CLINICIANS, MOUNT-SINAI PROGRAM AND VETERANS - ADMINISTRATION PROGRAM EVALUATED AGAINST CLINICOPATHOLOGICAL DATA DERIVED INDEPENDENTLY OF ELECTROCARDIOGRAM

  • 1 January 1978
    • journal article
    • research article
    • Vol. 8  (4-5) , 395-412
Abstract
The ECG recorded from 221 adult subjects with cardiac symptomatology were interpreted by clinicians and by the Mount Sinai (MS) and Veterans'' Administration (VA) computer programs. These interpretations were compared with corresponding clinico-pathological data derived independently of the ECG. A measure of overall diagnostic accuracy showed that the performances of the 2 computer programs were similar and not consistent with that of the clinicians. The clinicians and the computer programs showed more dissimilarity in diagnosing the ECG of women than in men. As the VA program''s interpretations may be altered by including information about the patient''s provisional diagnosis, 6 different sets of these prior probabilities were used to analyze 141 of the original 221 ECG. Different fixed sets of prior probabilities made only a small difference in overall diagnostic accuracy but caused a marked difference in the VA program''s ability to differentiate normal from abnormal ECG. Optimizing the prior probabilities for the individual subjects increased the VA program''s overall diagnostic accuracy to a level comparable with that of the clinicians. Both computer programs correctly diagnosed sinus rhythm as the dominant pattern in 165 out of 177 subjects. The MS program diagnosed the dominant rhythm as atrial fibrillation in 35 out of 41 subjects and the VA program in 27 (.chi.2 = 3.24; not significant).

This publication has 0 references indexed in Scilit: