Skin Disease Diagnoses: Disparities and AI Solutions in Medical Practice

According to a new study from MIT researchers, doctors have a harder time diagnosing skin diseases based solely on images when the patient has darker skin. The study’s lead author and an assistant professor at the Northwestern University Kellogg School of Management, Matt Groh PhD ’23, says that the research team found that physicians mostly featured lighter skin tones in dermatology textbooks and training materials, which may be contributing to the discrepancy. Another factor could be that some doctors may have less experience in treating patients with darker skin.

The study’s lead author is Matt Groh PhD ’23, an assistant professor at the Northwestern University Kellogg School of Management, while the senior author is Rosalind Picard, an MIT professor of media arts and sciences.

The research team recruited subjects for the study through Sermo, a social networking site for doctors.

Dermatologists and general practitioners lost about four percentage points in accuracy when diagnosing skin conditions based on images of darker skin. Dermatologists were also less likely to refer darker skin images of CTCL for biopsy, but more likely to refer them for biopsy for noncancerous skin conditions.

The researchers also gave doctors additional images to evaluate with assistance from an AI algorithm they had developed and found that using the AI algorithms improved accuracy for both dermatologists (up to 60 percent) and general practitioners (up to 47 percent).

The researchers hope that their findings will help stimulate medical schools and textbooks to incorporate more training on patients with darker skin.

Source link

Stay in the Loop

Get the daily email from AI Headliner that makes reading the news actually enjoyable. Join our mailing list to stay in the loop to stay informed, for free.

Latest stories

You might also like...