Acute Kidney Injury: Predicting 30-Day Readmissions

Many models have been developed to predict hospital 30-day readmissions. In this study, AUTO-WEKA was utilized against datasets with differing class imbalances to identify potential algorithms for further exploration. The study identified two algorithms, KStar and IBk, along with attribute selection criteria with high levels of sensitivity, specificity, precision, and accuracy. The two algorithms were identified with datasets containing higher class imbalances. Lower class imbalance datasets were not able to produce algorithms with acceptable performance.