Abstract

A computer program has been written to assist medical personnel in the diagnosis of eruptions with fever. Thirty-four criteria are utilized in the diagnosis of 33 clinical entities. Diagnosis is based on template analysis, Bayesian statistical analysis, or a combination of the two. Of 97 cases of febrile illnesses with eruption, 62 were documented diagnoses within the universe of the program. Template analysis succeeded in 90% of these, Bayesian analysis produced the correct diagnosis in 81%, and in 55% it resulted in a list containing the clinician's diagnosis is most probable. The combined method yielded the clinician's diagnosis as most probable in 65% of the cases. The discrepancies between the clinician's diagnosis and the computer output have been analyzed and found to be due to inadequacies in the dermatologic data base.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.