Difference between revisions of "Journal:Fostering reproducibility, reusability, and technology transfer in health informatics"

From LIMSWiki
Jump to navigationJump to search
(Saving and adding more.)
(Saving and adding more.)
Line 54: Line 54:
A manifold of studies have proven AI to be advantageous for disease diagnosis, prognosis, and [[Disease informatics|disease monitoring]].<ref>{{Cite web |last=Digital Health Center of Excellence |date=06 December 2017 |title=What are examples of Software as a Medical Device? |url=https://www.fda.gov/medical-devices/software-medical-device-samd/what-are-examples-software-medical-device |publisher=U.S. Food and Drug Administration}}</ref><ref>{{Cite journal |last=Fatima |first=Meherwar |last2=Pasha |first2=Maruf |date=2017 |title=Survey of Machine Learning Algorithms for Disease Diagnostic |url=http://www.scirp.org/journal/PaperInformation.aspx?PaperID=73781&#abstract |journal=Journal of Intelligent Learning Systems and Applications |language=en |volume=09 |issue=01 |pages=1 |doi=10.4236/jilsa.2017.91001}}</ref> In [[cancer]] research, for instance, ML is used on [[omics]] data to gain deeper insights and understanding of the genetic and metabolic alterations that determine disease progression and enable tailored prognoses and monitoring.<ref>{{Cite journal |last=Batra |first=Richa |last2=Alcaraz |first2=Nicolas |last3=Gitzhofer |first3=Kevin |last4=Pauling |first4=Josch |last5=Ditzel |first5=Henrik J. |last6=Hellmuth |first6=Marc |last7=Baumbach |first7=Jan |last8=List |first8=Markus |date=2017-12 |title=On the performance of de novo pathway enrichment |url=http://www.nature.com/articles/s41540-017-0007-2 |journal=npj Systems Biology and Applications |language=en |volume=3 |issue=1 |pages=6 |doi=10.1038/s41540-017-0007-2 |issn=2056-7189 |pmc=PMC5445589 |pmid=28649433}}</ref><ref>{{Cite journal |last=Hauschild |first=A.-C. |last2=Baumbach |first2=J.I. |last3=Baumbach |first3=J. |date=2012 |title=Integrated statistical learning of metabolic ion mobility spectrometry profiles for pulmonary disease identification |url=http://www.funpecrp.com.br/gmr/year2012/vol11-3/pdf/gmr2065.pdf |journal=Genetics and Molecular Research |volume=11 |issue=3 |pages=2733–2744 |doi=10.4238/2012.July.10.17}}</ref><ref>{{Citation |last=Jeanquartier |first=Fleur |last2=Jean-Quartier |first2=Claire |last3=Kotlyar |first3=Max |last4=Tokar |first4=Tomas |last5=Hauschild |first5=Anne-Christin |last6=Jurisica |first6=Igor |last7=Holzinger |first7=Andreas |date=2016 |editor-last=Holzinger |editor-first=Andreas |title=Machine Learning for In Silico Modeling of Tumor Growth |url=http://link.springer.com/10.1007/978-3-319-50478-0_21 |work=Machine Learning for Health Informatics |language=en |publisher=Springer International Publishing |place=Cham |volume=9605 |pages=415–434 |doi=10.1007/978-3-319-50478-0_21 |isbn=978-3-319-50477-3 |access-date=2021-08-22}}</ref><ref>{{Cite journal |last=Wiwie |first=Christian |last2=Kuznetsova |first2=Irina |last3=Mostafa |first3=Ahmed |last4=Rauch |first4=Alexander |last5=Haakonsson |first5=Anders |last6=Barrio-Hernandez |first6=Inigo |last7=Blagoev |first7=Blagoy |last8=Mandrup |first8=Susanne |last9=Schmidt |first9=Harald H.H.W. |last10=Pleschka |first10=Stephan |last11=Röttger |first11=Richard |date=2019-05 |title=Time-Resolved Systems Medicine Reveals Viral Infection-Modulating Host Targets |url=https://www.liebertpub.com/doi/10.1089/sysm.2018.0013 |journal=Systems Medicine |language=en |volume=2 |issue=1 |pages=1–9 |doi=10.1089/sysm.2018.0013 |issn=2573-3370 |pmc=PMC6524659 |pmid=31119214}}</ref> Additionally, computational models on clinical [[information]] are used to assess individualized health risks, for instance, to identify high-risk patients for sepsis in intensive care units<ref>{{Cite journal |last=Calvert |first=Jacob |last2=Saber |first2=Nicholas |last3=Hoffman |first3=Jana |last4=Das |first4=Ritankar |date=2019-02-13 |title=Machine-Learning-Based Laboratory Developed Test for the Diagnosis of Sepsis in High-Risk Patients |url=http://www.mdpi.com/2075-4418/9/1/20 |journal=Diagnostics |language=en |volume=9 |issue=1 |pages=20 |doi=10.3390/diagnostics9010020 |issn=2075-4418 |pmc=PMC6468682 |pmid=30781800}}</ref><ref>{{Cite journal |last=Desautels |first=Thomas |last2=Calvert |first2=Jacob |last3=Hoffman |first3=Jana |last4=Jay |first4=Melissa |last5=Kerem |first5=Yaniv |last6=Shieh |first6=Lisa |last7=Shimabukuro |first7=David |last8=Chettipally |first8=Uli |last9=Feldman |first9=Mitchell D |last10=Barton |first10=Chris |last11=Wales |first11=David J |date=2016-09-30 |title=Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach |url=https://medinform.jmir.org/2016/3/e28/ |journal=JMIR Medical Informatics |language=en |volume=4 |issue=3 |pages=e28 |doi=10.2196/medinform.5909 |issn=2291-9694 |pmc=PMC5065680 |pmid=27694098}}</ref>, the analysis of longitudinal data for the early detection of heart failure<ref>{{Cite journal |last=Chen |first=Robert |last2=Stewart |first2=Walter F. |last3=Sun |first3=Jimeng |last4=Ng |first4=Kenney |last5=Yan |first5=Xiaowei |date=2019-10 |title=Recurrent Neural Networks for Early Detection of Heart Failure From Longitudinal Electronic Health Record Data: Implications for Temporal Modeling With Respect to Time Before Diagnosis, Data Density, Data Quantity, and Data Type |url=https://www.ahajournals.org/doi/10.1161/CIRCOUTCOMES.118.005114 |journal=Circulation: Cardiovascular Quality and Outcomes |language=en |volume=12 |issue=10 |doi=10.1161/CIRCOUTCOMES.118.005114 |issn=1941-7713 |pmc=PMC6814386 |pmid=31610714}}</ref>, or applications in [[Infectious disease informatics|infectious diseases]].<ref>{{Cite journal |last=Heider |first=Dominik |last2=Dybowski |first2=Jan Nikolaj |last3=Wilms |first3=Christoph |last4=Hoffmann |first4=Daniel |date=2014-12 |title=A simple structure-based model for the prediction of HIV-1 co-receptor tropism |url=https://biodatamining.biomedcentral.com/articles/10.1186/1756-0381-7-14 |journal=BioData Mining |language=en |volume=7 |issue=1 |pages=14 |doi=10.1186/1756-0381-7-14 |issn=1756-0381 |pmc=PMC4124776 |pmid=25120583}}</ref><ref>{{Cite journal |last=Riemenschneider |first=Mona |last2=Hummel |first2=Thomas |last3=Heider |first3=Dominik |date=2016-12 |title=SHIVA - a web application for drug resistance and tropism testing in HIV |url=http://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-016-1179-2 |journal=BMC Bioinformatics |language=en |volume=17 |issue=1 |pages=314 |doi=10.1186/s12859-016-1179-2 |issn=1471-2105 |pmc=PMC4994198 |pmid=27549230}}</ref>
A manifold of studies have proven AI to be advantageous for disease diagnosis, prognosis, and [[Disease informatics|disease monitoring]].<ref>{{Cite web |last=Digital Health Center of Excellence |date=06 December 2017 |title=What are examples of Software as a Medical Device? |url=https://www.fda.gov/medical-devices/software-medical-device-samd/what-are-examples-software-medical-device |publisher=U.S. Food and Drug Administration}}</ref><ref>{{Cite journal |last=Fatima |first=Meherwar |last2=Pasha |first2=Maruf |date=2017 |title=Survey of Machine Learning Algorithms for Disease Diagnostic |url=http://www.scirp.org/journal/PaperInformation.aspx?PaperID=73781&#abstract |journal=Journal of Intelligent Learning Systems and Applications |language=en |volume=09 |issue=01 |pages=1 |doi=10.4236/jilsa.2017.91001}}</ref> In [[cancer]] research, for instance, ML is used on [[omics]] data to gain deeper insights and understanding of the genetic and metabolic alterations that determine disease progression and enable tailored prognoses and monitoring.<ref>{{Cite journal |last=Batra |first=Richa |last2=Alcaraz |first2=Nicolas |last3=Gitzhofer |first3=Kevin |last4=Pauling |first4=Josch |last5=Ditzel |first5=Henrik J. |last6=Hellmuth |first6=Marc |last7=Baumbach |first7=Jan |last8=List |first8=Markus |date=2017-12 |title=On the performance of de novo pathway enrichment |url=http://www.nature.com/articles/s41540-017-0007-2 |journal=npj Systems Biology and Applications |language=en |volume=3 |issue=1 |pages=6 |doi=10.1038/s41540-017-0007-2 |issn=2056-7189 |pmc=PMC5445589 |pmid=28649433}}</ref><ref>{{Cite journal |last=Hauschild |first=A.