Journal of multidisciplinary healthcare · 2026
Artificial Intelligence in the Nutritional Management of Inflammatory Bowel Disease: A Scoping Review.
СтатьяОбзорНазвание 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.
Qian Xia, Yu Jie, Zhang Qun, Jia Guanzhen, Guo Junjun, Lin Tianmei
Аннотация
BACKGROUND: Diet is closely associated with the onset, progression, and prognosis of inflammatory bowel disease (IBD). In the absence of specific dietary and nutritional guidelines, nutritional management for IBD patients is fraught with challenges and uncertainties. Existing research indicates that artificial intelligence (AI) has great potential for application in the nutritional management of patients with chronic diseases; however, current research on its use in IBD patients is limited.
METHODS: This scoping review was reported in strict accordance with the PRISMA-ScR checklist. A systematic search was conducted across 11 databases, including PubMed, Web of Science, and Scopus, covering the period from the inception of each database to February 2026, focusing on studies investigating the application of AI in the nutritional management of IBD patients.
RESULTS: Of the 4,560 records initially screened, 16 studies met the inclusion criteria. The results indicate that AI applications primarily focus on: dietary pattern recognition, such as using clustering algorithms to identify an association between plant-based diets and lower inflammation risk; treatment response prediction, with machine learning models predicting the success rate of total parenteral nutrition and achieving 90% accuracy in distinguishing between Crohn's disease and ulcerative colitis; personalized information support, where conversational AI such as ChatGPT answered nutritional questions with 83.0% accuracy, and smartphone apps can influence patients' dietary behaviors; identifying patient needs, where Natural Language Processing and Latent Dirichlet Allocation (LDA) topic modeling identified key patient concerns such as treatment experiences, dietary advice, and psychological burden. Key technologies encompass traditional machine learning, deep learning, natural language processing, and multi-omics integrated analysis. AI applications have preliminarily demonstrated the ability to reduce inflammatory markers and improve gut microbiota; fecal metabolites have been confirmed as reliable indicators of disease.
CONCLUSION: AI holds promise for the nutritional management of IBD and has shown preliminary success in pattern recognition, prediction of treatment efficacy, and patient empowerment. However, existing studies are often limited by small sample sizes and insufficient generalizability, and the evidence remains preliminary and heterogeneous. Future efforts should focus on large-scale studies and multidisciplinary collaboration to advance AI from proof-of-concept to clinical practice.
METHODS: This scoping review was reported in strict accordance with the PRISMA-ScR checklist. A systematic search was conducted across 11 databases, including PubMed, Web of Science, and Scopus, covering the period from the inception of each database to February 2026, focusing on studies investigating the application of AI in the nutritional management of IBD patients.
RESULTS: Of the 4,560 records initially screened, 16 studies met the inclusion criteria. The results indicate that AI applications primarily focus on: dietary pattern recognition, such as using clustering algorithms to identify an association between plant-based diets and lower inflammation risk; treatment response prediction, with machine learning models predicting the success rate of total parenteral nutrition and achieving 90% accuracy in distinguishing between Crohn's disease and ulcerative colitis; personalized information support, where conversational AI such as ChatGPT answered nutritional questions with 83.0% accuracy, and smartphone apps can influence patients' dietary behaviors; identifying patient needs, where Natural Language Processing and Latent Dirichlet Allocation (LDA) topic modeling identified key patient concerns such as treatment experiences, dietary advice, and psychological burden. Key technologies encompass traditional machine learning, deep learning, natural language processing, and multi-omics integrated analysis. AI applications have preliminarily demonstrated the ability to reduce inflammatory markers and improve gut microbiota; fecal metabolites have been confirmed as reliable indicators of disease.
CONCLUSION: AI holds promise for the nutritional management of IBD and has shown preliminary success in pattern recognition, prediction of treatment efficacy, and patient empowerment. However, existing studies are often limited by small sample sizes and insufficient generalizability, and the evidence remains preliminary and heterogeneous. Future efforts should focus on large-scale studies and multidisciplinary collaboration to advance AI from proof-of-concept to clinical practice.