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

Michael Green

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

Michael Green

Research output: Thesis › Doctoral Thesis (compilation)

150 Downloads (Pure)

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.

Original language	English
Qualification	Doctor
Awarding Institution
Supervisors/Advisors	Ohlsson, Mattias, Supervisor Edenbrandt, Lars, Supervisor
Award date	2008 Jun 18
ISBN (Print)	978-91-628-7434-6
Publication status	Published - 2008

Bibliographical note

Defence details

Date: 2008-06-18
Time: 10:15
Place: Lecture hall F, Department of Theoretical Physics, Sölvegatan 14A, SE-223 62 Lund, Sweden

External reviewer(s)

Name: Lisboa, Paulo
Title: Professor
Affiliation: Liverpool John Moores University, Liverpool, England

---

Subject classification (UKÄ)

Biophysics

Free keywords

ensemble
artificial neural network
machine learning
acute coronary syndrome
electrocardiogram
case based explanation
decision support system

Access to Document

Michael_Green_Thesis

4 Article
2 Paper in conference proceeding

Exploring new possibilities for case based explanation of artificial neural network ensembles
Green, M., Ekelund, U., Edenbrandt, L., Björk, J., Lundager Hansen, J. & Ohlsson, M., 2009, In: Neural Networks. 22, 1, p. 75-81
Research output: Contribution to journal › Article › peer-review
In search of the best method to predict acute coronary syndrome using only the electrocardiogram from the emergency department.
Forberg, J. L., Green, M., Björk, J., Ohlsson, M., Edenbrandt, L., Öhlin, H. & Ekelund, U., 2009, In: Journal of Electrocardiology. 42, 1, p. 58-63 6 p.
Research output: Contribution to journal › Article › peer-review
Explaining artificial neural network ensembles: A case study with electrocardiograms from chest pain patients
Green, M., Ekelund, U., Edenbrandt, L., Björk, J., Lundager Hansen, J. & Ohlsson, M., 2008, Proceedings of the ICML/UAI/COLT 2008 Workshop on Machine Learning for Health-Care Applications. Hauskrecht, M. (ed.). 8 p.
Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

File

Cite this

@phdthesis{4415dd7b68c74464a2a21a7797300988,

title = "Improving diagnosis of acute coronary syndromes in an emergency setting: A machine learning approach",

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.",

keywords = "ensemble, artificial neural network, machine learning, acute coronary syndrome, electrocardiogram, case based explanation, decision support system",

author = "Michael Green",

note = "Defence details Date: 2008-06-18 Time: 10:15 Place: Lecture hall F, Department of Theoretical Physics, S{\"o}lvegatan 14A, SE-223 62 Lund, Sweden External reviewer(s) Name: Lisboa, Paulo Title: Professor Affiliation: Liverpool John Moores University, Liverpool, England ---",

year = "2008",

language = "English",

isbn = "978-91-628-7434-6",

type = "Doctoral Thesis (compilation)",

}

TY - THES

T1 - Improving diagnosis of acute coronary syndromes in an emergency setting: A machine learning approach

AU - Green, Michael

N1 - Defence details Date: 2008-06-18 Time: 10:15 Place: Lecture hall F, Department of Theoretical Physics, Sölvegatan 14A, SE-223 62 Lund, Sweden External reviewer(s) Name: Lisboa, Paulo Title: Professor Affiliation: Liverpool John Moores University, Liverpool, England ---

PY - 2008

Y1 - 2008

N2 - 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.

AB - 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.

KW - ensemble

KW - artificial neural network

KW - machine learning

KW - acute coronary syndrome

KW - electrocardiogram

KW - case based explanation

KW - decision support system

M3 - Doctoral Thesis (compilation)

SN - 978-91-628-7434-6

ER -

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

Abstract

Bibliographical note

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Research output

Exploring new possibilities for case based explanation of artificial neural network ensembles

In search of the best method to predict acute coronary syndrome using only the electrocardiogram from the emergency department.

Explaining artificial neural network ensembles: A case study with electrocardiograms from chest pain patients

Cite this