-C. |last2=Baumbach |first2=J.I. |last3=Baumbach |first3=J. |date=2012 |title=Integrated statistical learning of metabolic ion mobility spectrometry profiles for pulmonary disease identification |url=http://www.funpecrp.com.br/gmr/year2012/vol11-3/pdf/gmr2065.pdf |journal=Genetics and Molecular Research |volume=11 |issue=3 |pages=2733–2744 |doi=10.4238/2012.July.10.17}}</ref><ref>{{Citation |last=Jeanquartier |first=Fleur |last2=Jean-Quartier |first2=Claire |last3=Kotlyar |first3=Max |last4=Tokar |first4=Tomas |last5=Hauschild |first5=Anne-Christin |last6=Jurisica |first6=Igor |last7=Holzinger |first7=Andreas |date=2016 |editor-last=Holzinger |editor-first=Andreas |title=Machine Learning for In Silico Modeling of Tumor Growth |url=http://link.springer.com/10.1007/978-3-319-50478-0_21 |work=Machine Learning for Health Informatics |language=en |publisher=Springer International Publishing |place=Cham |volume=9605 |pages=415–434 |doi=10.1007/978-3-319-50478-0_21 |isbn=978-3-319-50477-3 |access-date=2021-08-22}}</ref><ref>{{Cite journal |last=Wiwie |first=Christian |last2=Kuznetsova |first2=Irina |last3=Mostafa |first3=Ahmed |last4=Rauch |first4=Alexander |last5=Haakonsson |first5=Anders |last6=Barrio-Hernandez |first6=Inigo |last7=Blagoev |first7=Blagoy |last8=Mandrup |first8=Susanne |last9=Schmidt |first9=Harald H.H.W. |last10=Pleschka |first10=Stephan |last11=Röttger |first11=Richard |date=2019-05 |title=Time-Resolved Systems Medicine Reveals Viral Infection-Modulating Host Targets |url=https://www.liebertpub.com/doi/10.1089/sysm.2018.0013 |journal=Systems Medicine |language=en |volume=2 |issue=1 |pages=1–9 |doi=10.1089/sysm.2018.0013 |issn=2573-3370 |pmc=PMC6524659 |pmid=31119214}}</ref> Additionally, computational models on clinical [[information]] are used to assess individualized health risks, for instance, to identify high-risk patients for sepsis in intensive care units<ref>{{Cite journal |last=Calvert |first=Jacob |last2=Saber |first2=Nicholas |last3=Hoffman |first3=Jana |last4=Das |first4=Ritankar |date=2019-02-13 |title=Machine-Learning-Based Laboratory Developed Test for the Diagnosis of Sepsis in High-Risk Patients |url=http://www.mdpi.com/2075-4418/9/1/20 |journal=Diagnostics |language=en |volume=9 |issue=1 |pages=20 |doi=10.3390/diagnostics9010020 |issn=2075-4418 |pmc=PMC6468682 |pmid=30781800}}</ref><ref>{{Cite journal |last=Desautels |first=Thomas |last2=Calvert |first2=Jacob |last3=Hoffman |first3=Jana |last4=Jay |first4=Melissa |last5=Kerem |first5=Yaniv |last6=Shieh |first6=Lisa |last7=Shimabukuro |first7=David |last8=Chettipally |first8=Uli |last9=Feldman |first9=Mitchell D |last10=Barton |first10=Chris |last11=Wales |first11=David J |date=2016-09-30 |title=Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach |url=https://medinform.jmir.org/2016/3/e28/ |journal=JMIR Medical Informatics |language=en |volume=4 |issue=3 |pages=e28 |doi=10.2196/medinform.5909 |issn=2291-9694 |pmc=PMC5065680 |pmid=27694098}}</ref>, the analysis of longitudinal data for the early detection of heart failure<ref>{{Cite journal |last=Chen |first=Robert |last2=Stewart |first2=Walter F. |last3=Sun |first3=Jimeng |last4=Ng |first4=Kenney |last5=Yan |first5=Xiaowei |date=2019-10 |title=Recurrent Neural Networks for Early Detection of Heart Failure From Longitudinal Electronic Health Record Data: Implications for Temporal Modeling With Respect to Time Before Diagnosis, Data Density, Data Quantity, and Data Type |url=https://www.ahajournals.org/doi/10.1161/CIRCOUTCOMES.118.005114 |journal=Circulation: Cardiovascular Quality and Outcomes |language=en |volume=12 |issue=10 |doi=10.1161/CIRCOUTCOMES.118.005114 |issn=1941-7713 |pmc=PMC6814386 |pmid=31610714}}</ref>, or applications in [[Infectious disease informatics|infectious diseases]].<ref>{{Cite journal |last=Heider |first=Dominik |last2=Dybowski |first2=Jan Nikolaj |last3=Wilms |first3=Christoph |last4=Hoffmann |first4=Daniel |date=2014-12 |title=A simple structure-based model for the prediction of HIV-1 co-receptor tropism |url=https://biodatamining.biomedcentral.com/articles/10.1186/1756-0381-7-14 |journal=BioData Mining |language=en |volume=7 |issue=1 |pages=14 |doi=10.1186/1756-0381-7-14 |issn=1756-0381 |pmc=PMC4124776 |pmid=25120583}}</ref><ref>{{Cite journal |last=Riemenschneider |first=Mona |last2=Hummel |first2=Thomas |last3=Heider |first3=Dominik |date=2016-12 |title=SHIVA - a web application for drug resistance and tropism testing in HIV |url=http://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-016-1179-2 |journal=BMC Bioinformatics |language=en |volume=17 |issue=1 |pages=314 |doi=10.1186/s12859-016-1179-2 |issn=1471-2105 |pmc=PMC4994198 |pmid=27549230}}</ref>


