Journal of Crohn's & colitis · 2026
Results of the Ninth Scientific Workshop of the European Crohn's and Colitis Organisation (ECCO): Artificial Intelligence in medical management and precision medicine.
СтатьяСистематический обзорНазвание 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.
Kopylov Uri, Verstockt Bram, Marigorta Urko M, Noviello Daniele, Bossuyt Peter, Mookhoek Aart, Sinonquel Pieter, El-Hussuna Alaa, Sahnan Kapil, Baumgart Daniel C, Noor Nurulamin M, Allocca Mariangela, Carter Dan, Ensari Arzu, Iacucci Marietta, Pellino Gianluca, Soriano Alessandra, de Laffolie Jan, Daperno Marco, Raine Tim, Cleynen Isabelle, Sebastian Shaji
Аннотация
BACKGROUND AND AIMS: Artificial intelligence (AI) is increasingly being applied in various fields of medicine, including inflammatory bowel diseases (IBD). This systematic review, conducted as part of the ECCO 9th Scientific Workshop on AI in IBD, explores AI applications in multiomics precision medicine, large language models (LLMs) for textual tasks, and utilization of wearable and remote care technologies.
METHODS: A comprehensive systematic analysis of the literature was undertaken, emphasizing three topics: multiomics predictive models in IBD; natural language processing (NLP) and LLMs for clinical practice, research and patient communication; and the role of remote monitoring and wearable devices.
RESULTS: Key areas of promise include the implementation of NLP and LLMs for case identification and differentiation, tracking disease activity, pharmacovigilance, quality assurance, and patient support. Multiomic approaches, integrating genomics, transcriptomics, proteomics, metabolomics, and metagenomics, show potential for developing more accurate diagnostic and risk prediction models and improving treatment response prediction and detection of actionable drug targets for future therapeutics. Wearables and remote monitoring technologies can transform IBD management from episodic assessments to continuous, less biased tracking of patient-reported outcomes and physiological biomarkers.
CONCLUSIONS: While AI and multiomics approaches hold substantial promise for advancing IBD management and research, further refinement is necessary to ensure content validity and address safety concerns, thereby allowing integration of AI into clinical workflows and safeguarding of data privacy. Future research should prioritize the integration of diverse omic data, conduct of longitudinal studies, and validation in large and diverse cohorts.
METHODS: A comprehensive systematic analysis of the literature was undertaken, emphasizing three topics: multiomics predictive models in IBD; natural language processing (NLP) and LLMs for clinical practice, research and patient communication; and the role of remote monitoring and wearable devices.
RESULTS: Key areas of promise include the implementation of NLP and LLMs for case identification and differentiation, tracking disease activity, pharmacovigilance, quality assurance, and patient support. Multiomic approaches, integrating genomics, transcriptomics, proteomics, metabolomics, and metagenomics, show potential for developing more accurate diagnostic and risk prediction models and improving treatment response prediction and detection of actionable drug targets for future therapeutics. Wearables and remote monitoring technologies can transform IBD management from episodic assessments to continuous, less biased tracking of patient-reported outcomes and physiological biomarkers.
CONCLUSIONS: While AI and multiomics approaches hold substantial promise for advancing IBD management and research, further refinement is necessary to ensure content validity and address safety concerns, thereby allowing integration of AI into clinical workflows and safeguarding of data privacy. Future research should prioritize the integration of diverse omic data, conduct of longitudinal studies, and validation in large and diverse cohorts.