A Machine Learning-Based Predictive Model for 30-Day Hospital Readmission Prediction for COPD Patients

Machine learning (ML) based prediction models proved to be fast, accurate, and free from human errors with capabilities to address pressing problems in healthcare. Being progressive in nature, Chronic Obstructive Pulmonary Disease (COPD) patients require frequent hospital readmission. Frequent hospital readmission, may be preventable, is a patient-centric approach which result in expensive health services and poor utilization of overly-burdened medical resources in recent times. In this research study, we envisaged a ML-based model to predict hospital readmission in 30-day by analyzing daily physical activity (PA) data with an accelerometer-based wrist-worn device. Prediction models based on logistic regression, lasso regularization, and MLP deep neural network have been used for training and testing PA data. For analysis, 70% of PA data used for training and 30% for testing and predicting readmission. Readmission predicted with sensitivity 0.88, positive predictive value 0.75, false positive 0.25 and area under ROC curve 0.50. The novelty our approach is to predict hospital readmission by monitoring health condition with accelerometer-based wrist-worn device which generate PA data electronic in nature, can be readily employed with various e-healthcare services. Therefore, we propose to develop a cloud-based system, coordinated aligned with local-health services and e-healthcare, to provide better patient care system and alarming notifications; and to reduce preventable hospital readmission to cut medical expenses and conserve medical resources for better patient care and readily available medical services for all.