Cover Image

Survival versus non-survival prediction after acute coronary syndrome in Malaysian population using machine learning technique / Nanyonga Aziida

Prediction, identification, understanding and visualization of relationship between factors affecting mortality in ACS patients using feature selection and ML algorithms. Feature selection, classification and pattern recognition methods have been used in this research. From a group of 1480 patients...

Full description

Saved in:
Bibliographic Details
Main Author: Nanyonga , Aziida
Format: Thesis
Published: 2019
Subjects:
Q Science (General)
QH301 Biology
Online Access:http://studentsrepo.um.edu.my/12326/1/Nanyonga.pdf
http://studentsrepo.um.edu.my/12326/2/Nanyonga_Aziida.pdf
http://studentsrepo.um.edu.my/12326/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.stud.12326
record_format eprints
spelling my.um.stud.123262021-11-11T00:11:21Z Survival versus non-survival prediction after acute coronary syndrome in Malaysian population using machine learning technique / Nanyonga Aziida Nanyonga , Aziida Q Science (General) QH301 Biology Prediction, identification, understanding and visualization of relationship between factors affecting mortality in ACS patients using feature selection and ML algorithms. Feature selection, classification and pattern recognition methods have been used in this research. From a group of 1480 patients drawn from the Acute Coronary Syndrome Malaysian registry, 302 people satisfied the inclusion criteria, and 54 variables were duly considered. Combinations of feature selection and classification algorithms were used for mortality prediction post ACS. Self-Organizing Feature (SOM) was used to visualize and identify the relationship and pattern between factors affecting mortality after ACS. Prediction models' performance criteria was measured using area under the curve (AUC) ranged from 0.62 to 0.795. The best model (RF) executed using 5 predictors (Age, TG, creatinine, Troponin and TC). Most model’s performance plateaued using five predictors. The best performing model was compared with TIMI using an additional dataset that resulted in the ML model outperforming TIMI score (AUC 0.75 vs 0.60). Machine learning techniques for prediction and visualization of mortality related to ACS is presented in this study. The selected algorithms effectively show increase in prediction performance with decreasing features. Combination of ML prediction and visualization capabilities indicate effectiveness in predicting outcomes for clinical cardiology settings. 2019-08 Thesis NonPeerReviewed application/pdf http://studentsrepo.um.edu.my/12326/1/Nanyonga.pdf application/pdf http://studentsrepo.um.edu.my/12326/2/Nanyonga_Aziida.pdf Nanyonga , Aziida (2019) Survival versus non-survival prediction after acute coronary syndrome in Malaysian population using machine learning technique / Nanyonga Aziida. Masters thesis, Universiti Malaya. http://studentsrepo.um.edu.my/12326/
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Student Repository
url_provider http://studentsrepo.um.edu.my/
topic Q Science (General)
QH301 Biology
spellingShingle Q Science (General)
QH301 Biology
Nanyonga , Aziida
Survival versus non-survival prediction after acute coronary syndrome in Malaysian population using machine learning technique / Nanyonga Aziida
description Prediction, identification, understanding and visualization of relationship between factors affecting mortality in ACS patients using feature selection and ML algorithms. Feature selection, classification and pattern recognition methods have been used in this research. From a group of 1480 patients drawn from the Acute Coronary Syndrome Malaysian registry, 302 people satisfied the inclusion criteria, and 54 variables were duly considered. Combinations of feature selection and classification algorithms were used for mortality prediction post ACS. Self-Organizing Feature (SOM) was used to visualize and identify the relationship and pattern between factors affecting mortality after ACS. Prediction models' performance criteria was measured using area under the curve (AUC) ranged from 0.62 to 0.795. The best model (RF) executed using 5 predictors (Age, TG, creatinine, Troponin and TC). Most model’s performance plateaued using five predictors. The best performing model was compared with TIMI using an additional dataset that resulted in the ML model outperforming TIMI score (AUC 0.75 vs 0.60). Machine learning techniques for prediction and visualization of mortality related to ACS is presented in this study. The selected algorithms effectively show increase in prediction performance with decreasing features. Combination of ML prediction and visualization capabilities indicate effectiveness in predicting outcomes for clinical cardiology settings.
format Thesis
author Nanyonga , Aziida
author_facet Nanyonga , Aziida
author_sort Nanyonga , Aziida
title Survival versus non-survival prediction after acute coronary syndrome in Malaysian population using machine learning technique / Nanyonga Aziida
title_short Survival versus non-survival prediction after acute coronary syndrome in Malaysian population using machine learning technique / Nanyonga Aziida
title_full Survival versus non-survival prediction after acute coronary syndrome in Malaysian population using machine learning technique / Nanyonga Aziida
title_fullStr Survival versus non-survival prediction after acute coronary syndrome in Malaysian population using machine learning technique / Nanyonga Aziida
title_full_unstemmed Survival versus non-survival prediction after acute coronary syndrome in Malaysian population using machine learning technique / Nanyonga Aziida
title_sort survival versus non-survival prediction after acute coronary syndrome in malaysian population using machine learning technique / nanyonga aziida
publishDate 2019
url http://studentsrepo.um.edu.my/12326/1/Nanyonga.pdf
http://studentsrepo.um.edu.my/12326/2/Nanyonga_Aziida.pdf
http://studentsrepo.um.edu.my/12326/
_version_ 1738506596802101248
score 13.211869

Similar Items