A model-based expert system for interpretation of hemodynamic data from ICU patients

With the proliferation of modern monitoring and laboratory procedures, physicians in intensive care areas may face ''information overload'', in dealing with very large, complex and ever-changing quantities of clinical data, which often lacks efficient organization. This research analyzes the medical knowledge required for formulating decision models in the domain of hemodynamics. Based on, such analysis, a knowledge based expert system to track a patient's hemodynamic state has been developed and evaluated in a laboratory setting. The initial phase of the work utilizes a cardiovascular simulator to generate ''pseudo-ICU'' waveforms as input to the expert system in order to guide the development of the matrix of rules and search strategies. A number of pathological simulations have been successfully analyzed by this model-based expert system, including examples of hypertension, left ventricular failure, hypovolemia, pulmonary hypertension , etc. We conclude that our approach is practical, and provides a mechanism for transforming and reducing real-time physiologic data into pathophysiologic hypotheses relevant to the management of patients.