Summary of "Should electronic differential diagnosis support be used early or late in the diagnostic process? A multicentre experimental study of Isabel"

Participants from 6 Canadian medical schools comprising of 67 medical students, 62 internal medicine or emergency medicine residents, 61 internal medicine or emergency medicine attendings were randomized to either early or late use of an electronic differential diagnostic support (EDS) system called Isabel during the diagnostic process of solving 16 written cases. Early use was defined as using Isabel after the chief complaint and late used was defined as using Isabel after the complete history and physical & case details were presented. All participants provided an initial differential diagnosis list, including as many diagnoses as they felt relevant after receiving the chief complaint. Then the early group was randomized to use the EDS and then provide a revised list of differential diagnoses. After this, they read the rest of the case details and then provided another revised list of differential diagnoses. The late group read the entire case, revised their final differential diagnoses list without the EDS and then were used the EDS to further revise their differential diagnoses list. The primary outcome was the number of diagnoses proposed in the differential diagnosis list for each case and how often the correct diagnosis was present within the differential for each case. The study showed that the EDS system increased the number of diagnostic hypotheses by 2.32 (95% CI 2.10 to 2.49) when used early in the process and 0.89 (95% CI 0.69 to 1.10) when used late in the process (both p<0.001). Both early and late use of the EDS system increased the likelihood of the correct diagnosis being present in the differential (7% and 8%, respectively, both p<0.001). So, while early use increased the number of differential diagnoses (especially in medical students and residents), late use increased the likelihood of the correct diagnosis being present in the differential regardless of one’s level of experience. Overall, using an EDS system increased the number of differential diagnoses and the likelihood of the correct diagnosis appearing in the differential. These effects persisted irrespective of whether the EDS system was used early or late in the diagnostic process.