Course coordinators
Johnny Awwad (Qatar) and Mohammad Aboulghar (Egypt)
Course type
Advanced
Course description
Artificial intelligence (AI) tools are increasingly integrated into IVF laboratories and clinics, yet their clinical value, safety, bias, and regulatory readiness remain variable. This course provides a critical, evidence-based overview of how AI is currently used in reproductive medicine, how to evaluate it properly, and how to implement it responsibly in daily practice. Through expert-led lectures, participants will gain both conceptual understanding and practical insights to safely and effectively integrate AI into clinical and laboratory practice.
Target audience
REI clinicians, embryologists, lab directors, researchers running AI studies, regulators/ethics committee members, and industry scientists.
Educational needs and expected outcomes
A structured needs assessment was conducted using multiple complementary sources. A targeted review of recent literature and regulatory frameworks identified the rapid expansion of AI in ART alongside significant variability in validation quality and limited real-world evidence of clinical benefit. This was complemented by expert consensus among faculty, who highlighted common misconceptions, difficulties in interpreting AI outputs, and gaps in implementation. In addition, clinical practice observations across IVF centres revealed increasing exposure to AI tools without adequate training or standardised evaluation frameworks. Feedback from prior educational activities further confirmed a strong demand for practical, competency-based guidance and clearer understanding of ethical and regulatory considerations. These inputs collectively informed the identification of key educational needs, including critical appraisal of AI tools, clinical translation, domain-specific applications, implementation strategies, and ethical awareness.
The expected educational outcomes target improvements in knowledge, skills, behaviours, and ethical practice, with direct impact on daily clinical and laboratory work. Participants will gain the ability to understand and critically evaluate AI tools, integrate AI outputs into decision-making for stimulation, embryo selection, and endometrial assessment, and assess readiness for implementation within their clinics. The course also aims to foster a more critical and evidence-based attitude toward AI adoption, reducing inappropriate reliance on unvalidated technologies. Ethical competencies, including awareness of bias, transparency, and patient communication, will be strengthened. Overall, this will translate into improved clinical decision-making, more standardised laboratory practices, better team coordination, and safer, more transparent patient care within AI-enabled fertility services.
Programme
Sunday 05 July 2026
09:00 - 17:00
PCC14: MEFS exchange course: Artificial intelligence in reproductive medicine: from evaluation to clinical integration
Sunday 05 July 2026
09:00 - 17:00: PCC14: MEFS exchange course: Artificial intelligence in reproductive medicine: from evaluation to clinical integration:
09:00 - 09:30
AI in reproductive medicine: what is real, what is hype, and what actually changes practice
Cristina Hickman, United Kingdom
09:45 - 10:15
AI for stimulation personalisation: prediction of response and dose optimisation
10:30 - 11:00
Coffee break
Michel Abou Abdallah, Lebanon
Chairperson to be announced
11:00 - 11:30
AI and the endometrium: imaging-based receptivity, “omics” integration, and clinical decision boundaries
Patricia Diaz-Gimeno, Spain
11:45 - 12:15
AI-powered oocyte assessment: From imaging to decision support
Cristina Hickman, United Kingdom
12:30 - 13:30
Lunch break
Yacoub Khalaf, United Kingdom
13:30 - 14:00
AI for embryo selection: morphokinetics and multi-modal scoring
14:15 - 14:45
Beyond the biopsy: harnessing deep learning for non-invasive ploidy prediction
15:00 - 15:30
Coffee break
15:30 - 16:00
Large language models and generative AI in IVF care
16:15 - 16:45
Designing an AI-integrated fertility clinic: implementation realities, staffing, training, and patient pathways