Vokinger KN, Feuerriegel S, Kesselheim AS - Communications Medicine
- Commentary & Opinion
- Regulation and Clinical Evidence
Summary:
Machine learning systems used in medical applications are vulnerable to multiple sources of bias that can degrade performance and affect clinical outcomes. The authors propose mitigation strategies that address bias throughout the entire development pipeline of medical machine learning systems.
VIEW SOURCE
Recent Work from PORTAL
How Congress Can Fix Expert Advisory Committees
Daval CJR, Kesselheim AS - STAT
- Commentary & Opinion
- Regulation and Clinical Evidence
International Regulatory Status and Reimbursement Recommendations of Haematological Malignancy Drugs Withdrawn from the FDA Accelerated Approval Pathway
Mulsant SS, Kesselheim AS, Naci H - Journal of Cancer Policy
- Research Publications
- Price, Value, and Access
- Regulation and Clinical Evidence
The Impact of Semantics in Medicines Regulation
Costa E, Kesselheim AS - Journal of Law, Medicine, & Ethics
- Commentary & Opinion
- Innovation Incentives and Competition
- Regulation and Clinical Evidence
Program On Regulation, Therapeutics, And Law (PORTAL)
Division of Pharmacoepidemiology and Pharmacoeconomics
Brigham and Women's Hospital • Harvard Medical School
41 Avenue Louis Pasteur, Suite 0B17, Boston, MA 02115
©2026 Program On Regulation, Therapeutics, And Law (PORTAL). All rights reserved.