European geriatric medicine · 2025
AI-assisted PEG aftercare education for older adults: clinician-informed chatbot design (PEGAssist).
СтатьяНазвание 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.
Ozata Duygu, Cingar Alpay Kubra, Avlagi Gokalp Kurthan, Bilgin Seyda, Durak Ummugulsum, Ozata Ibrahim Halil, Calbay Deveci Sultan, Avci Suna, Doventas Alper, Erdinçler Ulev Deniz
Аннотация
PURPOSE: To evaluate whether a geriatric-focused, ChatGPT-based chatbot (PEGAssist) provides clinically adequate and comprehensible guidance for percutaneous endoscopic gastrostomy (PEG) aftercare in older adults. We examined whether its answers met expert expectations for depth/clinical usefulness, clarity/actionability, and scientific accuracy, with emphasis on complication recognition and triage.
METHODS: A multidisciplinary panel (geriatrics, nursing, surgery) independently rated chatbot responses to a curated set of common PEG aftercare questions spanning education, routine care, troubleshooting, and complications. Ratings addressed depth, clarity, and accuracy; inter-rater reliability was calculated. Free-text comments were analyzed to identify safety-critical omissions and practical improvements.
RESULTS: Overall answer quality was considered clinically appropriate, with good inter-rater agreement. Performance was strongest in complication management, where responses consistently highlighted clear red-flag signs (e.g., infection, tube dislodgement, and persistent pain) and specified escalation pathways (self-care, 24-48 h contact, urgent evaluation). No unsafe recommendations were identified. Needed refinements included frailty-aware tailoring and more stepwise, caregiver-oriented instructions.
CONCLUSIONS: A geriatric-focused LLM chatbot can deliver clinically useful, understandable PEG aftercare guidance aligned with expert expectations, particularly for recognizing complications and directing timely care. This clinician-informed evaluation assessed expert perceptions of chatbot responses; patient or caregiver usability and comprehension were not examined in this phase. Integrating such tools into discharge education may enhance safety and caregiver confidence. Prospective usability and effectiveness studies in older adults and caregivers are warranted.
METHODS: A multidisciplinary panel (geriatrics, nursing, surgery) independently rated chatbot responses to a curated set of common PEG aftercare questions spanning education, routine care, troubleshooting, and complications. Ratings addressed depth, clarity, and accuracy; inter-rater reliability was calculated. Free-text comments were analyzed to identify safety-critical omissions and practical improvements.
RESULTS: Overall answer quality was considered clinically appropriate, with good inter-rater agreement. Performance was strongest in complication management, where responses consistently highlighted clear red-flag signs (e.g., infection, tube dislodgement, and persistent pain) and specified escalation pathways (self-care, 24-48 h contact, urgent evaluation). No unsafe recommendations were identified. Needed refinements included frailty-aware tailoring and more stepwise, caregiver-oriented instructions.
CONCLUSIONS: A geriatric-focused LLM chatbot can deliver clinically useful, understandable PEG aftercare guidance aligned with expert expectations, particularly for recognizing complications and directing timely care. This clinician-informed evaluation assessed expert perceptions of chatbot responses; patient or caregiver usability and comprehension were not examined in this phase. Integrating such tools into discharge education may enhance safety and caregiver confidence. Prospective usability and effectiveness studies in older adults and caregivers are warranted.