A COMPARATIVE STUDY FOR EVALUATING THE FREQUENCY OF FALSE-POSITIVE DETECTION IN ELECTROCARDIOGRAM DEVICES IN COMPARISON TO CARDIOLOGIST DIAGNOSIS

Abstract

Electrocardiography is the most convenient and cost-effective method at the primary level of 
healthcare infrastructure to localize and diagnose Myocardial infarction, ischemic heart diseases, 
and numerous arrhythmias. The manufacturers of ECG machines provide computer-generated 
Interpretations. However, these machines have differences in implementing the algorithms, 
which cause the change in the diagnostic accuracy. Hence, the occurrence of False positives is 
the most commonly observed error that occurs during computer interpretation. This study aims to 
evaluate the differences observed in the computerized interpretation of ECG reports regarding 
the Cardiologist's diagnosis. The 12 lead ECG reports were collected from a 12-lead gold 
standard machine and a smartphone-based 12 lead ECG machine. The data of the 294 subjects 
out of 300 subjects were accessed from both ECG machines. The reports were evaluated by a 
Cardiologist based on the observational changes in the morphology of the ECG traces. The gold 
standard ECG machine was 92% sensitive, 47.9% specific and 26.43% accurate in correctly 
interpreting a normal ECG report concerning the diagnosis provided by a Cardiologist. Whereas 
the Smartphone-based 12 lead ECG was found to be 95.9% sensitive, 88.9% specific, and 86.2% 
accurate in detecting a normal ECG concerning the diagnosis provided by a Cardiologist.