Artificial Intelligence in In Vitro Fertilisation: Clinical Evidence, Market Trajectory, Regulation and Bioethics, with Foresight to 2031

Research monograph (working paper, not peer reviewed), 58 pages, 52 references. Background. Around one in six people experience infertility, more than three million IVF cycles are reported annually and an estimated 13 to 17 million children have been born through IVF. Artificial intelligence (AI) is now applied along the entire IVF pathway while its clinical benefit remains contested. Aim. To provide an integrated, critical assessment of AI in IVF as of late 2026 across clinical evidence, market development, regulation and ethics, and to derive scenario-based predictions and recommendations. Methods. Structured narrative review, documentary analysis of EU, Swiss, UK and US regulation, secondary analysis of market data, normative ethical analysis and scenario analysis. Results. AI embryo assessment is roughly ten times faster than manual assessment, but the largest randomised trial (n = 1,066) did not demonstrate noninferiority on clinical pregnancy (46.5% vs 48.2%), and time-lapse imaging did not improve live birth in a trial of more than 1,500 patients. The AI embryo selection market is estimated at USD 320 million in 2025, growing about 18.5% annually. Under the EU AI Act most clinical IVF AI is high-risk. Polygenic embryo screening is considered not ready for clinical practice by the ASRM. Conclusions. The study proposes the cohort constraint as an explanatory principle, a four-question governance framework for clinics, ten falsifiable predictions to 2031 and a research agenda. AI should inform and accelerate; accountable humans should decide. Use of AI: an AI language model assisted with literature synthesis, structuring and language editing; the author verified all sources and takes full responsibility.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-20
DOI
https://doi.org/10.5281/zenodo.24382099
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Artificial Intelligence in In Vitro Fertilisation: Clinical Evidence, Market Trajectory, Regulation and Bioethics, with Foresight to 2031

Nathaniel Jonathan Berky
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Healthcare and Education
article

Artificial Intelligence in In Vitro Fertilisation: Clinical Evidence, Market Trajectory, Regulation and Bioethics, with Foresight to 2031

Nathaniel Jonathan Berky
article en

Abstract

Research monograph (working paper, not peer reviewed), 58 pages, 52 references. Background. Around one in six people experience infertility, more than three million IVF cycles are reported annually and an estimated 13 to 17 million children have been born through IVF. Artificial intelligence (AI) is now applied along the entire IVF pathway while its clinical benefit remains contested. Aim. To provide an integrated, critical assessment of AI in IVF as of late 2026 across clinical evidence, market development, regulation and ethics, and to derive scenario-based predictions and recommendations. Methods. Structured narrative review, documentary analysis of EU, Swiss, UK and US regulation, secondary analysis of market data, normative ethical analysis and scenario analysis. Results. AI embryo assessment is roughly ten times faster than manual assessment, but the largest randomised trial (n = 1,066) did not demonstrate noninferiority on clinical pregnancy (46.5% vs 48.2%), and time-lapse imaging did not improve live birth in a trial of more than 1,500 patients. The AI embryo selection market is estimated at USD 320 million in 2025, growing about 18.5% annually. Under the EU AI Act most clinical IVF AI is high-risk. Polygenic embryo screening is considered not ready for clinical practice by the ASRM. Conclusions. The study proposes the cohort constraint as an explanatory principle, a four-question governance framework for clinics, ten falsifiable predictions to 2031 and a research agenda. AI should inform and accelerate; accountable humans should decide. Use of AI: an AI language model assisted with literature synthesis, structuring and language editing; the author verified all sources and takes full responsibility.

Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon