Research Papers

An Expert System for Differential Diagnosis of Myocardial Infarction

[+] Author and Article Information
Abdul Jaleel

Mechanical Engineering,
Texas A&M University,
P.O. Box 23874,
Education City,
Doha, Qatar
e-mail: ajaleelp@gmail.com

Reza Tafreshi

Associate Professor
Mechanical Engineering,
Texas A&M University,
P.O. Box 23874,
Education City,
Doha, Qatar
e-mail: reza.tafreshi@qatar.tamu.edu

Leyla Tafreshi

Lehigh Valley Health Network,
Allentown, PA 18105
e-mail: ltafreshi@gmail.com

Contributed by the Dynamic Systems Division of ASME for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received December 7, 2015; final manuscript received May 2, 2016; published online August 9, 2016. Assoc. Editor: Hashem Ashrafiuon.

J. Dyn. Sys., Meas., Control 138(11), 111012 (Aug 09, 2016) (8 pages) Paper No: DS-15-1621; doi: 10.1115/1.4033838 History: Received December 07, 2015; Revised May 02, 2016

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.

Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Fig. 1

Baseline correction of ECG through two-stage polynomial correction

Grahic Jump Location
Fig. 2

Detection of ectopic beats through QRS subtraction. The detections correspond to the ectopic beat at 13 s. Two redundant detections are seen as the beat changes from normal to ectopic and back to normal.

Grahic Jump Location
Fig. 3

(a) Original ECG recording within the selected window and (b) the composite beat (the middle beat, in red) obtained from the medians of the original beats (first and third beats, in blue)

Grahic Jump Location
Fig. 4

A sample ECG beat annotated with detections from the delineation algorithm

Grahic Jump Location
Fig. 5

The overall flowchart of the rule-based MI detection system

Grahic Jump Location
Fig. 6

A noisy ECG lead identified to be clinically indecisive




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In