An Expert System for Differential Diagnosis of Myocardial Infarction

Abdul Jaleel, Reza Tafreshi, Leyla Tafreshi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Automated early detection of myocardial infarction (MI) has been long studied for the purpose of saving human lives. In this paper, we propose a rule-based expert system to analyze a 12-lead electrocardiogram (ECG) for various types of MI. This system is developed by mapping clinical definitions of different types of MI and their differential diagnosis into corresponding algorithmic rule sets. Essential preprocessing steps such as baseline correction, removal of ectopic beats, and median filtering are carried out on recorded ECG. Techniques such as multistage polynomial correction and QRS subtraction are exploited to achieve reliable preprocessing. The processed ECG is then delineated using a time-domain differential-based search algorithm recently proposed by the team to obtain the relevant features and measures. These features and measures are further utilized by an if-then rule set to classify the ECG into various groups. The performance of the system when validated on sample MI database exhibited a sensitivity of 95.7% and specificity of 94.6%. Unlike many previous works, this reliable performance is achieved without the use of abstract classifiers or the need of prior training. Being based on medical definitions, the system is also easily comprehensible, modifiable, and compatible with manual diagnosis.

Original languageEnglish
Article number111012
JournalJournal of Dynamic Systems, Measurement and Control, Transactions of the ASME
Volume138
Issue number11
DOIs
Publication statusPublished - 1 Nov 2016

Fingerprint

myocardial infarction
electrocardiography
expert systems
Electrocardiography
Expert systems
preprocessing
classifiers
subtraction
synchronism
polynomials
Classifiers
education
Lead
Polynomials
sensitivity

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Information Systems
  • Instrumentation
  • Mechanical Engineering
  • Computer Science Applications

Cite this

An Expert System for Differential Diagnosis of Myocardial Infarction. / Jaleel, Abdul; Tafreshi, Reza; Tafreshi, Leyla.

In: Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME, Vol. 138, No. 11, 111012, 01.11.2016.

Research output: Contribution to journalArticle

@article{9b9a8772420e40058134915592f2de0d,
title = "An Expert System for Differential Diagnosis of Myocardial Infarction",
abstract = "Automated early detection of myocardial infarction (MI) has been long studied for the purpose of saving human lives. In this paper, we propose a rule-based expert system to analyze a 12-lead electrocardiogram (ECG) for various types of MI. This system is developed by mapping clinical definitions of different types of MI and their differential diagnosis into corresponding algorithmic rule sets. Essential preprocessing steps such as baseline correction, removal of ectopic beats, and median filtering are carried out on recorded ECG. Techniques such as multistage polynomial correction and QRS subtraction are exploited to achieve reliable preprocessing. The processed ECG is then delineated using a time-domain differential-based search algorithm recently proposed by the team to obtain the relevant features and measures. These features and measures are further utilized by an if-then rule set to classify the ECG into various groups. The performance of the system when validated on sample MI database exhibited a sensitivity of 95.7{\%} and specificity of 94.6{\%}. Unlike many previous works, this reliable performance is achieved without the use of abstract classifiers or the need of prior training. Being based on medical definitions, the system is also easily comprehensible, modifiable, and compatible with manual diagnosis.",
author = "Abdul Jaleel and Reza Tafreshi and Leyla Tafreshi",
year = "2016",
month = "11",
day = "1",
doi = "10.1115/1.4033838",
language = "English",
volume = "138",
journal = "Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME",
issn = "0022-0434",
publisher = "American Society of Mechanical Engineers(ASME)",
number = "11",

}

TY - JOUR

T1 - An Expert System for Differential Diagnosis of Myocardial Infarction

AU - Jaleel, Abdul

AU - Tafreshi, Reza

AU - Tafreshi, Leyla

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Automated early detection of myocardial infarction (MI) has been long studied for the purpose of saving human lives. In this paper, we propose a rule-based expert system to analyze a 12-lead electrocardiogram (ECG) for various types of MI. This system is developed by mapping clinical definitions of different types of MI and their differential diagnosis into corresponding algorithmic rule sets. Essential preprocessing steps such as baseline correction, removal of ectopic beats, and median filtering are carried out on recorded ECG. Techniques such as multistage polynomial correction and QRS subtraction are exploited to achieve reliable preprocessing. The processed ECG is then delineated using a time-domain differential-based search algorithm recently proposed by the team to obtain the relevant features and measures. These features and measures are further utilized by an if-then rule set to classify the ECG into various groups. The performance of the system when validated on sample MI database exhibited a sensitivity of 95.7% and specificity of 94.6%. Unlike many previous works, this reliable performance is achieved without the use of abstract classifiers or the need of prior training. Being based on medical definitions, the system is also easily comprehensible, modifiable, and compatible with manual diagnosis.

AB - Automated early detection of myocardial infarction (MI) has been long studied for the purpose of saving human lives. In this paper, we propose a rule-based expert system to analyze a 12-lead electrocardiogram (ECG) for various types of MI. This system is developed by mapping clinical definitions of different types of MI and their differential diagnosis into corresponding algorithmic rule sets. Essential preprocessing steps such as baseline correction, removal of ectopic beats, and median filtering are carried out on recorded ECG. Techniques such as multistage polynomial correction and QRS subtraction are exploited to achieve reliable preprocessing. The processed ECG is then delineated using a time-domain differential-based search algorithm recently proposed by the team to obtain the relevant features and measures. These features and measures are further utilized by an if-then rule set to classify the ECG into various groups. The performance of the system when validated on sample MI database exhibited a sensitivity of 95.7% and specificity of 94.6%. Unlike many previous works, this reliable performance is achieved without the use of abstract classifiers or the need of prior training. Being based on medical definitions, the system is also easily comprehensible, modifiable, and compatible with manual diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=84981539653&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84981539653&partnerID=8YFLogxK

U2 - 10.1115/1.4033838

DO - 10.1115/1.4033838

M3 - Article

VL - 138

JO - Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME

JF - Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME

SN - 0022-0434

IS - 11

M1 - 111012

ER -