Journal of cutaneous medicine and surgery · 2024
Emerging Uses of Artificial Intelligence in Chronic Dermatologic Disease: A Scoping Review.
СтатьяScoping ReviewНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Hollman Dylan, Doktorchik Chelsea, Mukovozov Ilya
Аннотация
BACKGROUND: Recent years have seen a surge in the use of artificial intelligence (AI) in healthcare, including dermatology. This scoping review aimed to assess the emerging applications of AI use in the context of chronic, non-neoplastic dermatologic diseases.
METHODS: MEDLINE, Embase, PubMed and SCOPUS were searched on August 11, 2023 using variations of the search concepts "dermatology," "artificial intelligence," and 12 common chronic dermatologic conditions. Article screening and data extraction were completed, and each study was categorized into themes and conditions.
RESULTS: A total of 224 unique studies were included. The most prevalent conditions that were studied in the context of AI included psoriasis (n = 67), atopic dermatitis/eczema (n = 41) and acne (n = 36). The majority of AI applications involved clinical evaluation (n = 176), images (analysis, generation or segmentation) (n = 163) and data analysis (n = 46). Clinical evaluation was further divided into 2 subthemes: diagnosis (n = 104) and disease assessment (n = 67). Diagnostic and analytic applications of AI are limited by the training datasets available (quantity of training data, image quality) and insufficient diagnostic information provided (eg, the patient's reported history of their lesion, disease/symptom onset and risk factors).
CONCLUSIONS: Common applications of AI are predominantly as an automated diagnostic tool for evaluating disease severity/characteristics, while niche and novel applications were explored further. However, recognizing the limitations of technology is critical prior to the widespread application of AI in dermatological practice. The insights from the current study can inform clinical adoption of AI in dermatology, and highlight research gaps to guide future academic initiatives.
METHODS: MEDLINE, Embase, PubMed and SCOPUS were searched on August 11, 2023 using variations of the search concepts "dermatology," "artificial intelligence," and 12 common chronic dermatologic conditions. Article screening and data extraction were completed, and each study was categorized into themes and conditions.
RESULTS: A total of 224 unique studies were included. The most prevalent conditions that were studied in the context of AI included psoriasis (n = 67), atopic dermatitis/eczema (n = 41) and acne (n = 36). The majority of AI applications involved clinical evaluation (n = 176), images (analysis, generation or segmentation) (n = 163) and data analysis (n = 46). Clinical evaluation was further divided into 2 subthemes: diagnosis (n = 104) and disease assessment (n = 67). Diagnostic and analytic applications of AI are limited by the training datasets available (quantity of training data, image quality) and insufficient diagnostic information provided (eg, the patient's reported history of their lesion, disease/symptom onset and risk factors).
CONCLUSIONS: Common applications of AI are predominantly as an automated diagnostic tool for evaluating disease severity/characteristics, while niche and novel applications were explored further. However, recognizing the limitations of technology is critical prior to the widespread application of AI in dermatological practice. The insights from the current study can inform clinical adoption of AI in dermatology, and highlight research gaps to guide future academic initiatives.