi=10.1109/MCC.2018.032591615}}</ref> Having someone else host the software for you typically means the hosting provider will carry a non-trivial portion of responsibility for technology maintenance and security.
 
Speaking of security, you'll also want to consider the [[cybersecurity]] of not only your software solution but also your overall laboratory operations. Does your organization have a cybersecurity plan already in place, or has the decision to make one been postponed? What extra investment is required to ensure your sensitive data is secure? How do your cybersecurity goals compare to the demands of standards like ISO/IEC 17025? Remember that how you rank your cybersecurity preparedness and implement a cybersecurity plan will also guide your technology investment decisions.<ref name="DouglasComp20">{{cite web |title=[[LII:Comprehensive Guide to Developing and Implementing a Cybersecurity Plan|''Comprehensive Guide to Developing and Implementing a Cybersecurity Plan'']] |author=Douglas, S.E. |work=LIMSwiki |date=July 2020 |accessdate=20 January 2023}}</ref>
 
===3.2 Functionality considerations===
Technology aside, the lab will also want to consider the functionality of the various laboratory informatics solutions offered by vendors. Some laboratorians may already be familiar with the LIMS or ELN and understand what it is capable of doing for the lab. However, others may have little familiarity with such systems and have only vague concepts of how they function. Either way, it's useful for the lab to gain a clearer understanding of what such solutions can do. There are several ways to go about this, from reading through examples of user requirements documents to participating in demonstrations of software from various vendors. In fact, both methods remain useful, and a standard approach to acquisition will usually include both. In the end, the question for any prospective vendor to answer is "how can your solution meet our laboratory's requirements?" This is where functionality comes in.
 
The follow sections will look at functionality considerations first by introducing the user requirements specification (URS) as a means of learning more about system functionality. From there we'll look specifically at a LIMS and what its core and ancillary features look like, before finally re-addressing the URS from the perspective of how it can be implemented to full effect.
 
====3.2.1 The user requirements specification as a functionality guide====
A specification is "a detailed precise presentation of something or of a plan or proposal for something."<ref name="MWSpec">{{cite web |url=https://www.merriam-webster.com/dictionary/specification |title=specification |work=Merriam-Webster |publisher=Merriam-Webster, Inc |accessdate=20 January 2023}}</ref> This concept of a specification as a presentation is critical to the laboratory seeking to find laboratory informatics software that fulfills their needs; they "present" their use case with the help of a requirements specification, and the vendor "presents" their ability (or inability) to comply through documentation and demonstration. However, even the most seasoned of presenters at conferences and the like still require quality preparation before the presentation. Similarly, your lab has work to do beforehand. This is where initial specification research comes into play for the lab.
 
Your lab's requirements specification document will eventually be a critical component for effectively selecting a laboratory informatics solution. For those labs with limited knowledge of what such a solution is capable of doing, building a URS can be especially useful. There are numerous ways to approach the overall development of a URS. But why re-invent the wheel when others have already gone down that road? Sure, you could search for examples of such documents on the internet and customize them to your needs, or you and your team could brainstorm how a laboratory informatics solution should help your lab accomplish its goals. Or you could turn to a robust URS like [[Book:LIMSpec 2022 R2|LIMSpec 2022]].
 
LIMSpec is a robust [[laboratory informatics]] requirements specification document that has evolved significantly over the years, and any lab can turn to LIMSpec to better visualize what the critical requirements of a LIMS (or other laboratory informatics solution) are. With the current version of LIMSpec having at its core standards such as [[ASTM E1578|ASTM E1578-18]] ''Standard Guide for Laboratory Informatics''<ref name="ASTME1578_18">{{cite web |url=https://www.astm.org/e1578-18.html |title=ASTM E1578-18 Standard Guide for Laboratory Informatics |publisher=ASTM International |date=23 August 2019 |accessdate=20 January 2023}}</ref> and ISO/IEC 17025 ''General requirements for the competence of testing and calibration laboratories''<ref name="ISO17025_17">{{cite web |url=https://www.iso.org/standard/66912.html |title=ISO/IEC 17025:2017 General requirements for the competence of testing and calibration laboratories |publisher=International Organization for Standardization |date=November 2017 |accessdate=20 January 2023}}</ref>, the LIMSpec makes for a durable URS that, when used to acquire an informatics solution, can better help a laboratory choose appropriate functionality based upon current standards, regulations, guidance, and more.
 
LIMSpec is divided into five distinct sections, with numerous subsections in each. These sections and subsections should be able to address most any requirement you have for your system. Of course, if something isn't covered by LIMSpec, you can always add additional requirements. More importantly, if you have little concept of what functionality systems such as a LIMS or SDMS should have, reviewing this URS can give you a leg up, as can participating in vendor demonstrations. Of course, the base LIMSpec can be used to develop your lab's custom URS to present to potential vendors. (More on that in a bit.)
 
====3.2.2 Core functions and features====
While laboratory, scientific, and clinical informatics vendors may provide a similar core set of functionality in their solutions, there's still a lot of room for variance. Some vendors may try to make a one-size-fits-all solution, while others may focus on certain specialties or uses. In the end, despite the different approaches, a certain set of core functionality becomes apparent. This guide will focus on the LIMS/LIS and its functionality. You should expect the following functionality to be demonstrated in a mature and professional LIMS/LIS offering:
 
'''''Test, experiment, and entity management'''''
 
*sample/specimen log-in and management, with support for unique IDs
*batching support
*barcode and RFID support
*sample/specimen tracking
*pre-defined and configurable industry-specific test and method management
*pre-defined and configurable industry-specific workflows
*clinical decision support (for clinical)
*event and instrument scheduling
*templates, forms, and data fields that are configurable
*analytical tools, including data visualization, trend analysis, and data mining features
*data import and export
*robust query tools
*document and image management, with support for unique document numbers
*project and experiment management
*case management (for clinical and forensic)
*supplier/vendor/customer/patient management
*storage management and monitoring
 
 
'''''Quality, security, and compliance'''''
 
*quality assurance / quality control mechanisms
*changed, amended, or re-issued report management
*data normalization and validation
*results review and approval
*trend and control charting for statistical analysis and measurement of uncertainty
*version control
*user qualification, performance, and training management
*audit trails and chain of custody support
*configurable and granular role-based security
*configurable system access and use (log-in requirements, account usage rules, account locking, etc.)
*electronic signature support
*configurable alarms and alerts
*data encryption and secure communication protocols
*data archiving and retention support
*configurable data backups
*environmental monitoring and control
*incident and non-conformance notification, tracking, and management
*instrument lock-out
 
