Predictive Analytics for Patient Discharge Using Electronic Health Records

Kekade, Shrey Sanjay (2024) Predictive Analytics for Patient Discharge Using Electronic Health Records. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (526kB) | Preview

Abstract

This study investigates the application of machine learning methods to predict patient discharge outcomes by using EHR data, focusing on two critical challenges in healthcare resource management and patient care continuity. The investigation involved a feature selection and model interpretability to balance predictive accuracy with practical usability in clinical environments. This systematic methodology, consisting of data preprocessing, hyperparameter tuning, and performance assessment using metrics such as F1-score and AUC-ROC, compared a total of five machine learning models: Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and Neural Network. Of these, the Random Forest model proved to be the most robust, high in accuracy, and easy to interpret using SHAP-based explanations. While the obtained results are promising, the limitation of a single dataset and real-world validation pose a need for improvement and future research. However, this work contributes to predictive analytics in healthcare by providing a replicable framework that integrates advanced machine learning with domain-specific insights. Future work will expand dataset diversity, implement real-time predictive pipelines, and validate models in clinical settings to enhance their utility and scalability.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hamill, David UNSPECIFIED
Uncontrolled Keywords:	Predictive Analytics; Patient Discharge; Machine Learning; Electronic Health Records (EHR); Healthcare Resource Management
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2025 16:10
Last Modified:	02 Sep 2025 16:10
URI:	https://norma.ncirl.ie/id/eprint/8726

Actions (login required)

View Item