CAA: A KNOWLEDGE BASED SYSTEM USING CAUSAL KNOWLEDGE TO DIAGNOSE CARDIAC RHYTHM DISORDERS Tetsutaro Shibahara, John K. Tsotsos, John Mylopoulos, and H. Dominic Covvey Laboratory for Computational Medicine Dept. of Computer Science, Univ. of Toronto Toronto, Ontario, CANADA M5S 1A4 ABSTRACT An expert system, Causal Arrhythmia Analyzer (CAA), is being developed to establish a framework for the recognition of time varying signals of a complex repetitive nature, such as electrocardiograms (ECGs). Using a stratified knowledge base the CAA system discerns several perspectives about the phenomena of underlying entities, such as the physiological event knowledge of the cardiac conduction system and the morphological waveform knowledge of ECG tracings, where conduction events are projected into the observable waveform domain. Projection links have been defined to represent projection in CAA's frame-based formalism and are used to raise hypotheses across different KBs. The CAA system also introduces and uses causal links extensively to represent various causal and temporal relations between concepts in the physiological event domain. Its control structure uses causal links to predict unseen events from recognized events, to confirm these event hypotheses against input data, and to calculate the degree of integrity among causally related events. The meta-knowledge representation of statistical information about events facilitates a default reasoning mechanism and supports this expectation process providing context sensitive statistical information. The CAA system inherits its basic control mechanisms from the ALVEN (A Left VENtricular Wall Motion Analysis) system [Tsotsos 1981], such as the change/focus attention mechanism with similarity links and the hypothesis rating mechanism. A prototype CAA system with a limited number of abnormalities has been implemented using the knowledge representation language PSN (Procedural Semantic Networks) [Levesque & Mylopoulos 1979]. The prototype has so far demonstrated satisfactory results using independently sampled ECG data. 7 INTRODUCTION The main objective of this study is to establish a framework for the recognition of time varying signals of a complex repetitive nature, such as electrocardiograms. To this end, an expert system called CAA (Causal Arrhythmia Analyzer) is being developed to diagnose rhythm disorders (usually called arrhythmias) in electrocardiographic monitoring. We have chosen the arrhythmia analysis problem because it is a domain rich in temporal and causal interrelationships, and because it is considered a remaining open question in the ECG research domain despite the efforts and the success in computerized ECG interpretation (early success: e.g. [Bonner 1972], recent Al approach: [Birman 1982]). To diagnose rhythm disorders of the heart, the events in the undorlying cardiac conduction system must be exactly determined from one or more streams of observed bodysurface ECG signals. Unlike other existing or proposed ECG systems, our system utilizes knowledge of the causal structure of physiological events in the conduction system, and tries to determine the most likely set (or sets) of underlying events that explain the input wave signals. The causal links, therefore, were introduced in the CAA system and they play an essential role in characterizing a complex event concept aggregated from other more basic (component) concepts by specifying the causal and temporal relationships among the component events. Hence, their representational role is analogous to that of structural descriptions in a composite structure concept in the spatial domain, as seen in other representational languages such as KLONE [Brachman, R.J. 1979]. In CAA's event recognition, causal links are most effectively used to make expectations of events linked to already recognized events when the direct observations of those events are difficult or impossible by noise or nature. A frame-type representation of semantic networks is used to maintain a stratified knowledge base that contains knowledge about the waveforms of ECG signals, knowledge about the physiology of rhythm disorders, and their interrelationships. Projection links were introduced to describe the concept-to-concept relationships across different KBs. As for the control structure, ALVEN's basic control structure [Tsotsos 1981] is used and extended to facilitate the above expectation and projection mechanisms, and to handle recursive hypothesis generation for repetitive event recognition. From the Al viewpoint, therefore, the CAA system is considered as an empirical semantic network system for event sequence recognition, which Includes the explicit description and use of causative temporal knowledge and the use of a stratified knowledge base structure with inter-related distinct KBs.