 
'''''Operations management and reporting'''''
 
*configurable dashboards
*customizable rich-text reporting, with multiple supported output formats
*custom and industry-specific reporting, including certificates of analysis (CoAs)
*synoptic reporting (for clinical)
*industry-compliant labeling
*email integration
*internal messaging system
*revenue management
*instrument interfacing and data management
*instrument calibration and maintenance tracking
*inventory and reagent management
*third-party software and database interfacing
*data import and export
*mobile device support
*voice recognition capability
*results portal for external parties
*integrated (or online) system help
*configurable language
 
====3.2.3 Additional useful features====
The following features are examples of additional LIMS/LIS functionality beyond the core functions a laboratory may seek (it is not meant to be a complete list):
 
*audit management
*clinical research support
*complaint management
*customer relationship management
*electronic laboratory notebook support
*ERP and accounting interfaces
*inventory reconciliation
*invoicing and quotation support
*product specification management
*project management
*recipe management
*reflex testing support
*safety tracking and compliance
*single sign-on support
*stability testing management
 
===3.3 Putting a URS to work for your lab===
As stated prior, building a URS specific to your lab can easily start by examining an existing URS like LIMSpec, which covers most functionality a laboratory could need out of their informatics solution. However, LIMSpec is extensive in what it covers. During the initial research put towards your URS, know that you likely don't want to send the full, comprehensive URS to vendors, at least not in the initial discovery stages. Most vendors appreciate a more inviting approach that doesn't initially overwhelm. Early on you're better off to go with a limited yet practical set of requirements carefully chosen because they matter to you and your laboratory the most. For a food and beverage laboratory, support for molecular biology workflows, stability studies, and production management could be critical. In the case of a lab seeking a solution to help them better comply with ISO/IEC 17025, the lab might want to focus on requirements related to complying with the standard.
 
However you choose to approach URS development and presentation, you'll likely want to wait until after participating in several vendors' software demonstrations before even considering your URS to be complete. The demo offers a unique and valuable opportunity to see in-person how data and information is added, edited, deleted, tracked, and protected within the context of the application; you can ask about how a function works and see it right then and there. Equally, it is an excellent time to compare notes with the vendor, particularly in regard to requirements your lab deems being critical. You can ask the vendor in real-time to answer questions about how a specific task is achieved, or how the system addresses specialized needs, and the vendor can ask you about your lab's system and workflow requirements and how you best envision them being implemented in the system.
 
Again, be careful about falling for the temptation of presenting a full URS or other specification document to the vendor during the demonstration. You'll want to wait until after participating in several software demonstrations to consider presenting your full specification document to the vendor, and that's assuming that you've grown enamored with their solution. By waiting to finalize your lab's URS until after the demos, a common error is avoided: too often labs think the first thing they must do is create a requirements list, then sit back and let the informatics vendors tell them how they meet it. Remember that even though most labs thoroughly understand their processes, they likely don't have as strong a grasp on the informatics portion of their processes and workflows. Participating in a demo before finalizing your list of specified requirements—or having only a minimal yet flexible requirements list during the demo—is a great way to later crosscheck the software features you have seen demonstrated to your lab's processes and any initial requirements specification you've made.<ref name="HammerHowTo19">{{cite web |url=https://www.striven.com/blog/erp-software-demo |title=How to Get the Most Value from an ERP Software Demo |author=Hammer, S. |work=The Takeoff |date=27 June 2019 |accessdate=02 February 2023}}</ref> After all, how can you effectively require specific functions of your laboratory informatics software if you don't fully know what such a system is capable of? After the demonstrations, you may end up adding several requirements to your final specifications document, which you later pass on to your potential vendors of choice for final confirmation.
 
In some cases, rather than approaching vendors, a lab may want to take a different exploratory route by issuing a [[request for information]] (RFI) or something similar. An RFI is an ideal means for learning more about a potential solution and how it can solve your problems, or for when you're not even sure how to solve your problem yet. However, like when approaching a vendor directly, the RFI should not be unduly long and tedious to complete for prospective vendors; it should be concise, direct, and honest. This means not only presenting a clear and humble vision of your own organization and its goals, but also asking just the right amount of questions to allow potential vendors to demonstrate their expertise and provide a clearer picture of who they are. Some take a technical approach to an RFI, using dense language and complicated spreadsheets for fact finding. However, as previously noted, you will want to limit the specified requirements in your RFI to those carefully chosen because they matter to you and your lab the most.<ref name="HolmesItsAMatch">{{cite web |url=https://allcloud.io/blog/its-a-match-how-to-run-a-good-rfi-rfp-or-rfq-and-find-the-right-partner/ |title=It's a Match: How to Run a Good RFI, RFP, or RFQ and Find the Right Partner |author=Holmes, T. |work=AllCloud Blog |accessdate=02 February 2023}}</ref>
 
Remember, an RFI is not meant to answer all of your questions. The RFI is meant as a means to help narrow down your search to a few quality candidates offering functionality that meets your needs, while also learning more about each other.<ref name="HolmesItsAMatch" /> Once the pool of potential software vendors is narrowed down, and you then participate in their demonstrations, you then can broadly add more requirements to the original collection of critical requirements from the RFI to ensure those vendors can meet all or most of your needs. That said, be cognizant that there may be no vendor that can meet each and every need of your lab. Your lab will have to make important decisions about which requirements are non-negotiable and which are more flexible. The vendors you engage with may be able to provide realistic advice in this regard, based upon your lab's requirements and their past experience with labs. As such, those vendors with real-world experience meeting the needs of laboratories like your may have a strong leg up on other vendors.
 
Ultimately, your URS may look similar to LIMSpec, or it may have a slightly different format. Many prospective buyers will develop a requirement specification in Microsoft Excel, but that has a few minor disadvantages. Regardless of format, you'll want to give plenty of space for vendors to submit a response to each requirement. With a more complete URS in hand, and your vendor list narrowed down to a few possibilities, you're ready to submit the full URS to those vendors. Other considerations come into play afterwards, depending how those vendors' respond to you URS. How well did the vendors respond to your laboratory's unique set of needs? Were there critical areas that one vendor could address with their off-the-shelf solution but another vendor would have to address with custom coding? Did any of the vendors meet your budget expectations? Have you followed up on any references and customer experiences the vendors provided to you?
 
