Pathophysiologic assessment of data from a stroke data bank

Stroke data banks have been instrumental in helping us to clarify stroke etiology and in the investigation of clinical-topographic correlations. For these purposes they have relied upon results from noninvasive vascular and cardiac methods, including extra- and transcranial Doppler sonography and echocardiography, as well as from procedures such as cranial computed tomography and magnetic resonance imaging. Conventional database concepts have also been used to assess pathophysiologic aspects of stroke. Although such applications have made important contributions in this multidiscipline area of investigation, they are limited by a lack of explicit representation of pathophysiologic knowledge for data interpretation. Recent results from artificial intelligence research suggest exciting new frontiers for medical database design with concepts stemming from second generation expert systems. We propose an extended concept for stroke data banks to include a knowledge-based system which incorporates current patient data, heuristic knowledge relating clinical features to functional impairment, and pathophysiologic models of neurological disease.