Internist-I, an Experimental Computer-Based Diagnostic Consultant for General Internal Medicine

INTERNIST-I is an experimental computer program capable of making multiple and complex diagnoses in internal medicine. It differs from most other programs for computer-assisted diagnosis in the generality of its approach and the size and diversity of its knowledge base. To document the strengths and weaknesses of the program we performed a systematic evaluation of the capabilities of INTERNIST-I. Its performance on a series of 19 clinicopathological exercises (Case Records of the Massachusetts General Hospital) published in the Journal appeared qualitatively similar to that of the hospital clinicians but inferior to that of the case discussants. The evaluation demonstrated that the present form of the program is not sufficiently reliable for clinical applications. Specific deficiencies that must be overcome include the program's inability to reason anatomically or temporally, its inability to construct differential diagnoses spanning multiple problem areas, its occasional attribution of findings to improper causes, and its inability to explain its "thinking." (N Engl J Med. 1982; 307:468–76.) INTERNIST-I, an experimental program for computer-assisted diagnosis in general internal medicine, differs considerably in scope from other medical diagnostic computer programs. In the past, techniques including mathematical modeling, use of Bayesian statistics, pattern recognition, and other approaches 1 2 3 have been shown to be useful in circumscribed areas, such as the differential diagnosis of abdominal pain 4 and the diagnosis and treatment of meningitis. 5 However, no program developed for use in a limited domain has been successfully adapted for more generalized use. From its inception, INTERNIST-I has addressed the problem of diagnosis within the broad context of general internal medicine. 6 7 8 Given a patient's . . .