Reproducibility in machine learning for health research: Still a ways to go.

Machine Learning Reproducibility of Results

Journal

Science translational medicine
ISSN: 1946-6242
Titre abrégé: Sci Transl Med
Pays: United States
ID NLM: 101505086

Informations de publication

Date de publication:
24 03 2021
Historique:
received: 10 02 2020
accepted: 02 10 2020
entrez: 25 3 2021
pubmed: 26 3 2021
medline: 13 7 2021
Statut: ppublish

Résumé

Machine learning for health must be reproducible to ensure reliable clinical use. We evaluated 511 scientific papers across several machine learning subfields and found that machine learning for health compared poorly to other areas regarding reproducibility metrics, such as dataset and code accessibility. We propose recommendations to address this problem.

Identifiants

DOI: 10.1126/scitranslmed.abb1655 PMID: 33762434
pubmed: 33762434
pii: 13/586/eabb1655
doi: 10.1126/scitranslmed.abb1655
pii:
doi:

Types de publication

Journal Article Research Support, N.I.H., Extramural Research Support, Non-U.S. Gov't Review

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

Copyright © 2021 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works.

Auteurs

Matthew B A McDermott (MBA)

Massachusetts Institute of Technology, Cambridge, MA 02139, USA. mmd@mit.edu.
ORCID: 0000-0001-6048-9707

Shirly Wang (S)

Department of Computer Science, University of Toronto, Toronto, ON M5T 3A1, Canada.
Layer 6 AI, TD Bank Group, Toronto, ON M5G 1M1, Canada.

Nikki Marinsek (N)

Evidation Health Inc., San Mateo, CA 94402, USA.

Rajesh Ranganath (R)

Center for Data Science and Department of Computer Science, Courant Institute of Mathematical Sciences, New York University, New York, NY 10011, USA ; Department of Population Health, NYU Langone Health, New York, NY, USA 10016.

Luca Foschini (L)

Evidation Health Inc., San Mateo, CA 94402, USA.
ORCID: 0000-0003-1409-3570

Marzyeh Ghassemi (M)

Department of Computer Science, University of Toronto, Toronto, ON M5T 3A1, Canada.
Vector Institute, University of Toronto, Toronto, ON M5G 1M1, Canada.
Department of Medicine, University of Toronto, Toronto, ON M5S 1A8, Canada.
ORCID: 0000-0001-6349-7251

Articles similaires

Relative victimization scale: initial development and retrospective reports of the impact on mental health.

Hacer Belen
1.00
Humans Male Crime Victims Female Bullying

Exploring blood-brain barrier passage using atomic weighted vector and machine learning.

Yoan Martínez-López, Paulina Phoobane, Yanaima Jauriga et al.
1.00
Blood-Brain Barrier Machine Learning Humans Support Vector Machine Software

Cultural adaptation and validation of the Sinhala version of the spiritual needs assessment for patients (S-SNAP) questionnaire.

Udayangani Ramadasa, Shehan Silva, Suraj Perera et al.
1.00
Humans Middle Aged Female Male Surveys and Questionnaires

Understanding the role of machine learning in predicting progression of osteoarthritis.

Simone Castagno, Benjamin Gompels, Estelle Strangmark et al.
1.00
Humans Disease Progression Machine Learning Osteoarthritis

Classifications MeSH

questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Apprentissage machine › Reproducibility in machine learning for health...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Méthodologie en recherche épidémiologique › Reproductibilité des résultats › Reproducibility in machine learning for health...