Hopefully, once all the due diligence is done, and with a little luck, you've found a vendor that fits your technology and functionality needs, even if a few minor compromises had to be made along the way. However, there's obviously more than technology and system functionality to consider! How is their solution offered? What kind of licensing is used? What are the specifics of the maintenance, warranty, and support plans? The next section addresses that.
 
 
==4. What other considerations should I make, and how much will it cost?==
 
===Purchase vs. subscribe===
In the past this was not an option. But much like the recent trend toward leasing cars rather than finding a large amount of money for up-front purchasing, labs can choose to pay only the cost of services (setup, training, report configuration, instrument interfaces, data migration, custom functions, etc.) and get started on a monthly subscription rather than buy licenses outright. When does this make sense? Subscriptions make sense primarily:
 
*...if a large lump sum is hard to get budgeted. If your business cash flow will support the regular subscription fee but finding license fees is more problematic, then a subscription may be right for you. But do the math. Calculate project costs over a reasonable period (e.g. five years) to make sure it is a value proposition. Be sure to include maintenance and support in your figures; this is often included in a subscription but not in a license.
*...if you may need to reduce the number of users. Once you buy licenses, they are yours. You can't "un-buy" them. But with a subscription you can raise and lower the number of users, workstations, etc. as you need to.
*...if you may need to bail. Business decisions often need to be dynamic. Your lab may decide to go into another area of analysis, and if your LIMS isn't versatile enough to support the change, you have potentially wasted a lot of money.
 
On the other hand, it may be important to you to have the LIMS source code. Some subscriptions allow you just as much access to it as if you had purchased licenses, while others may not give you the access you seek. Confirm this with the vendor. Alos, ask whether you get to keep an image of the database should you decide to end your subscription.
 
===Onsite vs. SaaS===
A small but growing number of LIMS vendors will actually host your system on their servers for you or cloud-host it elsewhere. We refer to software accessed via the Internet rather than your workstation or server as [[software as a service]] or SaaS. Most of us already make copious use of SaaS whenever we "Google" something. Cloudhosted SaaS is characterized by multiple load-balanced servers that allow resources to be strategically used, and virtualized servers that allow for the creation of custom environments.To decide if SaaS is for you or if you should go the traditional route, here are some points to consider:
 
*If you have a small or overworked IT department, or none at all, then it may make sense to let the LIMS provider take care of those functions rather than invest in additional hardware, personnel, and other resources just to support your LIMS. If you are a large company with an extensive and capable IT department, then you may prefer the LIMS and its database to reside on premises.
*IT techs cite security as a major reason to keep a LIMS on lab premises. The truth is, if the vendor uses a SAS-70 or SAS 70 Type II [[data center]] to host, with GxP SOPs, your system and data are probably a lot safer than on a typical business infrastructure. Ask the vendor.
*If you decide to have your system hosted, ensure it's not by Bob and his buddy in their basement. The vendor needs to have been around awhile, have solid references, and feature good customer service.
*A reputable SaaS host will guarantee you high availability, approaching 100% up time, with quick and responsive catastrophe response. Redundant components and infrastructure (power, cooling, etc.) allow them to do that.
 
===Modular vs. complete===
Some LIMS are offered as a collection of [[LIMS feature#Modular|modules]] for you to select from to constitute your completed system, while others come complete with all the functionality available. Those whose LIMS are modular espouse the benefit of only paying for the functionality you need. Those whose LIMS come as a complete package say labs won't need to pay extra for any add-ons. Who's right? Well, it depends. If buying modules means you need one module for [[LIMS feature#Sample tracking|sample tracking]] and another for data entry, and still another to generate reports, then it may not be long before you run up a sizable bill just to get basic standard functionality, especially if the modules require hourly services to implement. If the modules tend to be industry-specific and complete, then they may make sense. Make sure you compare your needs with the product functionality and identify all costs associated with getting everything you need out of the software.
 
===Named users vs. concurrent users===
When comparing license fees, understand the difference between named users and concurrent users. If a vendor charges by named users, and your lab will have 30 people who will use the LIMS at any time, you will need 30 licenses. If the vendor charges by concurrent users, then you only need enough licenses to cover the number of users who are likely to be on the system at the same time. Typically in a lab with 30 staff, you might need a maximum of 20 concurrent user licenses. This is reduced even further if you have sites in other parts of the world whose work days differ.
 
===The company===
As important as the LIMS and its functions are to you, the company is at least as important. Make no mistake: this is a relationship you are entering into. This is not like selecting a piece of furniture. A LIMS is like a living, dynamic entity, and you'll need to interact with the vendor from time to time even with the most trouble-free system. Of course that interaction will be particularly intense in the beginning as they provide installation, provisioning, training, and other set-up services. Take your cue from your initial dealings with them. Just like in any relationship, they will be presenting their best side to you then. If the vendor return calls or emails late or fails to follow through with what they say they'll do, then you can bet it will be much worse once you are their customer. So yes, do the usual: research their years in business, size, staff qualifications, references, etc., but also ask yourself if you would be comfortable doing business with the vendor in the long term.
 
 
===How much will it cost?===
OK, now you understand what to look for in a company and its products. What you likely don't yet know: the price tag. Heck, most of us don't even know how LIMS vendors price their products or what is involved, much less how much they actually cost. In truth, there are three vital pricing components for any LIMS:
 
#licenses
#subscriptions
#services
 
The software itself never comprises the entire cost. LIMS are complex creatures, and your lab, even if it's small, is fairly complex, too. Let's go over what's involved and how much it's roughly going to cost.
 
====Licenses====
If the software has a purchased license type (as opposed to rented/subscription), then you will of course have to pay for those. Keep in mind what we said earlier about [[LIMS Buyer's Guide#Named users vs. concurrent users|named vs. concurrent user pricing]]. Other methods include by site, by CPU or server, by workstation, or by unlimited user corporate level licensing. Arguably the lack of standardization in this area has contributed as much as anything to the vagueness that has surrounded LIMS pricing for so long. The linked vendor profiles in the next section feature pricing information for licenses for the included vendors. (Remember: the primary criterion for inclusion is publicly available pricing.) Review and compare, but make sure you factor in pricing method.
 
