COV-HM: Prediction of COVID-19 Patient's Hospitalization Period for Hospital Management Using SMOTE and Machine Learning Techniques

ABSTRACT

COVID-19 imposes burdens on hospitals. Evidence-based management and optimum resource allocation are essential. Understanding the time frame of support needs for COVID-19 patients staying in hospitals is vital for planning hospital resource allocation, especially in resource-constrained settings. Machine learning methods are being utilized in the approximation of the length of stay of a patient in the hospital. Four machine learning classifiers were used in this study to estimate the duration of hospitalization for patients in 11 different classes. Due to the dataset's imbalance, SMOTE was applied to eliminate the problem. The prediction accuracy of the K-Nearest Neighbors, Random Forest, Decision Tree, and Gradient Boosting classifiers was 73%, 69%, 58%, and 57%. The feature importance scores assist in the identification of vital features while building machine learning models. This research will assist responsible authorities in maintaining hospital services depending on the length of a patient's stay. © 2022 ACM.