More than 15,000 beneficiaries from ‘Hedayh’ programs in Alkhobar

How a Saudi university is using artificial intelligence to transform the diagnosis and treatment of skin diseases

RIYADH: In order to increase the efficiency and effectiveness of dermatological care, experts from Saudi Arabia’s King Abdullah University of Science and Technology have created a new, ground-breaking diagnostic system, SkinGPT-4, which utilizes the power of artificial intelligence.

The goal of SkinGPT-4 is to detect, diagnose and identify appropriate treatments for the skin, according to lead researcher Xin Gao, professor of computer science, co-chair of the Smart Health Center of Excellence and chair of the KAUST Bioinformatics Platform. diseases.

Developed in collaboration with SkinGPT-4 first author Juexiao Zhou, a PhD candidate at KAUST, Gao says the technology could potentially provide a life-saving service to patients, especially in rural areas where there are often shortages. qualified dermatologists.

“These specific challenges in dermatology led to the creation of SkinGPT-4,” Gao told Arab News. “The diversity of skin appearances and the need for specialized knowledge to correctly identify and treat these conditions highlighted the need for an advanced AI-driven solution.”

The team recognized the need for such a solution after recognizing the limitations of traditional diagnostic methods and the potential of artificial intelligence, particularly large language models (LLM) – such as the eponymous ChatGPT – to improve the accuracy and efficiency of dermatological diagnosis.

“With SkinGPT-4, users can upload their own skin photos for diagnosis, and SkinGPT-4 can independently determine the characteristics and categories of skin diseases, perform analysis, make treatment recommendations, and enable interactive diagnosis,” Gao said.

Gao and the KAUST team behind the SkinGPT-4 AI dermatologist. (attached)

SkinGPT-4 diagnoses conditions with distinct visual characteristics such as acne, rosacea, melanoma, psoriasis, basal cell carcinoma, eczema and more.

Gao said the development of SkinGPT-4 began with data collection and preprocessing, followed by model training and validation. “The team collected large data sets of dermatology images and patient records to train the AI ​​model,” he said.

“One significant challenge was the integration of different types of data, including images and text, which required the collaboration of computer scientists and dermatologists. The multidisciplinary team worked together to ensure that AI can effectively interpret and analyze images of skin diseases.”


• SkinGPT-4 diagnoses conditions that have different visual characteristics, such as melanoma, psoriasis and eczema.

• Uses a combination of computer vision algorithms, large language models and natural language processing.

• Technology can help doctors and patients in rural areas, where there is often a shortage of trained dermatologists.

SkinGPT-4 uses a combination of computer vision algorithms, LLMs, and natural language processing (NLP) to enable programs to understand human languages.

“The model processes dermatological images using a visual transformer (ViT) to identify patterns and features indicative of various skin diseases,” Gao said.

“ViT aligns to the Llama-2-13b-chat LLM on our dataset using a customized two-step training strategy. This enables LLM Llama-2-13b-chat to understand images of the skin disease and enable a conversation with the patient in natural language.”

This section contains relevant reference points, the (Comment Box)

SkinGPT-4 can be particularly useful in diagnosing rare skin conditions that are not easily recognized by general practitioners.

“A patient with a rare skin rash can be quickly and accurately diagnosed using SkinGPT-4, which has been trained on many dermatological images, including rare diseases,” Gao said.

“In addition, for chronic skin conditions such as psoriasis, SkinGPT-4 can track progression and response to treatment, providing ongoing support and modifying treatment plans as needed.”

Researchers hope SkinGPT-4 will be a game changer in remote or underserved areas with a shortage of dermatologists.

“For example, in a rural community where the nearest dermatologist is hundreds of miles away, a patient presents with a suspicious lesion that may be a rare form of skin cancer,” Gao said.

Properly trained artificial intelligence can provide enormous help to medical practitioners. (Shutterstock image)

“Using the SkinGPT-4, the local healthcare provider can take a high-resolution image of the lesion and enter the patient’s medical history into the system. SkinGPT-4 analyzes the image and the patient’s information, quickly prepares a preliminary diagnosis and recommendations for further actions.”

And as SkinGPT-4 evolves, Gao says the system will learn from its own mistakes through continuous learning and feedback mechanisms.

“By analyzing misdiagnoses and incorporating corrections, the system can refine its algorithms and improve its accuracy over time,” he said. “This iterative learning process ensures that SkinGPT-4 evolves and adapts to new data and emerging trends in dermatology.”

However, Gao is keen to stress that SkinGPT-4 is not designed to completely replace dermatologists. Rather, the program serves as an evolving and optimizing tool and acts as an assistant in facilitating communication between patients and physicians.

“Our aim is for SkinGPT-4 to get more information from patients about skin diseases, while also providing valuable assistance to doctors in the diagnostic process.”

Leave a Comment