Information Acquisition in Diagnosis

Ramesh S. Patil, Peter Szolovits, William B. Schwartz, M.D.

We argue that the question selection processes used in the existing AI in Medicine programs are inadequate. We trace these inadequacies to their use of purely surface level models of disease and to the lack of planning in sequencing their inquiries. We then describe the information gathering component of ABEL, (a program for Acid-Base and Electrolyte disturbances) with emphasis on its use of a causal model of a patient’s illness in guiding its diagnostic inquiries.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.