====Subscriptions====
These include two possible items:
 
#rented or SaaS LIMS
#annual maintenance, support, and warranty (MSW)
 
The cost of LIMS rental is equivalent to the licensed type, but a lump sum up front is not required. These can run anywhere from a couple of hundred
dollars a month for a single user up to maybe $2000 or so for 20+ users. Just like purchased licenses, however, these can be priced by site, concurrent or named users, etc., so make sure you compare like with like or at least factor these considerations in as you shop. And your rental may be annual instead of monthly. In most cases it does include all IT services and maintenance, support, and warranty, including updates, at a specified level.
 
The second type of subscription cost is annual MSW, and you need to factor that into your budgeting if you are buying LIMS licenses. Typically it is priced at around 15 percent of the license fee and is available at graduated levels. A certain level may be standard for a certain number of licenses (for example, 10 hours of support and additional services available at $200 per hour for a 10-concurrent user LIMS), but you can buy a higher level of support and cheaper
rate for additional services if you want to pay extra. One thing to keep in mind: with an MSW you will certainly need coverage as you go through your first year. If you think you can then drop it, think again. A modern LIMS should be built on technology that can give it a much longer life span than those in years past. That is dependent on staying updated. If you lose that update path, your LIMS will expire prematurely. If you decide later to renew MSW, you may
find yourself liable for the missed years before the vendor will bring you current.
 
====Services====
Your LIMS is a function of the cost of the LIMS itself plus the services involved in its implementation plus, in the case of a licensed LIMS, annual MSW. Many first-time LIMS buyers neglect to factor in the cost of services when budgeting. As mentioned earlier, any LIMS will require services to get going, and you may want more if there are extras you need or want. Services break down more or less like this:
 
'''Basic implementation services'''
 
*kickoff meeting (planning, coordination, communication procedures, etc.)
*ƒtraining
*setup (enter users, configure profiles, departments, tests, screens, etc.)
*create main report(s)
*go live support
 
'''Additional or optional services'''
 
*instrument interfaces
*additional reports
*data migration from a previous system
*interfaces to other systems or databases
*special customizations
*web portal configuration
*validation
*standards certification support
 
You may need other services. Rates for services vary from vendor to vendor, but a good rule of thumb for initial budgeting purposes is to figure service costs to be roughly equal to the licensing cost or to a year's worth of LIMS subscription.
</div>
<p>&nbsp;</p>
 
 
==5. Commercial vendors with public pricing==
''Finally, a primary criterion for inclusion in this guide is publicly available pricing information that can thusly be cited.'' If citeable public pricing is not available, the vendor will not be listed in this guide. Any vendors who remove pricing or no longer make it public will be removed from the vendor list.
 
{{Commercial vendors with public pricing}}
 
 
==6. Additional resources and help==
 
===LIMSforum===
Formerly a LinkedIn-associated group, [http://www.limsforum.com LIMSforum] is a web portal for those interested in laboratory, scientific, and [[health informatics]].
 
===LIMSforum Career Opportunities===
Formerly the LinkedIn-associated Lab Careers group, LIMSforum's [https://www.limsforum.com/career-opportunities/ career opportunities] section is available for the viewing and posting of job openings for laboratory, scientific, and health lab careers.
 
===LIMSforum Online Courses===
Formerly LIMS University, the [https://www.limsforum.com/labcourses/ laboratory courses] at LIMSforum provide free, open-access learning and teaching resources for those wanting to learn more about [[laboratory informatics]].
 
===LIMSfinder===
[http://www.limsfinder.com/ LIMSfinder] is a web portal for those looking for a LIMS and related information, services, products, news, events, resources, jobs, etc.
 
===LIMSpec.com===
[https://www.limspec.com/index.php?title=Main_Page LIMSpec.com] provides a collection of datasheets — from lab requirements assessment to LIMS vendor and system questionnaires, validation documents, and more — for identifying LIMS needs and matching them with what's out there.
 
===LIMSwiki informatics resource portal===
[[LIMSWiki:Resources|The informatics resource portal]] here at LIMSwiki features a collection of as many useful online scientific and health informatics-related materials and research tools as possible, including books, journals, blogs, web portals, education programs, conferences, and more.


==References==
==References==
<references />
{{Reflist|colwidth=30em}}
 
<!---Place all category tags here-->
[[Category:LII:Guides, white papers, and other publications]]

