[Artificial intelligence capabilities in multiple sclerosis].
Обработка статьи · этапы, ошибки и управление
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.
Belova A N, Sheiko G E, Rakhmanova E M, Boyko A N
Аннотация
MATERIAL AND METHODS: The literature search was performed in electronic search engines Scopus, eLibrary, PubMed using the following keywords: multiple sclerosis, diagnosis, prediction, artificial intelligence, machine learning. Scientific articles published between 2018 and 2024 were selected for the review.
RESULTS: A summary of AI technologies and machine learning (ML) models is provided. It is shown that AI opens up vast opportunities for studying the pathogenetic mechanisms of MS development, can help solve differential diagnosis problems, and predict the course of the disease. Examples of the use of ML algorithms to identify MS biomarkers, early diagnosis and prediction of disease activity are described. Restrictions on the use of AI in clinical practice are considered, including the need for access to large databases to create reliable ML algorithms, the lack of information understandable to clinicians about decision-making mechanisms, the risk of system errors and unreliable results, the suitability of the ML model results for those populations used to train this model only.
CONCLUSION: Implementing all AI capabilities in the management of MS patients requires the joint efforts of information technology specialists, scientists, and clinicians.
Оригинал публикации
[Artificial intelligence capabilities in multiple sclerosis].
OBJECTIVE: To systematize current data on the potential use of artificial intelligence (AI) in multiple sclerosis (MS) research.
MATERIAL AND METHODS: The literature search was performed in electronic search engines Scopus, eLibrary, PubMed using the following keywords: multiple sclerosis, diagnosis, prediction, artificial intelligence, machine learning. Scientific articles published between 2018 and 2024 were selected for the review.
RESULTS: A summary of AI technologies and machine learning (ML) models is provided. It is shown that AI opens up vast opportunities for studying the pathogenetic mechanisms of MS development, can help solve differential diagnosis problems, and predict the course of the disease. Examples of the use of ML algorithms to identify MS biomarkers, early diagnosis and prediction of disease activity are described. Restrictions on the use of AI in clinical practice are considered, including the need for access to large databases to create reliable ML algorithms, the lack of information understandable to clinicians about decision-making mechanisms, the risk of system errors and unreliable results, the suitability of the ML model results for those populations used to train this model only.
CONCLUSION: Implementing all AI capabilities in the management of MS patients requires the joint efforts of information technology specialists, scientists, and clinicians.