Computer-assisted adult medical diagnosis: subject review and evaluation of a new microcomputer-based system

Three decades after the conceptual foundation was laid for computer-aided diagnosis, some of its potential has been realized. Systems based on probabilistic reasoning have been developed and applied within limited domains (e.g., acute abdominal pain) and for the general diagnosis of systemic disorders. Less progress has been made in the development and application of diagnostic systems based on "artificial intelligence", reflecting theoretical limits to this application of computers to medicine and the enormity of the task. The presently available probabilistic systems have recently been joined by a new microcomputer-based system, MEDITEL Computer-Assisted Diagnosis, Adult System. The performance of this system was evaluated with both clinical-pathologic conference cases and consecutive admissions with undiagnosed illnesses. The correct diagnosis appeared on the list generated by the system in 80 to 90% of the cases. Experience with this and other systems illustrates current issues in the evaluation of computer systems for aid in diagnosis and of computer-based medical "expert" systems in general. These issues include physician acceptance of these systems and the ethical, legal, and regulatory aspects of computer system application. We conclude that, in appropriately selected cases, the accuracy and efficiency of physician diagnosis can be enhanced with computer assistance, and the risk of overlooking the correct diagnosis can be reduced.