Latest revision as of 19:33, 17 February 2023

Sandbox begins below

  • Discussion and practical use of artificial intelligence (AI) in the laboratory is, perhaps to the surprise of some, not a recent phenomena. In the mid-1980s, researchers were developing computerized AI systems able "to develop automatic decision rules for follow-up analysis of [clinical laboratory] tests depending on prior information, thus avoiding the delays of traditional sequential testing and the costs of unnecessary parallel testing."[1] In fact, discussion of AI in general was ongoing even in the mid-1950s.[2][3]
  • Hiring demand for laboratorians with AI experience (2015–18) has historically been higher in non-healthcare industries, such as manufacturing, mining, and agriculture, shedding a light on how AI adoption in the clinical setting may be lacking. According to the Brookings Institute, "Even for the relatively-skilled job postings in hospitals, which includes doctors, nurses, medical technicians, research lab workers, and managers, only approximately 1 in 1,250 job postings required AI skills." They add: "AI adoption may be slow because it is not yet useful, or because it may not end up being as useful as we hope. While our view is that AI has great potential in health care, it is still an open question."[4]
  • Today, AI is being practically used in not only clinical diagnostic laboratories but also clinical research labs, life science labs, and research and development (R&D) labs, and more. Practical uses of AI can be found in:
clinical research labs[5]
hospitals[5][6]
medical diagnostics labs[6][7][8][9][10][11]
chromatography labs[11]
biology and life science labs[12]
medical imaging centers[13]
ophthalmology clinics[14]
reproduction clinics[15][16][17]
digital pathology labs[18]
material testing labs[19][20][21]
chemical experimentation and molecular discovery labs[21][22][23]
quantum physics labs[24]
  • What's going on in these labs?
Materials science: The creation of "a modular robotic platform driven by a model-based optimization algorithm capable of autonomously optimizing the optical and electronic properties of thin-film materials by modifying the film composition and processing conditions ..."[19]
Materials science: "Most of the applications of [machine learning (ML)] in chemical and materials sciences, as we have said, feature supervised learning algorithms. The goal there is to supplement or replace traditional modeling methods, at the quantum chemical or classical level, in order to predict the properties of molecules or materials directly from their structure or their chemical composition ... Our research group was applying the same idea on a narrower range of materials, trying to confirm that for a given chemical composition, geometrical descriptors of a material’s structure could lead to accurate predictions of its mechanical features."[20]
Life science: "In biological experiments, we generally cannot as easily declare victory, but we can use the systems biology approach of cycling between experimentation and modelling to see which sequences, when tested, are most likely to improve the model. In artificial intelligence, this is called active learning, and it has some similarity to the way in which we as humans learn as infants: we get some help from parents and teachers, but mainly model the world around us by exploring it and interacting with it. Ideally then, we would recreate such an environment for our machine learning algorithms in the laboratory, where we start with an initial ‘infant’ model of a certain regulatory system or protein function and let the computer decide what sequence designs to try out – a deep learning version of the ‘robot scientist’. Microbes are ideal organisms for such an approach, given the ease and speed with which they can be grown and genetically manipulated. Combined with laboratory automation, many microbial experiments can (soon) be performed with minimal human intervention, ranging from strain construction and screening, such as operated by Amyris, Gingko, Transcriptic, etc., to full-genome engineering or even the design of microbial ecologies."[12]
Digital pathology: "The collaboration combines two AI solutions, VistaPath’s Sentinel, the world’s first automated tissue grossing platform, and Gestalt’s AI Requisition Engine (AIRE), a leading-edge AI algorithm for accessioning, to raise the bar in AI-driven pathology digitization. Designed to make tissue grossing faster and more accurate, VistaPath’s Sentinel uses a high-quality video system to assess specimens and create a gross report 93% faster than human technicians with 43% more accuracy. It not only improves on quality by continuously monitoring the cassette, container, and tissue to reduce mislabeling and specimen mix-up, but also increases traceability by retaining original images for downstream review."[25]
Chemistry and molecular science: "The benefits of combining automated experimentation with a layer of artificial intelligence (AI) have been demonstrated for flow reactors, photovoltaic films, organic synthesis, perovskites and in formulation problems. However, so far no approaches have integrated mobile robotics with AI for chemical experiments. Here, we built Bayesian optimization into a mobile robotic workflow to conduct photocatalysis experiments within a ten-dimensional space."[22]
Chemistry and immunology: "Chemistry and immunology laboratories are particularly well-suited to leverage machine learning because they generate large, highly structured data sets, Schulz and others wrote in a separate review paper. Labor-intensive processes used for interpretation and quality control of electrophoresis traces and mass spectra could benefit from automation as the technology improves, they said. Clinical chemistry laboratories also generate digital images—such as urine sediment analysis—that may be highly conducive to semiautomated analyses, given advances in computer vision, the paper noted."[26]
Clinical research: "... retrospective analysis of existing patient data for descriptive and clustering purposes [and] automation of knowledge extraction, ranging from text mining, patient selection for trials, to generation of new research hypotheses ..."[5]
Clinical research: "AI ... offers a further layer to the laboratory system by analyzing all experimental data collected by experiment devices, whether it be a sensor or a collaborative robot. From data collected, AI is able to produce hypotheses and predict which combination of materials or temperature is desired for the experiment. In short, this system will allow scientists to be aided by a highly intelligent system which is constantly monitoring and analyzing the experimental output. In this way, AI will help an experiment from its inception to conclusion."[27]
Clinical research/medical diagnostics: "Artificial intelligence (AI) in the laboratory is primarily used to make sense of big data, the almost impossibly large sets of data that biologists and pharmaceutical R&D teams are accustomed to working with. AI algorithms can parse large amounts of data in a short amount of time and turn that data into visualizations that viewers can easily understand. In certain data-intensive fields, such as genomic testing and virus research, AI algorithms are the best way to sort through the data and do some of the pattern recognition work."[28]
Medical diagnostics: Development and implementation of clinical decision support systems [5][6]
Medical diagnostics: "Finally, in the laboratory, AI reduces the number of unnecessary blood samples when diagnosing infection. Instead of the 'gold standard blood sample' that takes 24-72 hours, the algorithm can predict the outcome of the blood sample with almost 80% accuracy based on demographics, vital signs, medications, and laboratory and radiology results. These are all examples of how Artificial Intelligence can be used to test better and faster with information that already exists. This saves time and costs."[10]
Medical diagnostics: "Chang sees two overarching classes of AI models: those that tackle internal challenges in the lab, such as how to deliver more accurate results to clinicians; and those that seek to identify cohorts of patients and care processes to close quality gaps in health delivery systems. The lab, however, 'isn’t truly an island,' said Michelle Stoffel, MD, PhD, associate chief medical information officer for laboratory medicine and pathology at M Health Fairview and the University of Minnesota in Minneapolis. 'When other healthcare professionals are working with electronic health records or other applications, there could be AI-driven tools, or algorithms used by an institution’s systems that may draw on laboratory data.'"[26]
Medical diagnostics: AI is used for the formulation of reference ranges, improvement of quality control, and automated interpretation of results. "Continuous monitoring of specimen acceptability, collection and transport can result in the prompt identification and correction of problems, leading to improved patient care and a reduction in unnecessary redraws and delays in reporting results."[8]
