An Approach to Supervised Classification of Highly Imbalanced and High Dimensionality COPD Readmission Data on HPCC

摘要

Hospital readmission within a 30-day period causes severe economic and healthcare impacts. According to a study, 76% of the hospitals readmissions can be prevented by providing out of hospital post-discharge care. In order to appropriately mark the patients with high chances of getting readmitted, numerous studies and researches have been performed which uses various supervised machine learning algorithms to predict the readmission probability of a patient using labeled discharge summaries and clinical notes. The datasets used in these studies are highly imbalanced and has high dimensionality, which affects classification performance negatively. This study uses data sampling technique to reduce the imbalance and feature selection technique to reduce high dimensionality, thereby improving the overall classification performance and reducing the evaluation time as compared to other industry standard hospital readmission frameworks reviewed in this study.