The author of this document has limited its availability to on-campus or logged-in CSUSB users only.

Off-campus CSUSB users: To download restricted items, please log in to our proxy server with your MyCoyote username and password.

Date of Award


Document Type

Restricted Project: Campus only access

Degree Name

Master of Science in Computer Science


School of Computer Science and Engineering

First Reader/Committee Chair

Muheidat, Fadi


Emergency rooms in hospitals are usually affected by long wait times and inefficient allocation of resources [1]. In this study, we will be exploring the machine learning potential for improving the patient flow and allocation of resources in emergency rooms that are affected by overcrowding. We developed and evaluated three machine learning models: Naïve Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF) to predict hospital admission for patients in the emergency room. All three models are trained on a dataset of 1267 patient records with features like age, gender, and vitals like heart rate, body temperature, blood pressure, and other clinical features. By leveraging machine learning, the support vector machine achieved the highest accuracy of 80.3%, random forest by 75.9%, and multinomial naive bayes by 74.4%. Through exploratory data analysis, we got to know the important features that are helping the models predict better. With the help of this model, it will be beneficial to both hospitals and patients. Patients experiencing pain or injury can receive faster treatment, potentially reducing complications. Hospitals can efficiently allocate resources to high-risk patients and potentially alleviate overcrowding, ultimately leading to better quality care overall.