Reproduction science: "The field of AI is the marriage of humans and computers while reproductive medicine combines clinical medicine and the scientific laboratory of embryology. The application of AI has the potential to disconnect healthcare professionals from patients through algorithms, automated communication, and clinical imaging. However, in the embryology laboratory, AI, with its focus on gametes and embryos, can avoid the same risk of distancing from the patient. Areas of application of AI in the laboratory would be to enhance and automate embryo ranking through analysis of images, the ultimate goal being to predict successful implantation. Might such a trend obviate the need for embryo morphological assessment, time-lapse imaging and preimplantation genetic testing for aneuploidy (PGT-A), including mosaicism. Additionally, AI could assist with automation through analysis of testicular sperm samples searching for viable gametes, embryo grading uniformity."[15]
Chromatography-heavy sciences: " A great example of this is AI in the Liquid Chromatography Mass Spectrometry (LC-MS) field. LC-MS is a great tool used to measure various compounds in the human body, including everything from hormone levels to trace metals. One of the ways AI has already integrated with LC-MS is how it cuts down on the rate limiting steps of LC-MS, which more often than not are sample prep and LC separations. One system that Physicians Lab has made use of is parallel processing using SCIEX MPX 2.0 High Throughput System. This system can couple parallel runs with one LCMS instrument, resulting in twice the speed with no loss to accuracy. It can do this by staggering two runs either using the same method, or different methods entirely. What really makes this system great is its ability to automatically detect carryover and inject solvent blanks to clean the instrument. The system will then continue its analyzing, while automatically reinjecting samples that may be affected by the carryover. It will also flag high concentration without user input, allowing for easy detection of possibly faulty samples. This allows it to operate without users from startup to shut down. Some of the other ways that it can be used to increase efficiency are by using integrated network features to work on anything from streamlining management to increased throughput."[11]
Most any lab: "Predictive analytics, for example, is one tool that the Pistoia Alliance is using to better understand laboratory instruments and how they might fail over time... With the right data management strategies and careful consideration of metadata, how to best store data so that it can be used in future AI and ML workflows is essential to the pursuit of AI in the laboratory. Utilizing technologies such as LIMS and ELN enables lab users to catalogue data, providing context and instrument parameters that can then be fed into AI or ML systems. Without the correct data or with mismatched data types, AI and ML will not be possible, or at the very least, could provide undue bias trying to compare data from disparate sources."[29]
Most any lab: "When the actionable items are automatically created by Optima, the 'engine' starts working. An extremely sophisticated algorithm is able to assign the tasks to the resources, both laboratory personnel and instruments, according to the system configuration. Optima, thanks to a large amount of time dedicated to research the best way to automate this critical process, is able to automate most of the lab resource scheduling."[30]
  • A number of challenges exist in the realm of effectively and securely implementing AI in the laboratory. This includes:
Ethical and privacy challenges[5][26][31]
Algorithmic limitations[4]
Data access limitations, including "where to get it, how to share it, and how to know when you have enough to train a machine-learning system that will produce good results"[4][26][32][33]
Data integration and transformation issues[5][33]
Regulatory barriers[4][7]
Misaligned incentives[4]
Lack of knowledgeable/skilled talent[5][26][32][33]
Cost of skilled talent and infrastructure for maintaining and updating AI systems[26]
Legacy systems running outdated technologies[32]
Lack of IT systems or specialized software systems[33]
Lack of standardized, best practices-based methods of validating algorithms[26]
Failure to demonstrate real-world performance[7]
Failure to meet the needs of the professionals using it[7]
  • Given those challenges, some considerations should be made about implementing AI-based components in the laboratory. Examples include:
Clinical diagnostics: "From an industry and regulatory perspective, however, only the intended uses supported from the media manufacturer can be supported from AI applications, unless otherwise justified and substantive evidence is presented for additional claims support. This means strict adherence to specimen type and incubation conditions. Considering that the media was initially developed for human assessment using the well-trained microbiologist eye, and not an advanced imaging system with or without AI, this paradigm should shift to allow advancements in technology to challenge the status-quo of decreasing media read-times especially, as decreased read-times assist with laboratory turnaround times and thus patient management. Perhaps with an increasing body of evidence to support any proposed indications for use, either regulatory positions should be challenged, or manufacturers of media and industry AI-development specialists should work together to advance the field with new indications for use.
While the use of AI in the laboratory setting can be highly beneficial there are still some issues to be addressed. The first being phenotypically distinct single organism polymorphisms that may be interpreted by AI as separate organisms, as may also be the case for a human assessment, as well as small colony variant categorization. As detailed earlier, the broader the inputs, the greater the generalization of the model, and the higher the likelihood of algorithm accuracy. In that respect, understanding and planning around these design constraints is critical for ultimate deployment of algorithms. Additionally, expecting an AI system to correctly categorize “contamination” is a difficult task as often this again seemingly innocuous decision is dependent on years of experience and understanding the specimen type and the full clinical picture with detailed clinical histories. In this respect, a fully integrated AI-LIS system where all data is available may assist, but it is currently not possible to gather this granular detail needed to make this assessment reliable."[9]
Clinical diagnostics and pathology: "Well, if I’ve learned anything in my research into this topic, it’s that AI implementation needs to be a two-way street. First, any company who is active in this space must reach out to pathologists and laboratory medicine professionals to understand their daily workflows, needs, and pain points in as much detail as possible. Second, pathologists, laboratory medicine professionals, and educators must all play their important part – willingly offering their time and expertise when it is sought or proactively getting involved. And finally, it’s clear that there is an imbalanced focus on certain issues – with privacy, respect, and sustainability falling by the wayside."[31]
Healthcare: "While we are encouraged by the promise shown by AI in healthcare, and more broadly welcome the use of digital technologies in improving clinical outcomes and health system productivity, we also recognize that caution must be exercised when introducing any new healthcare technology. Working with colleagues across the NHS Transformation Directorate, as well as the wider AI community, we have been developing a framework to evaluate AI-enabled solutions in the health and care policy context. The aim of the framework is several-fold but is, at its core, a tool with which to highlight to healthcare commissioners, end users, patients and members of the public the considerations to be mindful when introducing AI to healthcare settings."[34]
Most any lab: A code of AI ethics should address objectivity, privacy, transparency, accountability, and sustainability in any AI implementation.[31]
Most any lab: "Another approach is to implement an AI program alongside a manual process, assessing its performance along the way, as a means to ease into using the program. 'I think one of the most impactful things that laboratorians can do today is to help make sure that the lab data that they’re generating is as robust as possible, because these AI tools rely on new training sets, and their performance is really only going to be as good as the training data sets they’re given,' Stoffel said."[26]

