Despite numerous attempts at devising algorithms for diagnosing broad compl
ex tachycardia (BCT) on the basis of the electrocardiogram (ECG), misdiagno
sis is still common. The reason for this may lie with difficulty in impleme
nting existent algorithms in practice, due to imperfect ascertainment of EC
G features within them. An attempt was made to approach the problem afresh
with the Bayesian inference by the construction of a diagnostic algorithm c
entered around the likelihood ratio (LR). Previously studied ECG features m
ost effective in discriminating ventricular tachycardia (VT) from supravent
ricular tachycardia with aberrant conduction (SVTAC), according to their LR
values, were selected for inclusion into a Bayesian diagnostic algorithm.
A test set of 244 BCT ECGs was assembled and shown to three independent obs
ervers who were blinded to the diagnoses made at electrophysiological study
. Their diagnostic accuracy by the Bayesian algorithm was compared against
that by clinical judgement with the diagnoses from EPS as the criterial sta
ndard. Clinical judgement correctly diagnosed 35% of SVTAC, 85% of VT, and
47% of fascicular tachycardia. In comparison, by the Bayesian algorithm dev
ised, 52% of SVTAC, 95% of VT, and 97% of fascicular tachycardia were corre
ctly diagnosed. The Bayesian algorithm devised has proved to be superior to
the clinical judgement of the observers who participated in this study, an
d theoretically will obviate the problem of imperfect ascertainment of ECG
features. Hence, it holds the promise for being an effective tool for routi
ne use in clinical practice.