Decision support software to help primary care physicians triage skin cancer - A pilot study

Objective: To determine whether decision support software can help primary care physicians proficiently triage lesions suggestive of basal cell and sq uamous cell carcinoma. Design/Measures: Physicians selected triage options for 15 digitized images of skin lesions, with and without use of the decision support software. Participants/Settings: Twenty primary care physicians practicing in a healt h maintenance organization or a city health clinic. Intervention: Decision support software designed to help physicians arrive at a triage recommendation consisted of a clinical information form, a deci sion tree, and support features (teaching points, example images, and diagr ams). Results: Without using the decision support software, physicians chose the wrong triage decision 36.7% of the time; using the decision support softwar e, they chose the wrong response only 13.3% of the time. Not using the deci sion support software, they failed to correctly perform a biopsy on or refe r patients with cancerous lesions 22.1% of the time; using the software, th ey failed to correctly perform a biopsy on or refer patients with cancerous lesions only 3.6% of the time. Physicians scored an average of 3 points (o f a possible 15 points) higher when they used the software (signed rank, 10 1.0; P<.001). They scored an average of 1 point higher on the 7 cancerous l esions when they used the software (signed rank, 65.5; P<.001). Conclusions: Use of decision support software could improve primary care ph ysicians' triage decisions for lesions suggestive of nonmelanoma skin cance r, and potentially reduce morbidity and health care costs. We are designing a larger study to evaluate the accuracy and utility of the software with p atients seen in clinical practice.