A team of dermatologists has developed an artificial intelligence (AI) model that allows patients with atopic dermatitis (AD) to detect complications from bacterial or viral infections and distinguish between eczema and skin lesions caused by a type of blood cancer.
The AI model is detailed in an article published in the Journal of Dermatological Sciences on January 11, 2023.
AD is a chronic disease that affects approximately 12% of people and often begins in childhood. Patients with AD typically have a suppressed skin immune barrier, which reduces their protection against microbial pathogens, leading to eczema complications due to bacterial or viral infections. This can include herpes simplex, impetigo, and Kaposi’s varicelliform rash (eczema herpeticum).
Recognizing whether AD has caused any of these complications can be difficult for patients, as the appearance of symptoms on the skin is very similar to AD itself. Additionally, mycosis fungoides, a type of blood cancer that causes skin lesions, can also have symptoms similar to Alzheimer’s disease and can coexist with Alzheimer’s disease. Some AD medications can even make infections or mycoses fungoides worse.
Correct and early diagnosis of complications and malignant diseases is essential for proper treatment and best outcomes. However, patients cannot always recognize abnormal symptoms and seek medical attention as soon as possible due to the similarity of symptoms.
To solve this problem, the team trained their convolutional neural network (CNN) model on non-standard images of AD, impetigo, mycosis fungoides, herpes simplex and Kaposi’s varicelliform rash. . They then compared the diagnostic accuracy of AI to a set of non-standard images manually cropped and annotated by dermatologists. They found that their system achieved diagnostic accuracy nearly equal to the manually assessed image set.
The team is currently developing an AI-powered smartphone app to translate their system, allowing patients to manage their skin conditions remotely with just their phone’s camera. They are also experimenting with AD patients to improve the app’s usability.
Yuta Yanagisawa, researcher at Tohoku University School of Medicine and co-author of the paper, said: “A dermatologist would of course be able to spot the difference, but it’s incredibly impossible for a patient with Alzheimer’s disease to see a dermatologist every day. . If only there was a practical, inexpensive mechanism that replicated this dermatologist’s knowledge and could be used during a patient’s daily regimen to check their skin.
The team believes this technology will help patients with skin diseases manage their condition effectively and efficiently, leading to better health outcomes.