Research | Reproducibility in Machine Learning
Reproducibility in machine learning for health research: Still a ways to go
ABSTRACT: 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.
Read the full publication here.
Related work
News
- January 8, 2026: Evidation Launches Temporal Proteomics Platform to Power Autoimmune Research
- December 16, 2025: Evidation Shares Insights on Real-World GLP-1 Dosing Behaviors from Over 60,000 Individuals
- December 2, 2025: Evidation Appoints Dr. Ghazanfar Khan as Chief Medical Officer
Good reads
- Digital Divide Goes Beyond Broadband, Rests with Digital Health Literacy
- Paying Research Participants — A Lot — May Be a Key to Increasing Diversity in Studies
- Bioethics International Reveals Index to Score Pharma on Trial Diversity
Upcoming events
Thanks to everyone who took the time to meet with us in San Francisco at this year’s J.P. Morgan Annual Conference and its surrounding events. Our team looks forward to staying in touch and helping you produce better health outcomes in 2023!
Get to know your Evidation team
Bertina Yen, Senior Vice President of People & Community
Bertina Yen is Evidation's Senior Vice President of People & Community, where she is responsible for the end-to-end employee experience and building a community that supports everyone's ability to show up as their authentic selves and perform their best work.
Outside of work, she enjoys hiking, traveling, and watching anything with a live audience (sporting events, plays, movies). She also starts every morning by completing at least one crossword puzzle!
Connect with Bertina here.