Is artificial intelligence better than manual methods in diagnosis of electrocardiograms (ECGs) or not?

Vishal Desai, Dinesh Dave


Background: Now artificial intelligence is used extensively to diagnose ECGs. Artificial intelligence is the point where the doctors and engineers meet to decrease the misdiagnosis of cardiac diseases. So, we thought it worthwhile to compare and contrast the ECG diagnosis by artificial intelligence and skilled physicians. This paper exposes the potential of diagnosis of each ECG by artificial intelligence and skilled physicians.

Methods: The research was done on 30 ECGs and their diagnosis was compared by both the methods.

Results: The result was divided into 3 categories: absolutely misdiagnosed, relatively misdiagnosed and correctly diagnosed. Out of these 33% ECGs are absolutely misdiagnosed, 44% ECGs are relatively misdiagnosed and 23% ECGs are correctly diagnosed. This research also focuses on those numbers of diseases which were not correctly diagnosed by artificial intelligence. Out of 23 ECGs 21% cases were of ischaemic heart disease, 26% cases were of early repolarisation syndrome and 17% cases were of atrial flutter/fibrillation (af).

Conclusions: Our study concludes that artificial intelligence needs human intervention as well. A combination of human brain and artificial intelligence has made wonders; thus, diagnosis and treatment planning can be enhanced.


Artificial intelligence, Cardiac diseases, Electrocardiograms, Skilled physicians

Full Text:



Luger GF. Artificial intelligence: structures and strategies for complex problem solving: Pearson Education India, 1998.

Genesereth MR, Nilsson NJ. Logical foundations of artificial. Intelligence Morgan Kaufmann 1987;2.

Ofri D. What doctors feel: how emotions affect the practice of medicine: Beacon Press, 2013. Available at

Carbonell JR. AI in CAI: an artificial-intelligence approach to computer-assisted instruction. IEEE Transactions Man-machine Systems. 1970;11(4):190-202.

Kulikowski CA. Artificial intelligence methods and systems for medical consultation. IEEE Transactions Pattern Analysis Machine Intelligence. 1980:464-76.

Malviya A, Gupta N, Sharma N. Overview a quality-scalable and energy-efficient approach for spectral analysis of heart rate variability. Int J Computer Applications. 2015;129:7-10.

Gustafson D, Bosworth K, Chewning B, Hawkins R: Computer-based health promotion: Combining technological advances with problem-solving techniques to effect successful health behavior changes. Annual Review Public Health. 1987;8:387-415.

National Academies of Sciences E, Medicine: Improving diagnosis in health care: National Academies Press, 2016.