Key result
XGBoost model integrating social determinants of health improves 30-day readmission prediction over a clinical-only baseline.
Why the study?
Most readmission prediction models rely on clinical data, and the use of machine learning to combine clinical and social determinants of health data remains limited.
Does integrating clinical and Social Determinants of Health (SDOH) data into machine learning models improve the prediction of 30-day all-cause hospital readmission in discharged adult patients?
Cohort (n=3,018)
No
Does integrating clinical and Social Determinants of Health (SDOH) data into machine learning models improve the prediction of 30-day all-cause hospital readmission in discharged adult patients?
Integrating social determinants of health with clinical data in machine learning models significantly improves the prediction of 30-day hospital readmissions compared to clinical-only models.
Answers are grounded in this paper and cite their sources.
May improve readmission risk stratification via SDOH-ML; extends conventional models but leaves open prospective validation before adoption.
Background Hospital readmissions remain a major challenge for healthcare systems, contributing to higher costs and worse patient outcomes. Although most prediction models rely primarily on clinical data, integrating social determinants of health (SDOH) may improve risk assessment. However, the use of machine learning (ML) to combine clinical and SDOH data for readmission prediction remains limited. Objective To develop and compare machine learning models for predicting 30-day hospital readmission by integrating clinical and SDOH data. Methods We conducted a retrospective cohort study of 3,018 adult patients discharged from a large academic medical center between January 2022 and December 2023. Clinical variables were extracted from electronic health records and linked, through geocoded residential addresses, to area-level SDOH indicators from publicly available census data, including neighborhood deprivation, median income, and educational attainment. Six tabular ML models were trained and evaluated, including Logistic Regression, Random Forest, XGBoost, LightGBM, CatBoost, and Support Vector Machine. Model performance was assessed using the area under the receiver operating characteristic curve (ROC-AUC), precision-recall AUC (PR-AUC), and F1-score. SHapley Additive exPlanations (SHAP) were used to assess feature importance. Results Ensemble models outperformed Logistic Regression, with XGBoost achieving the best performance on the test set (ROC-AUC 0.79, 95% CI 0.75–0.82; PR-AUC 0.71). In addition to key clinical variables such as prior admissions and comorbidity burden, SDOH features including neighborhood socioeconomic status and household composition were among the most important predictors. Conclusion Integrating clinical and SDOH data into ML models improved prediction of 30-day hospital readmission. These findings support moving beyond clinical-only models and suggest that SDOH-informed prediction may help identify high-risk patients earlier and guide more targeted care management.
No takes yet. Share an insight, caveat, or question.
Tianyu Zhang (2026) conducted a cohort in Hospital readmission (n=3,018). XGBoost machine learning model integrating clinical and SDOH data vs. Clinical-only Logistic Regression baseline model was evaluated on 30-day all-cause unplanned hospital readmission (evaluated by ROC-AUC) (95% CI 0.75-0.82, p=<0.001). An XGBoost machine learning model integrating clinical and social determinants of health data improved 30-day hospital readmission prediction compared to a clinical-only baseline model.
Synapse has enriched 10 related papers. Consider them for comparative context: