Evaluating RECONSIDER

RECONSIDER, a computer program designed to perform as a diagnostic prompting aid, was evaluated for its ability to include the correct diagnosis in an ordered computed list of candidate diseases. The study was performed using 100 consecutive first admissions to the medical service of a university hospital, where the individuals entering the data into the program were blind to all but a limited set of findings known at time of admission. Each person entering the data created one or more lists of diagnostic possibilities (versions) using the program. The program suggested the correct diagnosis within the first 40 on its list 61% (498/797) of the time; the correct diagnosis was present with the first 40 in at least one version 93% (98/105) of the time. Performance was found to be best with cases having a single diagnosis and when more terms were entered into the program.