Journal of obstetrics and gynaecology Canada : JOGC = Journal d'obstetrique et gynecologie du Canada : JOGC · 2026
Assessment of the Accuracy and Readability of Artificial Generative Intelligence for Patient Questions on Heavy Menstrual Bleeding.
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.
Carere Olivia, Clarfield Lauren, Murphy M Alix, Shivji Azra, Warshafsky Chelsie, Sermer Corey, Kumar Kinshuk, Murji Ally
Аннотация
OBJECTIVES: To evaluate the quality, patient-centredness, clinician endorsement, and readability of generative artificial intelligence (AI) responses to patient questions about heavy menstrual bleeding (HMB) compared with high-quality patient-facing websites.
METHODS: A cross-sectional study compared responses generated by ChatGPT and Google Gemini to excerpts from the 5 highest-quality HMB patient resources identified through a Google Trends-informed search and the QUality Evaluation Scoring Tool (QUEST). Five layperson-style questions representing HMB subtopics (definition, causes, investigations, management, and safety) were submitted to each model. Responses were de-identified and independently evaluated by 5 gynecologists, blinded to source, using 5-point Likert scales for accuracy/comprehensiveness (quality), empathetic and validating communication style (patient-centredness), and expert comfort with patient use of the resource to guide understanding (clinician endorsement). Readability was assessed using the Flesch-Kincaid Grade Level. Inter-rater reliability was measured using intraclass correlation coefficients.
RESULTS: Thirty-six responses were reviewed (16 AI-generated and 20 web-based). Compared with web-based excerpts, AI responses showed similar quality (3.94/5 ± 0.70 vs. 3.53/5 ± 1.21; P = 0.21), lower patient-centredness (2.81/5 ± 0.82 vs. 3.52/5 ± 1.13; P = 0.04), and comparable clinician endorsement (3.56/5 ± 0.92 vs. 3.44/5 ± 1.35; P = 0.52). Without impacting content quality, AI responses were written at a lower grade level (7.6 ± 2.4) than web-based excerpts (11.1 ± 5.2; P = 0.042). Inter-rater reliability was high (intraclass correlation coefficient = 0.82-0.84).
CONCLUSIONS: Compared with high-quality web-based resources, AI-generated responses to HMB questions were more inclusive for varying health literacy levels, comparable in quality and clinician endorsement, but performed worse in patient-centredness. In an evolving digital landscape for health information acquisition, AI-generated responses represent a valuable and safe supplementary or first-line resource for patients.
METHODS: A cross-sectional study compared responses generated by ChatGPT and Google Gemini to excerpts from the 5 highest-quality HMB patient resources identified through a Google Trends-informed search and the QUality Evaluation Scoring Tool (QUEST). Five layperson-style questions representing HMB subtopics (definition, causes, investigations, management, and safety) were submitted to each model. Responses were de-identified and independently evaluated by 5 gynecologists, blinded to source, using 5-point Likert scales for accuracy/comprehensiveness (quality), empathetic and validating communication style (patient-centredness), and expert comfort with patient use of the resource to guide understanding (clinician endorsement). Readability was assessed using the Flesch-Kincaid Grade Level. Inter-rater reliability was measured using intraclass correlation coefficients.
RESULTS: Thirty-six responses were reviewed (16 AI-generated and 20 web-based). Compared with web-based excerpts, AI responses showed similar quality (3.94/5 ± 0.70 vs. 3.53/5 ± 1.21; P = 0.21), lower patient-centredness (2.81/5 ± 0.82 vs. 3.52/5 ± 1.13; P = 0.04), and comparable clinician endorsement (3.56/5 ± 0.92 vs. 3.44/5 ± 1.35; P = 0.52). Without impacting content quality, AI responses were written at a lower grade level (7.6 ± 2.4) than web-based excerpts (11.1 ± 5.2; P = 0.042). Inter-rater reliability was high (intraclass correlation coefficient = 0.82-0.84).
CONCLUSIONS: Compared with high-quality web-based resources, AI-generated responses to HMB questions were more inclusive for varying health literacy levels, comparable in quality and clinician endorsement, but performed worse in patient-centredness. In an evolving digital landscape for health information acquisition, AI-generated responses represent a valuable and safe supplementary or first-line resource for patients.