Date of Award
Spring 2024
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Computer Science
First Advisor
Praveen Madiraju
Abstract
After the global spread of COVID-19, the enduring effects of Long COVID and its health implications have emerged as a significant global issue, affecting people worldwide. The lingering symptoms post a COVID-19 infection can significantly affect individuals who had previously contracted the virus, exerting considerable influence over their mental well-being. Prolonged recuperation associated with Long COVID has been connected with the emergence of symptoms such as depression and anxiety, all of which can have adverse effects on emotional health. This project delves into an in-depth analysis of healthcare data pertaining to Long COVID from the Froedtert Health (FH) Medical System in Wisconsin, United States. Through the application of advanced Machine Learning (ML) techniques, we present predictive models aimed at assessing the risk of developing Mental Health Disorders (MHD) in patients diagnosed with Long COVID. Our study also encompasses the identification of pivotal features impacting MHD. To thoroughly investigate the factors that have a substantial impact on MHD, we employed the Recursive Feature Elimination (RFE) technique to carefully pick out essential attributes from our dataset. Given the dataset's inherent imbalance, we have employed the Synthetic Minority Over-sampling Technique and Edited Nearest Neighbors (SMOTEEN) technique to effectively address this issue. Multiple ML models have been meticulously constructed and validated using cross-validation methodologies. The results indicate that Random Forest (RF) Classifier shows better performance in comparison to other models with an area under the ROC curve (AUC) of 0.97, precision of 0.90, and recall of 0.89. Remarkably, the XGBoost Classifier also demonstrates strong predictive abilities for MHD, achieving an AUC of 0.90, precision of 0.79, and recall of 0.82. Ultimately, the crucial features identified through our predictive models hold the potential to identify individuals at risk of MHD, facilitating the delivery of targeted preventive care and essential resources.