What does this research mean for the field?

A retrieval-augmented ChatGPT model trained on specialized medical society materials generates high-quality and highly usable educational responses for patient urogynecology queries. Novelty: ClaimNovelty.CONFIRMATORY. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Evaluate whether a retrieval-augmented artificial intelligence chatbot grounded in expert clinical resources provides high-quality and usable responses to patient-representative urogynecology questions.

August 22, 2026International Urogynecology JournalOpen Access

Improving Pelvic Floor Disorder Education: A Second Pilot of a Retrieval-Augmented AI Chatbot Model

View Full Paper

Ask AI

Bookmark

Authors

MMMadeline K. Moureau BDBerkley Davis CHChristopher X. Hong

Discussion

Member takes

Overview

Pilot evaluation demonstrates high response quality and usability for an evidence-grounded AI chatbot in urogynecology, suggesting its potential to support patient education.

Key Points

Evaluate whether a retrieval-augmented artificial intelligence chatbot grounded in expert clinical resources provides high-quality and usable responses to patient-representative urogynecology questions.
Developed a retrieval-augmented ChatGPT model using American Urogynecologic Society (AUGS) patient education materials.
Recruited urogynecology specialists to submit 22 patient-representative clinical queries (evaluated by 11 complete respondents).
Assessed chatbot performance using the Quality Analysis of Medical Artificial Intelligence (QAMAI) tool and the System Usability Scale (SUS), alongside thematic qualitative feedback.
The retrieval-augmented model achieved a median QAMAI quality score of 28 (IQR 24–29.8) and a mean SUS usability score of 81.8 ± 11.2.
Specialists identified patient-friendly language, high usability, and direct AUGS link integration as core strengths, while citing clinical depth, comprehensiveness, and citation consistency as areas needing improvement.

Cite This Study

Moureau et al. (2026) studied this question.

synapsesocial.com/papers/6a895f62ca7ade938187dff0 https://doi.org/10.1007/s00192-026-06834-x

View Full Paper

Ask AI

Bookmark

August 22, 2026International Urogynecology JournalOpen Access

Improving Pelvic Floor Disorder Education: A Second Pilot of a Retrieval-Augmented AI Chatbot Model

View Full Paper

Ask AI

Bookmark

Authors

MMMadeline K. Moureau BDBerkley Davis CHChristopher X. Hong

Discussion

Member takes

Overview

Pilot evaluation demonstrates high response quality and usability for an evidence-grounded AI chatbot in urogynecology, suggesting its potential to support patient education.

Key Points

Evaluate whether a retrieval-augmented artificial intelligence chatbot grounded in expert clinical resources provides high-quality and usable responses to patient-representative urogynecology questions.
Developed a retrieval-augmented ChatGPT model using American Urogynecologic Society (AUGS) patient education materials.
Recruited urogynecology specialists to submit 22 patient-representative clinical queries (evaluated by 11 complete respondents).
Assessed chatbot performance using the Quality Analysis of Medical Artificial Intelligence (QAMAI) tool and the System Usability Scale (SUS), alongside thematic qualitative feedback.
The retrieval-augmented model achieved a median QAMAI quality score of 28 (IQR 24–29.8) and a mean SUS usability score of 81.8 ± 11.2.
Specialists identified patient-friendly language, high usability, and direct AUGS link integration as core strengths, while citing clinical depth, comprehensiveness, and citation consistency as areas needing improvement.

Cite This Study

Moureau et al. (2026) studied this question.

synapsesocial.com/papers/6a895f62ca7ade938187dff0 https://doi.org/10.1007/s00192-026-06834-x

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark