Predicting Hospital Readmission Using Machine Learning

Makrani, Zainab Mohamed Ismail (2023) Predicting Hospital Readmission Using Machine Learning. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Rehospitalization is widespread among various patients and can be exhausting not just financially but also mentally due to the frequent hospital visits. The primary objective of this project is to incorporate machine learning techniques into healthcare, to create an affordable and efficient healthcare environment and structure. Simple machine learning techniques like random forest, xgboost, decision trees, linear regression and ordinary least squares regression are applied as well as neural networks. Random forest is best performing model with an accuracy of 82% and f1 score of 22 and r-squared of 0.04. When compared the dense neural network outperformed the rest with an accuracy of 82.88% and test loss of 0.5 while the rest were mostly overfitting to the model after training.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Basillio, Jorge UNSPECIFIED
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:	16 May 2025 10:32
Last Modified:	16 May 2025 10:32
URI:	https://norma.ncirl.ie/id/eprint/7563

Actions (login required)

View Item