Learning Disease Progression Models That Capture Health Disparities

Erica Chiang, Divya M Shanmugam, Ashley Beecy, Gabriel Sayer, Deborah Estrin, Nikhil Garg, Emma Pierson
Proceedings of the sixth Conference on Health, Inference, and Learning, PMLR 287:1-29, 2025.

Abstract

Disease progression models are widely used to inform the diagnosis and treatment of many progressive diseases. However, a significant limitation of existing models is that they do not account for health disparities that can bias the observed data. To address this, we develop an interpretable Bayesian disease progression model that captures three key health disparities: certain patient populations may (1) start receiving care only when their disease is more severe, (2) experience faster disease progression even while receiving care, or (3) receive follow-up care less frequently conditional on disease severity. We show theoretically and empirically that failing to account for disparities produces biased estimates of severity (underestimating severity for disadvantaged groups, for example). On a dataset of heart failure patients, we show that our model can identify groups that face each type of health disparity, and that accounting for these disparities meaningfully shifts which patients are considered high-risk.

Cite this Paper

BibTeX
@InProceedings{pmlr-v287-chiang25a, title = {Learning Disease Progression Models That Capture Health Disparities}, author = {Chiang, Erica and Shanmugam, Divya M and Beecy, Ashley and Sayer, Gabriel and Estrin, Deborah and Garg, Nikhil and Pierson, Emma}, booktitle = {Proceedings of the sixth Conference on Health, Inference, and Learning}, pages = {1--29}, year = {2025}, editor = {Xu, Xuhai Orson and Choi, Edward and Singhal, Pankhuri and Gerych, Walter and Tang, Shengpu and Agrawal, Monica and Subbaswamy, Adarsh and Sizikova, Elena and Dunn, Jessilyn and Daneshjou, Roxana and Sarker, Tasmie and McDermott, Matthew and Chen, Irene}, volume = {287}, series = {Proceedings of Machine Learning Research}, month = {25--27 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v287/main/assets/chiang25a/chiang25a.pdf}, url = {https://proceedings.mlr.press/v287/chiang25a.html}, abstract = {Disease progression models are widely used to inform the diagnosis and treatment of many progressive diseases. However, a significant limitation of existing models is that they do not account for health disparities that can bias the observed data. To address this, we develop an interpretable Bayesian disease progression model that captures three key health disparities: certain patient populations may (1) start receiving care only when their disease is more severe, (2) experience faster disease progression even while receiving care, or (3) receive follow-up care less frequently conditional on disease severity. We show theoretically and empirically that failing to account for disparities produces biased estimates of severity (underestimating severity for disadvantaged groups, for example). On a dataset of heart failure patients, we show that our model can identify groups that face each type of health disparity, and that accounting for these disparities meaningfully shifts which patients are considered high-risk.} }
Endnote
%0 Conference Paper %T Learning Disease Progression Models That Capture Health Disparities %A Erica Chiang %A Divya M Shanmugam %A Ashley Beecy %A Gabriel Sayer %A Deborah Estrin %A Nikhil Garg %A Emma Pierson %B Proceedings of the sixth Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2025 %E Xuhai Orson Xu %E Edward Choi %E Pankhuri Singhal %E Walter Gerych %E Shengpu Tang %E Monica Agrawal %E Adarsh Subbaswamy %E Elena Sizikova %E Jessilyn Dunn %E Roxana Daneshjou %E Tasmie Sarker %E Matthew McDermott %E Irene Chen %F pmlr-v287-chiang25a %I PMLR %P 1--29 %U https://proceedings.mlr.press/v287/chiang25a.html %V 287 %X Disease progression models are widely used to inform the diagnosis and treatment of many progressive diseases. However, a significant limitation of existing models is that they do not account for health disparities that can bias the observed data. To address this, we develop an interpretable Bayesian disease progression model that captures three key health disparities: certain patient populations may (1) start receiving care only when their disease is more severe, (2) experience faster disease progression even while receiving care, or (3) receive follow-up care less frequently conditional on disease severity. We show theoretically and empirically that failing to account for disparities produces biased estimates of severity (underestimating severity for disadvantaged groups, for example). On a dataset of heart failure patients, we show that our model can identify groups that face each type of health disparity, and that accounting for these disparities meaningfully shifts which patients are considered high-risk.
APA
Chiang, E., Shanmugam, D.M., Beecy, A., Sayer, G., Estrin, D., Garg, N. & Pierson, E.. (2025). Learning Disease Progression Models That Capture Health Disparities. Proceedings of the sixth Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 287:1-29 Available from https://proceedings.mlr.press/v287/chiang25a.html.

Related Material