Researchers at the Perelman School of Medicine at the University of Pennsylvania found that a computer-assisted tool can improve diagnostic accuracy in assessing skin conditions.
The tool, VisualDx, allows allowing physicians to enter information such as the type and location of a rash, and associated symptoms such as pain or itching, and then generates a range of possible diagnoses accompanied by photographs. The photos allow the users to compare the rash of the patient with of more than 1,300 pediatric and adult skin conditions represented by nearly 30,000 images. The researchers say it could help providers overcome cognitive shortcomings such as availability bias, when they diagnose patients with conditions they've recently seen or can easily recall, rather than those conditions that are most likely to occur.
The researchers compared the 12 months before VisualDx was introduced to the 18 months it was use and found there was no change in the rate of dermatologic consultations at the Hospital of the University of Pennsylvania. “This is important because these tools by design suggest numerous potential diagnoses, which could result in an increase in unnecessary testing and specialty consultation, and associated costs and harms, particularly in the hands of less experienced clinicians," the study's senior author, Craig A. Umscheid, M.D. assistant professor of Medicine and Epidemiology and director of the Penn Medicine Center for Evidence-based Practice, said in a statement.
Dr. Umscheid said that a drop in consultations would have suggested that general internists, emergency room physicians, family doctors, and pediatricians may have relied on the tool to make dermatologic diagnoses, rather than consulting a dermatologist for help.
Providers accessed the applications through mobile devices (35 percent), inpatient (34 percent), outpatient (11 percent), and emergency department (one percent) electronic health records, and via searches in UpToDate, a point-of-care evidence summary resource (19 percent).
