Performance of a web-based clinical diagnosis support system for internists

Abstract

BACKGROUND: Clinical decision support systems can improve medical diagnosis and reduce diagnostic errors. Older systems, however, were cumbersome to use and had limited success in identifying the correct diagnosis in complicated cases. OBJECTIVE: To measure the sensitivity and speed of 'Isabel' (Isabel Healthcare Inc., USA), a new web-based clinical decision support system designed to suggest the correct diagnosis in complex medical cases involving adults. METHODS: We tested 50 consecutive Internal Medicine case records published in the New England Journal of Medicine. We first either manually entered 3 to 6 key clinical findings from the case (recommended approach) or pasted in the entire case history. The investigator entering key words was aware of the correct diagnosis. We then determined how often the correct diagnosis was suggested in the list of 30 differential diagnoses generated by the clinical decision support system. We also evaluated the speed of data entry and results recovery. RESULTS: The clinical decision support system suggested the correct diagnosis in 48 of 50 cases (96%) with key findings entry, and in 37 of the 50 cases (74%) if the entire case history was pasted in. Pasting took seconds, manual entry less than a minute, and results were provided within 2-3 seconds with either approach. CONCLUSIONS: The Isabel clinical decision support system quickly suggested the correct diagnosis in almost all of these complex cases, particularly with key finding entry. The system performed well in this experimental setting and merits evaluation in more natural settings and clinical practice