Eva Aagaard | Searcharxiv

arXiv2025

An MLI-Guided Framework for Subgroup-Aware Modeling in Electronic Health Records (AdaptHetero)

Machine learning interpretation (MLI) has primarily been leveraged to foster clinician trust and extract insights from electronic health records (EHRs), rather than to guide subgroup-specific, operationalizable modeling strategies. To bridge this gap, we propose AdaptHetero, a novel MLI-driven framework that transforms interpretability insights into actionable guidance for tailoring model training and evaluation across subpopulations. Evaluated on three large-scale EHR datasets -- GOSSIS-1-eICU, WiDS, and MIMIC-IV -- AdaptHetero consistently uncovers heterogeneous model behaviors in predicting ICU mortality, in-hospital death, and hidden hypoxemia. Integrating SHAP-based interpretation with unsupervised clustering, AdaptHetero identifies clinically meaningful, subgroup-specific characteristics, improving predictive performance across many subpopulations (with gains up to 174.39 percent) while proactively flagging potential risks in others. These results highlight the framework's promise for more robust, equitable, and context-aware clinical deployment.

cs.LG↗

arXiv2025

Translating Machine Learning Interpretability into Clinical Insights for ICU Mortality Prediction

Current research efforts largely focus on employing at most one interpretable method to elucidate machine learning (ML) model performance. However, significant barriers remain in translating these interpretability techniques into actionable insights for clinicians, notably due to complexities such as variability across clinical settings and the Rashomon effect. In this study, we developed and rigorously evaluated two ML models along with interpretation mechanisms, utilizing data from 131,051 ICU admissions across 208 hospitals in the United States, sourced from the eICU Collaborative Research Database. We examined two datasets: one with imputed missing values (130,810 patients, 5.58% ICU mortality) and another excluding patients with missing data (5,661 patients, 23.65% ICU mortality). The random forest (RF) model demonstrated an AUROC of 0.912 with the first dataset and 0.839 with the second dataset, while the XGBoost model achieved an AUROC of 0.924 with the first dataset and 0.834 with the second dataset. Consistently identified predictors of ICU mortality across datasets, cross-validation folds, models, and explanation mechanisms included lactate levels, arterial pH, body temperature, and others. By aligning with routinely collected clinical variables, this study aims to enhance ML model interpretability for clinical use, promote greater understanding and adoption among clinicians, and ultimately contribute to improved patient outcomes.

cs.CY↗