Document Type
Article
Publication Date
8-30-2025
Abstract
RESEARCH QUESTION: Can generative artificial intelligence (AI) models provide reliable counselling to fertility patients regarding real-world clinical questions?
DESIGN: In this cross-sectional study, 12 clinical questions were developed to reflect common, real-life dilemmas encountered during fertility workup and treatment. Responses to each question were generated by two experienced fertility specialists, and two AI models - ChatGPT and Gemini. Eight leading internationally recognized fertility experts, blinded to the source of each reply, independently rated all the responses on a scale from 1 (strongly disagree) to 10 (strongly agree). Ratings were compared across all four repliers using non-parametric statistical tests.
RESULTS: The replies authored by physicians received significantly higher overall scores than those generated by AI models (P < 0.001). The median scores were highest for Doctor A (9.0), followed by Doctor B (8.0), then ChatGPT (7.0) and finally Gemini, which received the lowest score (4.5). The proportion of high-scoring responses (≥8) was greatest for Doctor A (70.8%), followed by Doctor B (56.3%), then ChatGPT (47.9%) and finally Gemini (35.4%) (P < 0.001).
CONCLUSIONS: Experienced fertility specialists outperformed generative AI models in providing accurate responses to complex clinical questions. Despite the growing accessibility and sophistication of AI tools, their use for individualized fertility counselling remains limited. Continued refinement and clinical validation of AI tools are essential before they can be considered reliable for patient-specific guidance. At present, AI should be viewed as a complementary resource rather than a substitute for expert clinical judgement.
Recommended Citation
Alcalay, Idan; Weissman, Ariel; Ganer Herman, Hadas; Tsafrir, Avi; Friedman, Matan; Weiner, Eran; Orvieto, Raoul; Polyzos, Nikolaos P.; Dahan, Michael H.; Polyakov, Alex; Fischer, Robert; Esteves, Sandro C.; Ata, Baris; Franasiak, Jason M.; and Mizrachi, Yossi, "Can Artificial Intelligence Models Provide Reliable Medical Counselling to Fertility Patients?" (2025). Department of Obstetrics and Gynecology Faculty Papers. Paper 140.
https://jdc.jefferson.edu/obgynfp/140
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
PubMed ID
41475300
Language
English
Comments
This article is the author’s final published version in Reproductive BioMedicine Online, Volume 52, Issue 2, 2026, Article number 105237.
The published version is available at https://doi.org/105237. Crown Copyright © 2025 Published by Elsevier Ltd on behalf of Reproductive Healthcare Ltd.