Current oncology reports · 2026
From Symptom Control to Precision Supportive Oncology: Integrating Artificial Intelligence in Supportive Oncology for Gastrointestinal Cancers.
СтатьяОбзорНазвание и аннотация: Перевод в очереди
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.
Krishnan Arunkumar, Davis Mellar P, Kadakia Kunal C
Аннотация
PURPOSE OF REVIEW: Gastrointestinal (GI) cancers are among the most common malignancies worldwide and impose a substantial symptom burden from diagnosis through survivorship. Despite advances in systemic therapies and surgical approaches, patients continue to experience undertreated symptoms, psychosocial distress, financial toxicity, and fragmented supportive care. This review examines how artificial intelligence (AI) may help transform GI supportive oncology from a reactive, episodic model to a proactive, continuous, and personalized approach.
RECENT FINDINGS: AI applications in GI supportive oncology are advancing along two related domains: (1) AI-enabled patient-reported outcome (PRO) tools, including real-time symptom monitoring, unsupervised symptom clustering, and AI-enhanced triage pathways; and (2) tumor-aware supportive care, including AI-driven radiomics for sarcopenia detection and multimodal prognostic models that inform supportive care needs. Systematic electronic PRO monitoring has been associated with improved survival and reduced acute care utilization, while AI-automated CT sarcopenia detection identifies muscle wasting that routine clinical documentation often misses. Important implementation challenges remain, including the black-box problem, algorithmic bias, privacy concerns, the digital divide, and regulatory uncertainty. Precision supportive oncology, integrating PRO-based symptom intelligence with imaging-derived risk stratification, has the potential to improve GI cancer care by making it more anticipatory and patient-centered. This review proposes a two-lane framework consisting of PRO-driven symptom intelligence and tumor-aware supportive care, unified by principles of privacy, explainability, and equity. Responsible adoption will require prospective validation, equitable design, and clinically interpretable systems.
RECENT FINDINGS: AI applications in GI supportive oncology are advancing along two related domains: (1) AI-enabled patient-reported outcome (PRO) tools, including real-time symptom monitoring, unsupervised symptom clustering, and AI-enhanced triage pathways; and (2) tumor-aware supportive care, including AI-driven radiomics for sarcopenia detection and multimodal prognostic models that inform supportive care needs. Systematic electronic PRO monitoring has been associated with improved survival and reduced acute care utilization, while AI-automated CT sarcopenia detection identifies muscle wasting that routine clinical documentation often misses. Important implementation challenges remain, including the black-box problem, algorithmic bias, privacy concerns, the digital divide, and regulatory uncertainty. Precision supportive oncology, integrating PRO-based symptom intelligence with imaging-derived risk stratification, has the potential to improve GI cancer care by making it more anticipatory and patient-centered. This review proposes a two-lane framework consisting of PRO-driven symptom intelligence and tumor-aware supportive care, unified by principles of privacy, explainability, and equity. Responsible adoption will require prospective validation, equitable design, and clinically interpretable systems.