Sepsis Prediction using Machine Learning and Deep Learning Algorithms

Thomas, Terrance (2020) Sepsis Prediction using Machine Learning and Deep Learning Algorithms. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (939kB) | Preview

Abstract

This paper aims at presenting a method and comparing various machine learning (ML) and deep learning (DL) algorithms for predicting sepsis from clinical time-series data. Sepsis is among the most threatening condition that could occur during intensive care unit (ICU) treatment of a patient. Therefore, in this research, multiple models is applied to the data after they are cleaned and pre-processed to get the best results. In the research DL method such as long short-term memory (LSTM) and ML method such as decision tree (DT), random forest (RF), adaptive boosting (AdaBoost), k-nearest neighbours (KNN) and extreme gradient boosting (XGB) to the data set which is taken from 2 hospitals via an online challenge and has hourly data of over 40,000 patients. Data are processed in two separate ways and the best performing was used to apply all the models. Of which XGB performs the best with 0.98 of accuracy, 0.96 recall score, 0.98 f1 score, and 0.99 precision followed by RF as the second-best model.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software R Medicine > R Medicine (General)
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	22 Jan 2021 10:14
Last Modified:	22 Jan 2021 10:14
URI:	https://norma.ncirl.ie/id/eprint/4429

Actions (login required)

View Item