Interpretation strategies in a cardiologist-controllable automatic assistant for ECG description

An approach to electrocardiogram (ECG) interpretation which exploits a uniform notation to define structures to be found and interpretation strategies is presented. The study of the ECG visual interpretation activity by cardiologists provided the guidelines for the development of the system for ECG interpretation (SIECG), an automatic assistant able to identify and evaluate structures which are tracks of meaningful events in an ECG. SIECG follows a data-driven strategy, i.e. a sequence of computational actions determined step by step. The strategy provides for the accumulation of findings at different levels of abstraction. A method for defining strategies based on conditional attributed rewriting systems has been defined which provides SIECG with reflective abilities. Some examples have shown situations in which the system has to exploit this feature