Learning Disease Progression Models That Capture Health Disparities

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chiang, Erica, Shanmugam, Divya, Beecy, Ashley N., Sayer, Gabriel, Estrin, Deborah, Garg, Nikhil, Pierson, Emma
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910922163879936
author Chiang, Erica
Shanmugam, Divya
Beecy, Ashley N.
Sayer, Gabriel
Estrin, Deborah
Garg, Nikhil
Pierson, Emma
author_facet Chiang, Erica
Shanmugam, Divya
Beecy, Ashley N.
Sayer, Gabriel
Estrin, Deborah
Garg, Nikhil
Pierson, Emma
contents 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 any of these disparities can result in biased estimates of severity (e.g., underestimating severity for disadvantaged groups). 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 while inferring disease severity meaningfully shifts which patients are considered high-risk.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16406
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Disease Progression Models That Capture Health Disparities
Chiang, Erica
Shanmugam, Divya
Beecy, Ashley N.
Sayer, Gabriel
Estrin, Deborah
Garg, Nikhil
Pierson, Emma
Machine Learning
Artificial Intelligence
Computers and Society
Applications
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 any of these disparities can result in biased estimates of severity (e.g., underestimating severity for disadvantaged groups). 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 while inferring disease severity meaningfully shifts which patients are considered high-risk.
title Learning Disease Progression Models That Capture Health Disparities
topic Machine Learning
Artificial Intelligence
Computers and Society
Applications
url https://arxiv.org/abs/2412.16406