AI Insight
Researchers used machine learning to predict which heart failure patients would be readmitted to the hospital within 30 days, drawing on data from the Kansas Health Information Network, a statewide health information exchange covering 2,734 patients. Among five models tested, XGBoost performed best with an AUROC of 0.75, and patients identified as highest risk accounted for roughly one-third of all 30-day readmissions with a positive predictive value of 76%. The most informative predictors were prior hospital utilization, comorbidity burden, and management indicators for diabetes and kidney disease.
Why it matters
Identifying high-risk heart failure patients before discharge could allow clinicians to prioritize transitional care resources more efficiently, potentially reducing costly and harmful readmissions. The use of routinely collected clinical data from a health information exchange suggests the approach could be feasible to implement in real-world healthcare settings.
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Background: Heart failure (HF) is a major contributor to inpatient hospital utilization, with persistently high 30-day readmission rates. Existing prediction tools are frequently restricted to primary-diagnosis HF admissions, potentially excluding clinically relevant HF-related hospitalizations. Objectives: To develop and validate risk prediction models using machine learning (ML)-based risk prediction models to predict 30-day readmissions among patients with HF using the Kansas Health Information Network, a statewide health information exchange. Methods: This retrospective cohort study analyzed HF hospitalizations using predictors including demographics, comorbidities, laboratory results, medications, clinical quality metrics for diabetes and kidney disease management, and prior healthcare utilization. Five ML models, including regularized logistic regression, random forest, extreme gradient boosting, categorical boosting, and deep neural network, were trained using stratified 5-fold cross-validation. Model performance was evaluated on an independent test set using the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), misclassification rate (MCR), and Brier score. Results: Among 2,734 HF patients, the 30-day readmission rate was 27%. The XGBoost model achieved the best discrimination (AUROC=0.75; AUPRC=0.58; MCR=0.21). Patients in the highest-risk decile had a positive predictive value of 76%, accounted for approximately one-third of all 30-day readmissions, and had a 3.3-fold enrichment compared with baseline risk. The key predictors included prior hospital utilization, diabetes and kidney disease management indicators, and comorbidity burden. Conclusions: Risk stratification using routinely collected clinical data identified a subgroup at elevated risk for 30-day readmission. These findings support the potential role of data-driven risk prediction to inform targeted transitional care.