MODEL-BASED DIAGNOSIS OF BRAIN DISORDERS - A PROTOTYPE FRAMEWORK

This paper describes a prototype framework, named NEUROLAB, dedicated to research and diagnosis in the area of brain disorders. The diagnost ic task uses a blending of factual knowledge, formal knowledge, and ex periential knowledge. The prototype's first target clinical applicatio n is partial seizures in epilepsy. Diagnosis is carried out using qual itative electroencephalographic descriptions, clinical attack pattern descriptions, and pre- and post-ictal observations. From this informat ion, the system builds explanations in the form of candidate epileptog enic foci and trajectories of the seizure spread. Hypothesis-testing a nd discrimination is based on minimal set coverage, and consistency-ch ecking is performed using the general background knowledge. Upon compl etion, NEUROLAB will provide specific physiological knowledge for solv ing the so-called inverse problems in electroencephalography (EEG) and magnetoencephalography (MEG).