Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data

Aims: Patients visiting the emergency department (ED) or hospitalized for heart failure (HF) are at increased risk for subsequent adverse outcomes, however effective risk stratification remains challenging. We utilized a machine-learning (ML)-based approach to identify HF patients at risk of adverse outcomes after an ED visit or hospitalization using a large regional administrative healthcare data system. Methods and results: Patients visiting the ED or hospitalized with HF between 2002–2016 in Alberta, Canada were included. Outcomes of interest were 30-day and 1-year HF-related ED visits, HF hospital readmission or all-cause mortality. We applied a feature extraction method using deep feature synthesis from multiple sources of health data and compared performance of a gradient boosting algorithm (CatBoost) with logistic regression modelling. The area under receiver operating characteristic curve (AUC-ROC) was used to assess model performance. We included 50,630 patients with 93,552 HF ED visits/hospitalizations. At 30-day follow-up in the holdout validation cohort, the AUC-ROC for the combined endpoint of HF ED visit, HF hospital readmission or death for the Catboost and logistic regression models was 74.16 (73.18–75.11) versus 62.25 (61.25–63.18), respectively. At 1-year follow-up corresponding values were 76.80 (76.1–77.47) versus 69.52 (68.77–70.26), respectively. AUC-ROC values for the endpoint of all-cause death alone at 30-days and 1-year follow-up were 83.21 (81.83–84.41) versus 69.53 (67.98–71.18), and 85.73 (85.14–86.29) versus 69.40 (68.57–70.26), for the CatBoost and logistic regression models, respectively. Conclusions: ML-based modelling with deep feature synthesis provided superior risk stratification for HF patients at 30-days and 1-year follow-up after an ED visit or hospitalization using data from a large administrative regional healthcare system. Author summary: Patients visiting the emergency department (ED) or hospitalized for heart failure (HF) are at increased risk for subsequent adverse outcomes, however effective risk stratification remains challenging. Healthcare administrative or claims databases capture data on large, unselected cohorts of patients and can be used to monitor HF outcomes at a population-level. The primary objective of our study was to develop and validate a risk prediction ML model for 30-day and 1-year HF ED visits, hospital readmissions or death using administrative health data and evaluate its performance and potential utility from a large regional healthcare system. We used deep feature synthesis for automated feature engineering to pool patient information from multiple data sources and developed models using a gradient boosting-based ML algorithm (CatBoost). From a database that included over 50,000 HF patients, Catboost demonstrated superior prognostic utility and precision to both conventional logistic regression and other ML-based risk prediction modelling approaches for all study endpoints. This model may be of value to healthcare administrators for developing strategies to reduce adverse outcomes for hospitalized HF patients.