Document Type

Thesis

Degree

Master of Science

Major

Computer Science

Date of Defense

4-22-2024

Graduate Advisor

Badri Adhikari

Committee

Badri Adhikari

Azim Ahmadzadeh

Reda M. Amer

Abstract

Understanding the factors that contribute to the risk of hospitalization among individuals with schizophrenia is crucial for optimizing treatment strategies and improving patient outcomes. In this study, we used recent Medicaid adminis trative claims data in Missouri (from 2016 to 2019) and predicted the risk of hospitalization of patients diagnosed with Schizophrenia (N=143446). We ana lyzed the association between previous hospitalizations and the likelihood of future hospitalizations. We developed machine learning techniques, including logistic re gression and decision tree classifiers, to predict the risk of hospitalization based on demographic factors, clinical variables, and historical hospitalization records. Our findings reveal that the significant predictors of hospitalization risk are the frequency and duration of previous hospitalizations and socio-demographic fac tors. The results of this study have important implications for clinical practice and healthcare policy, highlighting the need for personalized interventions and targeted support services to mitigate the risk of hospitalization among individu als with schizophrenia. By leveraging predictive modeling techniques, healthcare providers can identify high-risk patients early and implement preventive measures to reduce the burden of hospitalizations and improve long-term outcomes.

Download

Share

COinS