Researchers trained an Artificial Intelligence Algorithm (AIA) to assess patients’ acne condition.

Sophie Seité, Ph.D., La Roche-Posay Dermatological Laboratories, Levallois-Perret, France, and her team have designed an artificial intelligence algorithm that accurately assesses acne and associated lesions through a smartphone. (Aesthetic Authority)

Early assessment of acne severity and its timely treatment can avoid scarring for life. This involves the correct grading and identification of the skin lesions as the first step. This assessment is usually performed by trained and qualified dermatologists – which are decreasing in number according to Dr. Seité.

AI and smartphone technology can help fill the gap.

Grading acne using AI

The researchers collected facial images from acne patients from France, South Africa, China, India, and Brazil.

Three dermatologists then tagged each image for their assessment of its GEA and post-inflammatory hyperpigmentation (PIHP).

Dr. Seité and her team then trained their model algorithm on these tagged images.

Once trained, they ran the algorithm on 1,014 images from 169 patients. Dermatologists checked the algo’s output and corrected it.

The algo was retrained on the changes and corrections. It’s GEA grading thereafter reached 68%, the level of most dermatologists.

“This is the first validated AI algorithm which, using smartphones, allows the grading of acne severity based on the Global Acne Severity (GEA) scale,” says Dr. Seité. “It provides a fast determination of the severity of acne and identifies the different lesion types, thus supporting the early therapeutic management of acne patients.”

The outlook for AI

Patients currently suffer from a paucity of qualified dermatologists. This results in negligence or delay in treatment.

Many patients, therefore, suffer from scarring and residual hyperpigmentation.

According to Dr. Seité, the AI study demonstrates the potential for refining strategies for the management of the condition in the future.

“Non‐adherence to treatment is a common problem worldwide and this application can help practitioners evaluate their patients’ improvement between consultations,” observes Dr. Seité. “Such an approach can help for early management and serve as an educative tool to help the parents and or adolescents to better follow prescribed acne treatments.”

Related Story:   AI May Provide Early Warning of Heart Damage Due to COVID