Once the outcome of this development is sufficiently mature and robust to be published and used in routine treatment or diagnosis, there is a need to transfer this knowledge to other research groups and, ultimately, clinical practice. Therefore, a straightforward technology transfer to a manufacturer of [[medical device]]s would be beneficial.<ref>{{Cite journal |last=Brito |first=Jaqueline J |last2=Li |first2=Jun |last3=Moore |first3=Jason H |last4=Greene |first4=Casey S |last5=Nogoy |first5=Nicole A |last6=Garmire |first6=Lana X |last7=Mangul |first7=Serghei |date=2020-06-01 |title=Recommendations to enhance rigor and reproducibility in biomedical research |url=https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giaa056/5849489 |journal=GigaScience |language=en |volume=9 |issue=6 |pages=giaa056 |doi=10.1093/gigascience/giaa056 |issn=2047-217X |pmc=PMC7263079 |pmid=32479592}}</ref><ref>{{Cite journal |last=Riemenschneider |first=Mona |last2=Wienbeck |first2=Joachim |last3=Scherag |first3=André |last4=Heider |first4=Dominik |date=2018-06 |title=Data Science for Molecular Diagnostics Applications: From Academia to Clinic to Industry |url=http://www.liebertpub.com/doi/10.1089/sysm.2018.0002 |journal=Systems Medicine |language=en |volume=1 |issue=1 |pages=13–17 |doi=10.1089/sysm.2018.0002 |issn=2573-3370}}</ref>
Once the outcome of this development is sufficiently mature and robust to be published and used in routine treatment or diagnosis, there is a need to transfer this knowledge to other research groups and, ultimately, clinical practice. Therefore, a straightforward technology transfer to a manufacturer of [[medical device]]s would be beneficial.<ref name=":0">{{Cite journal |last=Brito |first=Jaqueline J |last2=Li |first2=Jun |last3=Moore |first3=Jason H |last4=Greene |first4=Casey S |last5=Nogoy |first5=Nicole A |last6=Garmire |first6=Lana X |last7=Mangul |first7=Serghei |date=2020-06-01 |title=Recommendations to enhance rigor and reproducibility in biomedical research |url=https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giaa056/5849489 |journal=GigaScience |language=en |volume=9 |issue=6 |pages=giaa056 |doi=10.1093/gigascience/giaa056 |issn=2047-217X |pmc=PMC7263079 |pmid=32479592}}</ref><ref name=":2">{{Cite journal |last=Riemenschneider |first=Mona |last2=Wienbeck |first2=Joachim |last3=Scherag |first3=André |last4=Heider |first4=Dominik |date=2018-06 |title=Data Science for Molecular Diagnostics Applications: From Academia to Clinic to Industry |url=http://www.liebertpub.com/doi/10.1089/sysm.2018.0002 |journal=Systems Medicine |language=en |volume=1 |issue=1 |pages=13–17 |doi=10.1089/sysm.2018.0002 |issn=2573-3370}}</ref>
 
