New Study Confirms VisualDx’s AI Improves Diagnostic Accuracy at the Point of Care

December 8, 2020

Clinical Decision Support Leader’s DermExpert Solution Brings Specialist Knowledge to General Practitioners, Enhances Diagnosis for Skin of Color

 

ROCHESTER, N.Y. – December 9, 2020 – A new study published in the Journal of Investigative Dermatology (JID) found that VisualDx’s artificial intelligence solution, DermExpert™, analyzed skin conditions with the same degree of accuracy as primary care physicians (PCPs) referencing a visual aid. The researchers also found that DermExpert was equally effective when identifying diseases in light and dark skin types, suggesting that clinical decision support tools built on diverse data sets can augment physician decision-making and help to reduce medical errors and improve patient outcomes, particularly for patients of color.

 

Diagnosing the skin remains challenging as dermatologic disease presentation varies widely, and most medical schools offer 10 hours or less of dermatology-specific instruction. To contextualize general practitioners’ ability to diagnose skin conditions, the research team compared the accuracy of board-certified internal medicine physicians to DermExpert. When presented with a series of clinical images, PCPs accurately diagnosed skin conditions 36% of the time; with the assistance of a visual aid, their diagnostic accuracy increased to 68%. Similarly, DermExpert achieved 68% accuracy, indicating that PCPs can leverage VisualDx’s solution at the point of care to diagnose skin conditions with confidence and speed.

 

“Research shows that over a quarter of all patient visits involve a skin-related problem, which means all physicians must be able to identify dermatologic conditions, no matter their specialty,” said Dr. Steve Xu, a board-certified dermatologist, Assistant Professor of Dermatology at Northwestern University Feinberg School of Medicine, and the study’s primary investigator. “Our research demonstrates a clear need for diagnostic tools like VisualDx in the exam room to make specialist knowledge readily accessible for the benefit of both the patient and the provider.”

 

Given that skin of color remains significantly underrepresented in medical education and training, Dr. Xu’s team also examined the AI algorithm’s ability to accurately identify diseases across a range of skin types. When VisualDx Plus DermExpert was applied to a wide set of clinical images, it achieved nearly equal efficacy in analyzing lighter (70%) and darker skin (68%). As the medical community continues to seek ways to eliminate racial bias in healthcare, this study indicates that AI can help reduce health disparities for traditionally marginalized patient populations.

 

“Our mission at VisualDx is not to replace providers, but to give them that expert ‘second opinion’ needed to make the right call with confidence,” said Dr. Art Papier, CEO of VisualDx. “We’re incredibly proud to see our platform validated by Dr. Xu’s team, particularly in its ability to assist diagnosis in skin of color, as making accurate diagnoses in a timely manner is paramount to providing quality care and improving outcomes.”

 

The full study, “A Point-of-Care, Real-Time Artificial Intelligence System to Support Clinician Diagnosis of a Wide Range of Skin Diseases,” is featured in the Journal of Investigative Dermatology. To speak with VisualDx and the research team, please contact Lindsey Honig at lhonig@ariamarketing.com.

 

About VisualDx

VisualDx is an award-winning diagnostic clinical decision support system that has become the standard medical professional resource at more than 50% of U.S. medical schools and more than 2,300 hospitals and clinics worldwide. VisualDx combines problem oriented clinical search with the world's best curated medical image library, plus medical knowledge from experts and sophisticated machine learning algorithms to help with differential diagnosis, variation, treatment, and patient communication. Our mission is to improve healthcare decision making and reduce diagnostic errors. Learn more at www.visualdx.com.