PubMed · 6986092
The source did not provide an abstract. Follow the original record for more information.
Explore connections, maps & timelines
Z C Taintor. 1980. Computers and diagnosis.. https://doi.org/10.1176/ajp.137.1.61
Cite the original work for its findings. Save a collection to share your selection of sources.
KEEP EXPLORING
Explore the source record for details and available documents.
A number of computer-based systems with diagnostic capabilities have been developed for internal medicine. Quick Medical Reference (QMR) is one such program. The authors describe key features of QMR and report on their study of its effectiveness as a diagnostic tool. They investigated how frequently the correct diagnosis would appear among the 5 highest ranked diagnoses generated by QMR. The charts of 1144 consecutive patients admitted to a teaching unit were retrospectively screened. Eligible cases included those referred for investigation of an undiagnosed illness with an objectively proven final diagnosis (n = 154). Two physicians familiar with, but not experts in, the use of QMR entered clinical information abstracted from the patients' charts into the program. Physician A obtained the correct diagnosis in 62 (40%) of the 154 cases, and physician B was successful in 56 (36%) of the cases. The authors use study cases to illustrate QMR's strengths and weaknesses.
BACKGROUND AND OBJECTIVE: HepatoConsult (HC) is a medical expert system, based on the expert system building block D3, designed to aid in the diagnosis of liver and biliary tract disease. It was the aim of this study to evaluate its diagnostic competence in clinical cases prospectively. PATIENTS AND METHODS: The diagnostic accuracy of HC was tested prospectively in 106 consecutive patients with the main diagnosis of liver disease. 57 were ambulant, 49 were in-patients. The data were obtained and stored at defined phases of the diagnosis. The diagnoses put forward by HC were compared with the final clinical diagnosis and, on the basis of the data, checked for plausibility by four experienced physicians. RESULTS: After history taking and physical examination HC put forward the main diagnosis, as established by the doctors in charge, in 60% of patients. After addition of the results of basic laboratory tests and sonography, HC provided the correct diagnosis in 85% and, after inclusion of all the findings, in 93%. In almost all cases HC put forward diagnoses that were, on the basis of the supplied data, considered correct by the four physicians experienced in liver disease. In 56% of cases HC provided more differentiated diagnoses or items in the differential diagnosis than the attending doctors. In the opinion of the four assessors HC had not put forward any seriously wrong diagnoses. CONCLUSION: HC can be useful in solving diagnostic problems and thus in ensuring the quality of medical diagnoses.