==Challenges of scientific software development for health==
While the knowledge and technologies to develop effective and efficacious AI-driven [[clinical decision support system]]s exist, a manifold of pressing issues hinders further reuse in research and transfer to clinical practice. In software development projects in the industry, specialized developers typically work in large teams with considerable resources and are able to focus on usability and reusability.<ref>{{Cite journal |last=Guellec, D.; van Pottelsberghe de la Potterie, B. |date=2000-06-14 |title=The Impact of Public R&D Expenditure on Business R&D |url=https://www.oecd-ilibrary.org/science-and-technology/the-impact-of-public-r-d-expenditure-on-business-r-d_670385851815 |journal=OECD Science, Technology and Industry Working Papers |language=en |volume=2000/04 |issue= |doi=10.1787/670385851815}}</ref><ref name=":1">{{Cite journal |last=Mangul |first=Serghei |last2=Mosqueiro |first2=Thiago |last3=Abdill |first3=Richard J. |last4=Duong |first4=Dat |last5=Mitchell |first5=Keith |last6=Sarwal |first6=Varuni |last7=Hill |first7=Brian |last8=Brito |first8=Jaqueline |last9=Littman |first9=Russell Jared |last10=Statz |first10=Benjamin |last11=Lam |first11=Angela Ka-Mei |date=2019-06-20 |title=Challenges and recommendations to improve the installability and archival stability of omics computational tools |url=https://dx.plos.org/10.1371/journal.pbio.3000333 |journal=PLOS Biology |language=en |volume=17 |issue=6 |pages=e3000333 |doi=10.1371/journal.pbio.3000333 |issn=1545-7885 |pmc=PMC6605654 |pmid=31220077}}</ref> In contrast, academic teams often consist of small groups of researchers (e.g., graduate students and postdoctoral scholars) who are typically not trained software engineers and only have temporary contracts and frequent turnover. Thus, individuals often develop software on a one-person-one-project basis.<ref name=":0" /><ref name=":1" />
 
