Model-based interpretation of the ECG: a methodology for temporal and spatial reasoning.

A new software architecture for automatic interpretation of the electrocardiographic rhythm is presented. Using the hypothesize-and-test paradigm, a semiquantitative physiological model and production rule-based knowledge are combined to reason about time- and space-varying characteristics of complex heart rhythms. A prototype system implementing the methodology accepts a semiquantitative description of the onset and morphology of the P waves and QRS complexes that are observed in the body-surface electrocardiogram. A beat-by-beat explanation of the origin and consequences of each wave is produced. The output is in the standard cardiology laddergram format. The current prototype generates the full differential diagnosis of narrow-complex tachycardia and correctly diagnoses complex rhythms, such as atrioventricular (AV) nodal reentrant tachycardia with either hidden or visible P waves and varying degrees of AV block.