A Machine-Learned Comorbidity Index
Suleman Baloch, Kishlay Jha, Alberto Segre, Philip Polgreen, Bijaya Adhikari
Abstract
Traditional comorbidity scores (e.g., Charlson and Elixhauser) are widely used for risk adjustment and patient stratification, but they have two key limitations: they are largely mortality-centric and do not align well with other outcomes, and their linear, rule-based structure cannot capture nonlinear, outcome-specific risk relationships. We propose a Machine-Learned Comorbidity Index (MLCI) that maps diagnosis codes to a single scalar by maximizing the normalized Hilbert–Schmidt Independence Criterion (nHSIC) between the score and multiple clinical outcomes. MLCI captures nonlinear risk–outcome dependence and is supported by a novel theory that characterizes when a unified, informative patient ordering can be achieved across outcomes. Empirical results on multiple benchmark electronic health record (EHR) datasets show that MLCI outperforms strong single-index baselines across multiple evaluation metrics.
BibTeX
@inproceedings{
baloch2026a,
title={A Machine-Learned Comorbidity Index},
author={Suleman Baloch and Kishlay Jha and Alberto Maria Segre and Philip M. Polgreen and Bijaya Adhikari},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=C6ZTjSXbz7}
}