Moreover, funders and the academic hiring and promotion processes incentivize the pressure to publish and focus on “novelty” rather than software quality. Thus, it entices researchers to focus on theoretical aspects and proof of concept development.<ref name=":0" /><ref>{{Cite journal |last=Mangul |first=Serghei |last2=Martin |first2=Lana S. |last3=Eskin |first3=Eleazar |last4=Blekhman |first4=Ran |date=2019-12 |title=Improving the usability and archival stability of bioinformatics software |url=https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1649-8 |journal=Genome Biology |language=en |volume=20 |issue=1 |pages=47, s13059–019–1649-8 |doi=10.1186/s13059-019-1649-8 |issn=1474-760X |pmc=PMC6391762 |pmid=30813962}}</ref> Therefore, most researchers implement software in a prototype-centered manner, which often lacks [[Quality (business)|quality]] checks such as systematic testing and may be published quickly.<ref>{{Cite journal |last=Lee |first=Graham |last2=Bacon |first2=Sebastian |last3=Bush |first3=Ian |last4=Fortunato |first4=Laura |last5=Gavaghan |first5=David |last6=Lestang |first6=Thibault |last7=Morton |first7=Caroline |last8=Robinson |first8=Martin |last9=Rocca-Serra |first9=Philippe |last10=Sansone |first10=Susanna-Assunta |last11=Webb |first11=Helena |date=2021-02 |title=Barely sufficient practices in scientific computing |url=https://linkinghub.elsevier.com/retrieve/pii/S2666389921000167 |journal=Patterns |language=en |volume=2 |issue=2 |pages=100206 |doi=10.1016/j.patter.2021.100206 |pmc=PMC7892476 |pmid=33659915}}</ref> However, these implementations often lack crucial qualities required for long-term reuse, such as documentation, usability, appropriate performance for real-life application, user-friendly interfaces, reusability, or minimized risk for potential users.<ref name=":0" /><ref name=":2" />




