Evaluation of machine learning algorithms for predicting readmission after acute myocardial infarction using routinely collected clinical data

Background — The ability to accurately predict readmission after acute myocardial infarction (AMI) hospitalization is limited in current statistical models. Machine learning (ML) methods have shown improved predictive ability in various clinical contexts, but their utility in predicting readmission after AMI hospitalization is unknown.

Methods — Using detailed clinical information collected from patients hospitalized with AMI, we evaluated six ML algorithms (logistic regression, naïve Bayes, support vector machines, random forest, gradient boosting, and deep neural networks) to predict readmission within 30-days and 1-year of discharge. A nested cross-validation approach was used to develop and test models. We used C-statistics to compare discriminatory capacity, while the Brier score was used to indicate overall model performance. Model calibration was assessed using calibration plots.

Results — The 30-day readmission rate was 16.3%, while the 1-year readmission rate was 45.1%. For 30-day readmission, the discriminative ability for the ML models was modest (c-statistic 0.641; 95% CI, 0.621-0.662 for gradient boosting) and did not outperform previously reported methods. For 1-year readmission, different ML models showed moderate performance, with c-statistics around 0.72. Despite modest discriminatory capabilities, the observed readmission rates were markedly higher in the tenth decile of predicted risk compared to in the first decile of predicted risk for both 30-day and 1-year readmission.

Conclusion — Despite including detailed clinical information and evaluating various ML methods, these models did not have better discriminatory ability to predict readmission outcomes compared to previously reported methods.