0
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.

FIGURES IN THIS ARTICLE
<>
Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.

References

Mathers, C. D. , Boerma, T. , and Ma Fat, D. , 2009, “ Global and Regional Causes of Death,” Br. Med. Bull., 92(1), pp. 7–32. [CrossRef] [PubMed]
Kannel, W. B. , 1986, “ Silent Myocardial Ischemia and Infarction: Insights From the Framingham Study,” Cardiol. Clin., 4(4), pp. 583–591. [PubMed]
Haraldsson, H. , Edenbrandt, L. , and Ohlsson, M. , 2004, “ Detecting Acute Myocardial Infarction in the 12-Lead ECG Using Hermite Expansions and Neural Networks,” Artif. Intell. Med., 32(2), pp. 127–136. [CrossRef] [PubMed]
Mitra, S. , Mitra, M. , and Chaudhuri, B. B. , 2006, “ A Rough-Set-Based Inference Engine for ECG Classification,” IEEE Trans. Instrum. Meas., 55(6), pp. 2198–2206. [CrossRef]
Sun, L. , Lu, Y. , Yang, K. , and Li, S. , 2012, “ ECG Analysis Using Multiple Instance Learning for Myocardial Infarction Detection,” IEEE Trans. Biomed. Eng., 59(12), pp. 3348–3356. [CrossRef] [PubMed]
Maharaj, E. A. , and Alonso, A. M. , 2014, “ Discriminant Analysis of Multivariate Time Series: Application to Diagnosis Based on ECG Signals,” Comput. Stat. Data Anal., 70, pp. 67–87. [CrossRef]
Thygesen, K. , Alpert, J. S. , Jaffe, A. S. , Simoons, M. L. , Chatiman, B. R. , and White, H. D. , 2012, “ Third Universal Definition of Myocardial Infarction,” Circulation, 126(16), pp. 2020–2035. [CrossRef] [PubMed]
Dubin, D. , 2000, Rapid Interpretation of EKG's: An Interactive Course, Cover Publishing Company, Tampa, FL.
Wang, K. , Asinger, R. W. , and Marriott, H. J. , 2003, “ ST-Segment Elevation in Conditions Other Than Acute Myocardial Infarction,” N. Engl. J. Med., 349(22), pp. 2128–2135. [CrossRef] [PubMed]
Derval, N. , Shah, A. , and Jaïs, P. , 2011, “ Definition of Early Repolarization: A Tug of War,” Circulation, 124(20), pp. 2185–2186. [CrossRef] [PubMed]
Sovari, A. A. , Assadi, R. , Lakshminarayanan, B. , and Kocheril, A. G. , 2007, “ Hyperacute T Wave: The Early Sign of Myocardial Infarction,” Am. J. Emerg. Med., 25(7), pp. 859-e1–859-e7.
Wienbergen, H. , Gitt, A. K. , Schiele, R. , Juenger, C. , Heer, T. , Vogel, C. , Gottwik, M. , and Senges, J. , 2004, “ Different Treatments and Outcomes of Consecutive Patients With Non-ST-Elevation Myocardial Infarction Depending on Initial Electrocardiographic Changes (Results of the Acute Coronary Syndromes [ACOS] Registry),” Am. J. Cardiol., 93(12), pp. 1543–1546. [CrossRef] [PubMed]
Tafreshi, R. , Jaleel, A. , Lim, J. , and Tafreshi, L. , 2014, “ Automated Analysis of ECG Waveforms With Atypical QRS Complex Morphologies,” Biomed. Signal Process. Control, 10, pp. 41–49. [CrossRef]
Pandit, S. V. , 1996, “ ECG Baseline Drift Removal Through STFT,” 18th Annual International Conference of the IEEE in Engineering in Medicine and Biology Society, Amsterdam, The Netherlands, Oct. 31–Nov. 3, Vol. 4, pp. 1405–1406.
Chouhan, V. S. , and Mehta, S. S. , 2007, “ Total Removal of Baseline Drift From ECG Signal,” International Conference on Computing: Theory and Applications (ICCTA'07), Kolkata, India, Mar. 5–7, pp. 512–515.
Plesnik, E. , Malgina, O. , Tasic, J. F. , and Zajc, M. , 2012, “ ECG Baseline Drift Correction Through Phase Space for Simple R-Point Detection,” 25th International Symposium on Computer-Based Medical Systems (CBMS), Rome, Italy, June 20–22.
Manriquez, A. I. , and Zhang, Q. , 2007, “ An Algorithm for QRS Onset and Offset Detection in Single Lead Electrocardiogram Records,” 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, Lyon, France, Aug. 22–26, pp. 541–544.
Jaleel, A. , Tafreshi, R. , Mohsin, N. , and Tafreshi, L. , 2012, “ A Comprehensive Algorithm for the Analysis of ECG Waveforms,” ASME Paper No. IMECE2012-87553.
Shah, D. , Yamane, T. , Choi, K. J. , and Haissaguerre, M. , 2004, “ QRS Subtraction and the ECG Analysis of Atrial Ectopics,” Ann. Noninvasive Electrocardiol., 9(4), pp. 389–398. [CrossRef] [PubMed]
Salinet, J. L., Jr. , Madeiro, J. P. V. , Cortez, P. C. , Stafford, P. J. , Ng, G. A. , and Schlindwein, F. S. , 2013, “ Analysis of QRS-T Subtraction in Unipolar Atrial Fibrillation Electrograms,” Med. Biol. Eng. Comput., 51(12), pp. 1381–1391. [CrossRef] [PubMed]
Afonso, V. X. , Tompkins, W. J. , Nguyen, T. Q. , Michler, K. , and Luo, S. , 1996, “ Comparing Stress ECG Enhancement Algorithms,” IEEE Eng. Med. Biol. Mag., 15(3), pp. 37–44. [CrossRef]
Brownfield, J. , and Herbert, M. , 2008, “ ECG Criteria for Fibrinolysis: What's Up With the J Point?” West. J. Emerg. Med., 9(1), pp. 40–42. [PubMed]
Sgarbossa, E. B. , Pinski, S. L. , Barbagelata, A. , Underwood, D. A. , Gates, K. B. , Topol, E. J. , Califf, R. M. , and Wagner, G. S. , 1996, “ Electrocardiographic Diagnosis of Evolving Acute Myocardial Infarction in the Presence of Left Bundle-Branch Block,” N. Engl. J. Med., 334(8), pp. 481–487. [CrossRef] [PubMed]
Bousseljot, R. , Kreiseler, D. , and Schnabel, A. , 1995, “ Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet,” Biomed. Tech., 40(s1), pp. 317–318.
Banerjee, S. , and Mitra, M. , 2010, “ ECG Feature Extraction and Classification of Anteroseptal Myocardial Infarction and Normal Subjects Using Discrete Wavelet Transform,” International Conference on Systems in Medicine and Biology (ICSMB), Kharagpur, India, Dec. 16–18, pp. 55–60.

Figures

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. 1

Baseline correction of ECG through two-stage polynomial correction

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

Tables

Errata

Discussions

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