References

  1. Berger-Hershkowitz, H.; Neuhauser, D. (1987). "Artificial intelligence in the clinical laboratory". Cleveland Clinic Journal of Medicine 54 (3): 165–166. doi:10.3949/ccjm.54.3.165. ISSN 0891-1150. PMID 3301059. https://www.ccjm.org/content/54/3/165. 
  2. Minsky, M. (17 December 1956). Heuristic Aspects of the Artificial Intelligence Problem. Ed Services Technical Information Agency. https://books.google.com/books?hl=en&lr=&id=fvWNo6_IZGUC&oi=fnd&pg=PA1. Retrieved 16 February 2023. 
  3. Minsky, Marvin (1 January 1961). "Steps toward Artificial Intelligence". Proceedings of the IRE 49 (1): 8–30. doi:10.1109/JRPROC.1961.287775. ISSN 0096-8390. http://ieeexplore.ieee.org/document/4066245/. 
  4. 4.0 4.1 4.2 4.3 4.4 Goldfarb, A.; Teodoridis, F. (9 March 2022). "Why is AI adoption in health care lagging?". Series: The Economics and Regulation of Artificial Intelligence and Emerging Technologies. Brookings Institute. https://www.brookings.edu/research/why-is-ai-adoption-in-health-care-lagging/. Retrieved 17 February 2023. 
  5. 5.0 5.1 5.2 5.3 5.4 5.5 5.6 Damiani, A.; Masciocchi, C.; Lenkowicz, J.; Capocchiano, N. D.; Boldrini, L.; Tagliaferri, L.; Cesario, A.; Sergi, P. et al. (7 December 2021). "Building an Artificial Intelligence Laboratory Based on Real World Data: The Experience of Gemelli Generator". Frontiers in Computer Science 3: 768266. doi:10.3389/fcomp.2021.768266. ISSN 2624-9898. https://www.frontiersin.org/articles/10.3389/fcomp.2021.768266/full. 
  6. 6.0 6.1 6.2 University of California, San Francisco; Adler-Milstein, Julia; Aggarwal, Nakul; University of Wisconsin-Madison; Ahmed, Mahnoor; National Academy of Medicine; Castner, Jessica; Castner Incorporated et al. (29 September 2022). "Meeting the Moment: Addressing Barriers and Facilitating Clinical Adoption of Artificial Intelligence in Medical Diagnosis". NAM Perspectives 22 (9). doi:10.31478/202209c. PMC PMC9875857. PMID 36713769. https://nam.edu/meeting-the-moment-addressing-barriers-and-facilitating-clinical-adoption-of-artificial-intelligence-in-medical-diagnosis. 
  7. 7.0 7.1 7.2 7.3 Government Accountability Office (GAO); National Academy of Medicine (NAM) (September 2022). "Artificial Intelligence in Health Care: Benefits and Challenges of Machine Learning Technologies for Medical Diagnostics" (PDF). Government Accountability Office. https://www.gao.gov/assets/gao-22-104629.pdf. Retrieved 16 February 2023. 
  8. 8.0 8.1 Wen, Xiaoxia; Leng, Ping; Wang, Jiasi; Yang, Guishu; Zu, Ruiling; Jia, Xiaojiong; Zhang, Kaijiong; Mengesha, Birga Anteneh et al. (24 September 2022). "Clinlabomics: leveraging clinical laboratory data by data mining strategies" (in en). BMC Bioinformatics 23 (1): 387. doi:10.1186/s12859-022-04926-1. ISSN 1471-2105. PMC PMC9509545. PMID 36153474. https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-022-04926-1. 
  9. 9.0 9.1 DeYoung, B.; Morales, M.; Giglio, S. (4 August 2022). "Microbiology 2.0–A “behind the scenes” consideration for artificial intelligence applications for interpretive culture plate reading in routine diagnostic laboratories". Frontiers in Microbiology 13: 976068. doi:10.3389/fmicb.2022.976068. ISSN 1664-302X. PMC PMC9386241. PMID 35992715. https://www.frontiersin.org/articles/10.3389/fmicb.2022.976068/full. 
  10. 10.0 10.1 Schut, M. (1 December 2022). "Get better with bytes". Amsterdam UMC. https://www.amsterdamumc.org/en/research/news/get-better-with-bytes.htm. Retrieved 16 February 2023. 
  11. 11.0 11.1 11.2 Albano, V.; Morris, C.; Kent, T. (6 December 2019). "Calculations to Diagnosis: The Artificial Intelligence Shift That’s Already Happening". Physicians Lab. https://physicianslab.com/calculations-to-diagnosis-the-artificial-intelligence-shift-thats-already-happening/. Retrieved 16 February 2023. 
  12. 12.0 12.1 de Ridder, Dick (1 January 2019). "Artificial intelligence in the lab: ask not what your computer can do for you" (in en). Microbial Biotechnology 12 (1): 38–40. doi:10.1111/1751-7915.13317. PMC PMC6302702. PMID 30246499. https://onlinelibrary.wiley.com/doi/10.1111/1751-7915.13317. 
  13. Brandao-de-Resende, C.; Bui, M.; Daneshjou, R. et al. (11 October 2022). "AI Webinar: Clinical Adoption of AI Across Image Producing Specialties". Society for Imaging Informatics in Medicine. https://siim.org/page/22w_clinical_adoption_of_ai. 
  14. He, Mingguang; Li, Zhixi; Liu, Chi; Shi, Danli; Tan, Zachary (1 July 2020). "Deployment of Artificial Intelligence in Real-World Practice: Opportunity and Challenge" (in en). Asia-Pacific Journal of Ophthalmology 9 (4): 299–307. doi:10.1097/APO.0000000000000301. ISSN 2162-0989. https://journals.lww.com/10.1097/APO.0000000000000301. 
  15. 15.0 15.1 Trolice, Mark P.; Curchoe, Carol; Quaas, Alexander M (1 July 2021). "Artificial intelligence—the future is now" (in en). Journal of Assisted Reproduction and Genetics 38 (7): 1607–1612. doi:10.1007/s10815-021-02272-4. ISSN 1058-0468. PMC PMC8260235. PMID 34231110. https://link.springer.com/10.1007/s10815-021-02272-4. 
  16. European Society of Human Reproduction and Embryology (6 July 2022). "Annual Meeting 2022: Artificial intelligence in embryology and ART". Focus on Reproduction. https://www.focusonreproduction.eu/article/ESHRE-News-22AI. Retrieved 16 February 2023. 
  17. Hinckley, M. (17 March 2021). "Applying AI (Artificial Intelligence) in the Lab for Better IVF Success". Reproductive Science Center Blog. Reproductive Science Center of the Bay Area. https://rscbayarea.com/blog/applying-ai-for-better-ivf-success. Retrieved 16 February 2023. 