Revision as of 18:44, 22 August 2021

Full article title Fostering reproducibility, reusability, and technology transfer in health informatics
Journal iScience
Author(s) Hauschild, Anne-Christin; Eick, Lisa; Wienbeck, Joachim; Heider, Dominik
Author affiliation(s) Philipps University of Marburg
Primary contact Email: dominik dot heider at uni-marburg dot de
Year published 2021
Volume and issue 24(7)
Article # 102803
DOI 10.1016/j.isci.2021.102803
ISSN 2589-0042
Distribution license Creative Commons Attribution 4.0 International
Website https://www.sciencedirect.com/science/article/pii/S2589004221007719
Download https://www.sciencedirect.com/science/article/pii/S2589004221007719/pdfft (PDF)
Emblem-important-yellow.svg This article should be considered a work in progress and incomplete. Consider this article incomplete until this notice is removed.

Abstract

Computational methods can transform healthcare. In particular, health informatics combined with artificial intelligence (AI) has shown tremendous potential when applied in various fields of medical research and has opened a new era for precision medicine. The development of reusable biomedical software for research or clinical practice is time-consuming and requires rigorous compliance with quality requirements as defined by international standards.

However, research projects rarely implement such measures, hindering smooth technology transfer to the research community or manufacturers, as well as reproducibility and reusability.

Here, we present a guideline for quality management systems (QMS) for academic organizations incorporating the essential components, while confining the requirements to an easily manageable effort. It provides a starting point to effortlessly implement a QMS tailored to specific needs and greatly facilitates technology transfer in a controlled manner, thereby supporting reproducibility and reusability.

Ultimately, the emerging standardized workflows can pave the way for an accelerated deployment in clinical practice.

Keywords: health informatics, bioinformatics, software engineering, software robustness


Abst1 Hauschild iScience2021 24-7.jpg

Graphical abstract

Introduction

Computational approaches offer new opportunities to transform health care. In particular, modern artificial intelligence (AI) and machine learning (ML) techniques have shown substantial potential when applied in various fields of medical research and therefore have opened up a new era for precision medicine. (Hawgood et al., 2015)[1] In the last decade, universities and other research organizations supported and encouraged by public funding agencies have allocated tremendous efforts to develop and enhance such predictive software models, algorithms, and “systems as medical devices” (SaMD) for clinical research and application.

A manifold of studies have proven AI to be advantageous for disease diagnosis, prognosis, and disease monitoring.[2][3] In cancer research, for instance, ML is used on omics data to gain deeper insights and understanding of the genetic and metabolic alterations that determine disease progression and enable tailored prognoses and monitoring.[4][5][6][7] Additionally, computational models on clinical information are used to assess individualized health risks, for instance, to identify high-risk patients for sepsis in intensive care units[8][9], the analysis of longitudinal data for the early detection of heart failure[10], or applications in infectious diseases.[11][12]

Once the outcome of this development is sufficiently mature and robust to be published and used in routine treatment or diagnosis, there is a need to transfer this knowledge to other research groups and, ultimately, clinical practice. Therefore, a straightforward technology transfer to a manufacturer of medical devices would be beneficial.[13][14]

Challenges of scientific software development for health

While the knowledge and technologies to develop effective and efficacious AI-driven clinical decision support systems exist, a manifold of pressing issues hinders further reuse in research and transfer to clinical practice. In software development projects in the industry, specialized developers typically work in large teams with considerable resources and are able to focus on usability and reusability.[15][16] In contrast, academic teams often consist of small groups of researchers (e.g., graduate students and postdoctoral scholars) who are typically not trained software engineers and only have temporary contracts and frequent turnover. Thus, individuals often develop software on a one-person-one-project basis.[13][16]

Moreover, funders and the academic hiring and promotion processes incentivize the pressure to publish and focus on “novelty” rather than software quality. Thus, it entices researchers to focus on theoretical aspects and proof of concept development.[13][17] Therefore, most researchers implement software in a prototype-centered manner, which often lacks quality checks such as systematic testing and may be published quickly.[18] However, these implementations often lack crucial qualities required for long-term reuse, such as documentation, usability, appropriate performance for real-life application, user-friendly interfaces, reusability, or minimized risk for potential users.[13][14]


