Advanced

Improving diagnosis of acute coronary syndromes in an emergency setting: A machine learning approach

Green, Michael LU (2008)
Abstract (Swedish)
Popular Abstract in Swedish

Akut koronart syndrom (AKS) är den största folkdödaren i väst idag. Trots välutbildade läkare och bra diagnostiska verktyg så är det forfarande svårt att ställa en diagnos tidigt på sjukhusens akutavdelningar. I den här avhandlingen undersöker vi möjligheter att i ett tidigt skede förutsäga AKS med hjälp av maskininlärning. Främst användes logistiska regressionsmodeller och kommitteer av artificiella neurala nätverk (ANN). Jämförelser med expertläkare genomfördes kontinuerligt som en kvalitetskontroll. Vi utvecklade även praktiska patientbaserade förklaringsmodeller för ett ANNs beslutsprocess.
Abstract
Acute coronary syndrome (ACS) is the biggest people killer in the western world today. Despite well trained physicians and reliable diagnostic tools, diagnosing ACS early in the emergency departments (ED) remains a challenge. In this thesis we used machine learning, via logistic regression models and artificial neural network ensembles, to investigate the possibility of predicting ACS at an early stage using electrocardiogram data. Thorough comparisons were made to several expert physicians, currently working in the ED, to verify the models. In the context of neural networks we developed methods for the case based explanation of their decisions.
Please use this url to cite or link to this publication:
author
supervisor
opponent
  • Professor Lisboa, Paulo, Liverpool John Moores University, Liverpool, England
organization
publishing date
type
Thesis
publication status
published
subject
keywords
ensemble, artificial neural network, machine learning, acute coronary syndrome, electrocardiogram, case based explanation, decision support system
pages
147 pages
defense location
Lecture hall F, Department of Theoretical Physics, Sölvegatan 14A, SE-223 62 Lund, Sweden
defense date
2008-06-18 10:15
ISBN
978-91-628-7434-6
language
English
LU publication?
yes
id
4415dd7b-68c7-4464-a2a2-1a7797300988 (old id 1151299)
date added to LUP
2008-05-23 11:30:46
date last changed
2016-09-19 08:45:19
@phdthesis{4415dd7b-68c7-4464-a2a2-1a7797300988,
  abstract     = {Acute coronary syndrome (ACS) is the biggest people killer in the western world today. Despite well trained physicians and reliable diagnostic tools, diagnosing ACS early in the emergency departments (ED) remains a challenge. In this thesis we used machine learning, via logistic regression models and artificial neural network ensembles, to investigate the possibility of predicting ACS at an early stage using electrocardiogram data. Thorough comparisons were made to several expert physicians, currently working in the ED, to verify the models. In the context of neural networks we developed methods for the case based explanation of their decisions.},
  author       = {Green, Michael},
  isbn         = {978-91-628-7434-6},
  keyword      = {ensemble,artificial neural network,machine learning,acute coronary syndrome,electrocardiogram,case based explanation,decision support system},
  language     = {eng},
  pages        = {147},
  school       = {Lund University},
  title        = {Improving diagnosis of acute coronary syndromes in an emergency setting: A machine learning approach},
  year         = {2008},
}