Machine Learning-based Risk of Hospital Readmissions Predicting Acute Readmissions within 30 Days of Discharge

The objective of this study was to design and develop a 30-day risk of hospital readmission predictive model using machine learning techniques. The proposed risk of readmission predictive model was then validated with the two most commonly used risk of readmission models - LACE index and patient at-risk of hospital readmission (PARR). The study cohort consisted Data set of actual readmissions within 30-day of hospital discharge. We developed a machine learning model to predict 30-day readmissions using the model types: XGBoost, Random Forests and Adaboost with decision stumps as a base learner with different feature combinations and preprocessing procedures. The proposed model achieved the better F1-score, sensitivity, positive predictive value (PPV) and negative predictive value (NPV). When compared with LACE and PARR (NZ) models, the proposed model achieved better F1-score by compared to LACE and   to PARR (NZ). The mean sensitivity of the proposed model was higher than LACE and higher than PARR (NZ). The mean PPV was higher than LACE and PARR (NZ).

Keywords: Risk of readmission; machine learning model; LACE; PARR and Patient at risk of hospital readmission.