References

  1. ↑ Hawgood, Sam; Hook-Barnard, India G.; O’Brien, Theresa C.; Yamamoto, Keith R. (12 August 2015). "Precision medicine: Beyond the inflection point" (in en). Science Translational Medicine 7 (300): 300ps17–300ps17. doi:10.1126/scitranslmed.aaa9970. ISSN 1946-6234. https://stm.sciencemag.org/lookup/doi/10.1126/scitranslmed.aaa9970. 
  2. ↑ Digital Health Center of Excellence (6 December 2017). "What are examples of Software as a Medical Device?". U.S. Food and Drug Administration. https://www.fda.gov/medical-devices/software-medical-device-samd/what-are-examples-software-medical-device. 
  3. ↑ Fatima, Meherwar; Pasha, Maruf (2017). "Survey of Machine Learning Algorithms for Disease Diagnostic" (in en). Journal of Intelligent Learning Systems and Applications 09 (01): 1. doi:10.4236/jilsa.2017.91001. http://www.scirp.org/journal/PaperInformation.aspx?PaperID=73781&#abstract. 
  4. ↑ Batra, Richa; Alcaraz, Nicolas; Gitzhofer, Kevin; Pauling, Josch; Ditzel, Henrik J.; Hellmuth, Marc; Baumbach, Jan; List, Markus (1 December 2017). "On the performance of de novo pathway enrichment" (in en). npj Systems Biology and Applications 3 (1): 6. doi:10.1038/s41540-017-0007-2. ISSN 2056-7189. PMC PMC5445589. PMID 28649433. http://www.nature.com/articles/s41540-017-0007-2. 
  5. ↑ Hauschild, A.-C.; Baumbach, J.I.; Baumbach, J. (2012). "Integrated statistical learning of metabolic ion mobility spectrometry profiles for pulmonary disease identification". Genetics and Molecular Research 11 (3): 2733–2744. doi:10.4238/2012.July.10.17. http://www.funpecrp.com.br/gmr/year2012/vol11-3/pdf/gmr2065.pdf. 
  6. ↑ Jeanquartier, Fleur; Jean-Quartier, Claire; Kotlyar, Max; Tokar, Tomas; Hauschild, Anne-Christin; Jurisica, Igor; Holzinger, Andreas (2016), Holzinger, Andreas, ed., "Machine Learning for In Silico Modeling of Tumor Growth" (in en), Machine Learning for Health Informatics (Cham: Springer International Publishing) 9605: 415–434, doi:10.1007/978-3-319-50478-0_21, ISBN 978-3-319-50477-3, http://link.springer.com/10.1007/978-3-319-50478-0_21 
  7. ↑ Wiwie, Christian; Kuznetsova, Irina; Mostafa, Ahmed; Rauch, Alexander; Haakonsson, Anders; Barrio-Hernandez, Inigo; Blagoev, Blagoy; Mandrup, Susanne et al. (1 May 2019). "Time-Resolved Systems Medicine Reveals Viral Infection-Modulating Host Targets" (in en). Systems Medicine 2 (1): 1–9. doi:10.1089/sysm.2018.0013. ISSN 2573-3370. PMC PMC6524659. PMID 31119214. https://www.liebertpub.com/doi/10.1089/sysm.2018.0013. 
  8. ↑ Calvert, Jacob; Saber, Nicholas; Hoffman, Jana; Das, Ritankar (13 February 2019). "Machine-Learning-Based Laboratory Developed Test for the Diagnosis of Sepsis in High-Risk Patients" (in en). Diagnostics 9 (1): 20. doi:10.3390/diagnostics9010020. ISSN 2075-4418. PMC PMC6468682. PMID 30781800. http://www.mdpi.com/2075-4418/9/1/20. 
  9. ↑ Desautels, Thomas; Calvert, Jacob; Hoffman, Jana; Jay, Melissa; Kerem, Yaniv; Shieh, Lisa; Shimabukuro, David; Chettipally, Uli et al. (30 September 2016). "Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach" (in en). JMIR Medical Informatics 4 (3): e28. doi:10.2196/medinform.5909. ISSN 2291-9694. PMC PMC5065680. PMID 27694098. https://medinform.jmir.org/2016/3/e28/. 
  10. ↑ Chen, Robert; Stewart, Walter F.; Sun, Jimeng; Ng, Kenney; Yan, Xiaowei (1 October 2019). "Recurrent Neural Networks for Early Detection of Heart Failure From Longitudinal Electronic Health Record Data: Implications for Temporal Modeling With Respect to Time Before Diagnosis, Data Density, Data Quantity, and Data Type" (in en). Circulation: Cardiovascular Quality and Outcomes 12 (10). doi:10.1161/CIRCOUTCOMES.118.005114. ISSN 1941-7713. PMC PMC6814386. PMID 31610714. https://www.ahajournals.org/doi/10.1161/CIRCOUTCOMES.118.005114. 
  11. ↑ Heider, Dominik; Dybowski, Jan Nikolaj; Wilms, Christoph; Hoffmann, Daniel (1 December 2014). "A simple structure-based model for the prediction of HIV-1 co-receptor tropism" (in en). BioData Mining 7 (1): 14. doi:10.1186/1756-0381-7-14. ISSN 1756-0381. PMC PMC4124776. PMID 25120583. https://biodatamining.biomedcentral.com/articles/10.1186/1756-0381-7-14. 
  12. ↑ Riemenschneider, Mona; Hummel, Thomas; Heider, Dominik (1 December 2016). "SHIVA - a web application for drug resistance and tropism testing in HIV" (in en). BMC Bioinformatics 17 (1): 314. doi:10.1186/s12859-016-1179-2. ISSN 1471-2105. PMC PMC4994198. PMID 27549230. http://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-016-1179-2. 
  13. ↑ 13.0 13.1 13.2 13.3 Brito, Jaqueline J; Li, Jun; Moore, Jason H; Greene, Casey S; Nogoy, Nicole A; Garmire, Lana X; Mangul, Serghei (1 June 2020). "Recommendations to enhance rigor and reproducibility in biomedical research" (in en). GigaScience 9 (6): giaa056. doi:10.1093/gigascience/giaa056. ISSN 2047-217X. PMC PMC7263079. PMID 32479592. https://academic.oup.com/gigascience/article/doi/10.1093/gigascience/giaa056/5849489. 
  14. ↑ 14.0 14.1 Riemenschneider, Mona; Wienbeck, Joachim; Scherag, André; Heider, Dominik (1 June 2018). "Data Science for Molecular Diagnostics Applications: From Academia to Clinic to Industry" (in en). Systems Medicine 1 (1): 13–17. doi:10.1089/sysm.2018.0002. ISSN 2573-3370. http://www.liebertpub.com/doi/10.1089/sysm.2018.0002. 
  15. ↑ Guellec, D.; van Pottelsberghe de la Potterie, B. (14 June 2000). "The Impact of Public R&D Expenditure on Business R&D" (in en). OECD Science, Technology and Industry Working Papers 2000/04. doi:10.1787/670385851815. https://www.oecd-ilibrary.org/science-and-technology/the-impact-of-public-r-d-expenditure-on-business-r-d_670385851815. 
  16. ↑ 16.0 16.1 Mangul, Serghei; Mosqueiro, Thiago; Abdill, Richard J.; Duong, Dat; Mitchell, Keith; Sarwal, Varuni; Hill, Brian; Brito, Jaqueline et al. (20 June 2019). "Challenges and recommendations to improve the installability and archival stability of omics computational tools" (in en). PLOS Biology 17 (6): e3000333. doi:10.1371/journal.pbio.3000333. ISSN 1545-7885. PMC PMC6605654. PMID 31220077. https://dx.plos.org/10.1371/journal.pbio.3000333. 
  17. ↑ Mangul, Serghei; Martin, Lana S.; Eskin, Eleazar; Blekhman, Ran (1 December 2019). "Improving the usability and archival stability of bioinformatics software" (in en). Genome Biology 20 (1): 47, s13059–019–1649-8. doi:10.1186/s13059-019-1649-8. ISSN 1474-760X. PMC PMC6391762. PMID 30813962. https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1649-8. 
  18. ↑ Lee, Graham; Bacon, Sebastian; Bush, Ian; Fortunato, Laura; Gavaghan, David; Lestang, Thibault; Morton, Caroline; Robinson, Martin et al. (1 February 2021). "Barely sufficient practices in scientific computing" (in en). Patterns 2 (2): 100206. doi:10.1016/j.patter.2021.100206. PMC PMC7892476. PMID 33659915. https://linkinghub.elsevier.com/retrieve/pii/S2666389921000167. 

Notes

This presentation is faithful to the original, with only a few minor changes to presentation, though grammar and word usage was substantially updated for improved readability. In some cases important information was missing from the references, and that information was added. The original article lists references alphabetically, but this version—by design—lists them in order of appearance.

Retrieved from "https://www.limswiki.org/index.php?title=Journal:Fostering_reproducibility,_reusability,_and_technology_transfer_in_health_informatics&oldid=43817"