  18. Yousif, M.; McClintock, D.S.; Yao, K. (2021). "Artificial intelligence is the key driver for digital pathology adoption". Clinical Laboratory Int. PanGlobal Media. https://clinlabint.com/artificial-intelligence-is-the-key-driver-for-digital-pathology-adoption/. Retrieved 16 February 2023. 
  19. 19.0 19.1 MacLeod, B. P.; Parlane, F. G. L.; Morrissey, T. D.; Häse, F.; Roch, L. M.; Dettelbach, K. E.; Moreira, R.; Yunker, L. P. E. et al. (15 May 2020). "Self-driving laboratory for accelerated discovery of thin-film materials" (in en). Science Advances 6 (20): eaaz8867. doi:10.1126/sciadv.aaz8867. ISSN 2375-2548. PMC PMC7220369. PMID 32426501. https://www.science.org/doi/10.1126/sciadv.aaz8867. 
  20. 20.0 20.1 Chibani, Siwar; Coudert, François-Xavier (1 August 2020). "Machine learning approaches for the prediction of materials properties" (in en). APL Materials 8 (8): 080701. doi:10.1063/5.0018384. ISSN 2166-532X. http://aip.scitation.org/doi/10.1063/5.0018384. 
  21. 21.0 21.1 Mullin, R. (28 March 2021). "The lab of the future is now". Chemical & Engineering News 99 (11). Archived from the original on 06 May 2022. https://web.archive.org/web/20220506192926/http://cen.acs.org/business/informatics/lab-future-ai-automated-synthesis/99/i11. Retrieved 16 February 2023. 
  22. 22.0 22.1 Burger, Benjamin; Maffettone, Phillip M.; Gusev, Vladimir V.; Aitchison, Catherine M.; Bai, Yang; Wang, Xiaoyan; Li, Xiaobo; Alston, Ben M. et al. (9 July 2020). "A mobile robotic chemist" (in en). Nature 583 (7815): 237–241. doi:10.1038/s41586-020-2442-2. ISSN 0028-0836. https://www.nature.com/articles/s41586-020-2442-2.epdf?sharing_token=HOkIS6P5VIAo2_l3nRELmdRgN0jAjWel9jnR3ZoTv0Nw4yZPDO1jBpP52iNWHbb8TakOkK906_UHcWPTvNxCmzSMpAYlNAZfh29cFr7WwODI2U6eWv38Yq2K8odHCi-qwHcEDP18OjAmH-0KgsVgL5CpoEaQTCvbmhXDSyoGs6tIMe1nuABTeP58z6Ck3uULcdCtVQ66X244FsI7uH8GnA%3D%3D&tracking_referrer=cen.acs.org. 
  23. Lemonick, S. (6 April 2020). "Exploring chemical space: Can AI take us where no human has gone before?". Chemical & Engineering News 98 (13). Archived from the original on 29 July 2020. https://web.archive.org/web/20200729004137/https://cen.acs.org/physical-chemistry/computational-chemistry/Exploring-chemical-space-AI-take/98/i13. Retrieved 16 February 2023. 
  24. Doctrow, B. (16 December 2019). "Artificial intelligence in the laboratory". PNAS Science Sessions. https://www.pnas.org/post/podcast/artificial-intelligence-laboratory. Retrieved 16 February 2023. 
  25. VistaPath (28 July 2022). "VistaPath Launches New Collaboration with Gestalt Diagnostics to Further Accelerate Pathology Digitization". PR Newswire. Cision US Inc. https://www.prnewswire.com/news-releases/vistapath-launches-new-collaboration-with-gestalt-diagnostics-to-further-accelerate-pathology-digitization-301594718.html. Retrieved 17 February 2023. 
  26. 26.0 26.1 26.2 26.3 26.4 26.5 26.6 26.7 Blum, K. (1 January 2023). "A Status Report on AI in Laboratory Medicine". Clinical Laboratory News. American Association for Clinical Chemistry. https://www.aacc.org/cln/articles/2023/janfeb/a-status-report-on-ai-in-laboratory-medicine. Retrieved 17 February 2023. 
  27. Chubb, P. (3 November 2020). "How disruptive technology is helping laboratories combat COVID-19". Datafloq. https://datafloq.com/read/disruptive-technologies-lab-help-us-prepare-future-pandemics/. Retrieved 16 February 2023. 
  28. Stewart, B. (18 March 2021). "Using LIMS for Data Visualization". CSols Insights. CSols, Inc. https://www.csolsinc.com/insights/published-articles/using-lims-for-data-visualization/. Retrieved 17 February 2023. 
  29. "Data Analytics". Scientific Computing World - Building a Smart Laboratory 2020. Europa Science Ltd. 29 January 2021. https://www.scientific-computing.com/feature/data-analytics-0. Retrieved 17 February 2023. 
  30. Optima Team (15 December 2020). "The concept of machine learning applied to lab resources scheduling". Optima Blog. Optima PLC Tracking Tools S.L. https://www.optima.life/blog/the-concept-of-machine-learning-applied-to-lab-resources-scheduling/. Retrieved 17 February 2023. 
  31. 31.0 31.1 31.2 Lee, G.F. (10 October 2022). "The Robot May See You Now: It’s time to stop and think about the ethics of artificial intelligence". The Pathologist. https://thepathologist.com/outside-the-lab/the-robot-may-see-you-now. Retrieved 17 February 2023. 
  32. 32.0 32.1 32.2 Sherwood, L. (10 February 2022). "SLAS 2022: Barriers remain to AI adoption in life sciences". LabPulse.com Showcasts. Science and Medicine Group. https://www.labpulse.com/showcasts/slas/2022/article/15300130/slas-2022-barriers-remain-to-ai-adoption-in-life-sciences. Retrieved 17 February 2023. 
  33. 33.0 33.1 33.2 33.3 Bellini, Claudia; Padoan, Andrea; Carobene, Anna; Guerranti, Roberto (25 November 2022). "A survey on Artificial Intelligence and Big Data utilisation in Italian clinical laboratories" (in en). Clinical Chemistry and Laboratory Medicine (CCLM) 60 (12): 2017–2026. doi:10.1515/cclm-2022-0680. ISSN 1434-6621. https://www.degruyter.com/document/doi/10.1515/cclm-2022-0680/html. 
  34. Chada, Bharadwaj V; Summers, Leanne (10 October 2022). "AI in the NHS: a framework for adoption" (in en). Future Healthcare Journal: fhj.2022–0068. doi:10.7861/fhj.2022-0068. ISSN 2514-6645. PMC PMC9761451. PMID 36561823. https://www.rcpjournals.org/lookup/doi/10.7861/fhj.2022-0068.