Diagnostic accuracy in Family Medicine residents using a clinical decision support system (DXplain): a randomized-controlled trial

Background: Clinical reasoning is an essential skill in physicians, required to address the challenges of accurate patient diagnoses. The goal of the study was to compare the diagnostic accuracy in Family Medicine residents, with and without the use of a clinical decision support tool (DXplain http://www.mghlcs.org/projects/dxplain). Methods: A total of 87 first-year Family Medicine residents, training at the National Autonomous University of Mexico (UNAM) Postgraduate Studies Division in Mexico City, participated voluntarily in the study. They were randomized to a control group and an intervention group that used DXplain. Both groups solved 30 clinical diagnosis cases (internal medicine, pediatrics, gynecology and emergency medicine) in a multiple-choice question test that had validity evidence. Results: The percent-correct score in the Diagnosis Test in the control group (44 residents) was 74.1 +/- 9.4 (mean +/- standard deviation) whereas the DXplain intervention group (43 residents) had a score of 82.4 +/- 8.5 (p < 0.001). There were significant differences in the four knowledge content areas of the test. Conclusions: Family Medicine residents have appropriate diagnostic accuracy that can improve with the use of DXplain. This could help decrease diagnostic errors, improve patient safety and the quality of medical practice. The use of clinical decision support systems could be useful in educational interventions and medical practice.