A Machine-Learned Comorbidity Index
For healthcare researchers and practitioners, MLCI provides a more flexible and outcome-specific comorbidity index that captures nonlinear risk relationships, addressing limitations of existing mortality-centric scores.
The authors propose a Machine-Learned Comorbidity Index (MLCI) that learns a single scalar from diagnosis codes by maximizing dependence with multiple clinical outcomes, outperforming traditional comorbidity scores across multiple EHR datasets.
Traditional comorbidity scores (e.g., Charlson and Elixhauser) are widely used for risk adjustment and patient stratification, but they have two key limitations: (i) they are largely mortality-centric and do not align well with other clinical outcomes, and (ii) 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 learned score and multiple clinical outcomes. MLCI captures nonlinear risk-outcome dependence and is supported by a theory that characterizes when a unified, informative admission-level ordering can be achieved across outcomes. Empirical results on multiple benchmark electronic health record (EHR) datasets show that MLCI outperforms strong baselines across multiple evaluation metrics.