Special Collection
Operationalising Fairness in Medical Algorithms
The world is abuzz with applications of data science in almost every field: commerce, transportation, banking, and more recently, healthcare.
Data is proliferating not only because of widespread digital health record adoption, but also because of the growing use of wireless technologies for ambulatory monitoring.
These breakthroughs are due to rediscovered and newly created algorithms, improved computing power and, most importantly, the availability of bigger and increasingly reliable data with which to train these algorithms. From machine learning to artificial intelligence, data science is expected to transform healthcare. Such technological progress offers paths towards discoveries and more precise diagnostic and treatment prescriptions not previously possible. However, numerous critical ethical issues have been identified, spanning privacy, data protection, transparency and explainability, responsibility, and bias.
It is widely recognised that many of the machine learning models and tools may have discriminatory impact thereby inadvertently encoding and perpetuating societal biases, thereby contributing to health inequities.
We propose that machine learning algorithms should not be focused solely on accuracy, but should also be evaluated with respect to how they might impact disparities in patient outcomes.
This special issue aims to bring together the growing community of healthcare practitioners, social scientists, policymakers, engineers and computer scientists to design and discuss practical solutions to address algorithmic fairness and accountability.
Original research
Identifying undercompensated groups defined by multiple attributes in risk adjustment
Zink A, Rose S
10.1136/bmjhci-2021-100414
Can medical algorithms be fair? Three ethical quandaries and one dilemma
Bærøe K, Gundersen T, Henden E, et al
10.1136/bmjhci-2021-100445
Resampling to address inequities in predictive modeling of suicide deaths
Reeves M, Bhat HS, Goldman-Mellor S
10.1136/bmjhci-2021-100456
Evaluating algorithmic fairness in the presence of clinical guidelines: the case of atherosclerotic cardiovascular disease risk estimation
Foryciarz A, Pfohl SR, Patel B, et al
10.1136/bmjhci-2021-100460
Operationalising fairness in medical AI adoption: detection of early Alzheimer’s disease with 2D CNN
Heising L, Angelopoulos S
10.1136/bmjhci-2021-100485
Investigating for bias in healthcare algorithms: a sex-stratified analysis of supervised machine learning models in liver disease prediction
Straw I, Wu H
10.1136/bmjhci-2021-100457
Review
A proposal for developing a platform that evaluates algorithmic equity and accuracy
Cerrato P, Halamka J, Pencina M
10.1136/bmjhci-2021-100423
Communication
Global disparity bias in ophthalmology artificial intelligence applications
Nakayama LF, Kras A, Ribeiro LZ, et al
10.1136/bmjhci-2021-100470
Guest Editors
Leo Anthony Celi, Harvard Medical School
Miguel Angel Armengol de la Hoz, Regional Ministry of Health of Southern Spain
Sonali Parbhoo, Harvard University
Judy Wawira Gichoya, Emory University