Key result
Adding social determinants of health to machine learning models modestly improves heart failure risk prediction.
Why the study?
To develop and validate subtype-specific, fairness-aware ML models integrating clinical and SDoH information to predict 6-month adverse outcomes in HFpEF or HFrEF and assess demographic subgroup error disparities.
Does integrating social determinants of health into fairness-aware machine learning models improve the prediction of 6-month readmission or mortality in adult patients with HFpEF or HFrEF?
Cohort (n=6,207)
No
Does integrating social determinants of health into fairness-aware machine learning models improve the prediction of 6-month readmission or mortality in adult patients with HFpEF or HFrEF?
Integrating social determinants of health into fairness-aware machine learning models provides modest discrimination gains and reduces subgroup error disparities for predicting 6-month readmission or mortality in heart failure patients.
Answers are grounded in this paper and cite their sources.
Modest C-statistic gains from adding SDOH to HF readmission ML models should not yet change practice; hypothesis-generating and requires prospective validation.
Objectives: Develop and validate subtype-specific, fairness-aware machine learning (ML) models that integrate clinical and social determinants of health (SDoH) information to predict 6-month readmission or mortality after hospitalization among patients with HFpEF or HFrEF, and to evaluate the incremental contribution of SDoH, model explainability, and subgroup error disparities across demographic groups. Materials and Methods: We used University of Florida Health electronic health record (EHR) data (2016-2022) to identify adult heart failure (HF) hospitalizations and followed patients for 6 months for a composite outcome of readmission or mortality. Features included clinical characteristics, contextual SDoH (eg, neighborhood deprivation), and individual SDoH extracted from clinical notes via natural language processing (NLP). Logistic regression and XGBoost models were trained with random oversampling. Performance metrics included the C statistic, F1-score, and recall. Fairness was evaluated using false negative rate (FNR) parity across sex, race/ethnicity, and age band, and mitigation methods were applied (eg, Disparate Impact Remover, Adversarial Debiasing, and Calibrated Equalized Odds). Results: Adding SDoH improved the C statistic for logistic regression in HFpEF (0.603 vs 0.586) and HFrEF (0.641 vs 0.637). SHapley Additive exPlanations (SHAP) highlighted sodium, financial constraint level, and emergency department visit count in HFpEF, and utilization measures and financial constraint level in HFrEF. FNR ratios indicated race/ethnicity disparities; HFpEF FNRBlack/FNRWhite was 0.7834 (0.8728 after Disparate Impact Remover), and HFrEF FNRHispanic/FNRWhite was 1.2217 (0.9880 after Adversarial Debiasing). Discussion: SDoH integration and mitigation can modestly improve performance while reducing subgroup error disparities. Conclusion: Subtype-specific, fairness-aware ML models for HFpEF and HFrEF provided interpretable 6-month risk stratification and enabled subgroup fairness assessment. Integrating clinical and SDoH information added modest discrimination gains while strengthening interpretation and fairness assessment. These findings support further validation of explainable, equity-aware HF prediction models.
No takes yet. Share an insight, caveat, or question.
Yeh et al. (2026) conducted a cohort in Heart failure with preserved or reduced ejection fraction (HFpEF or HFrEF) (n=6,207). Integration of social determinants of health (SDoH) into clinical machine learning models vs. Clinical variables only models was evaluated on Composite of HF readmission or death within 6 months. Integrating social determinants of health into machine learning models modestly improved the C-statistic for predicting 6-month readmission or mortality in HFpEF and HFrEF.
Synapse has enriched 10 related papers. Consider them for comparative context: