Machine learning-enabled prediction of ART pregnancy outcomes: a systematic review and meta-analysis.

AI / informaticsJournal of assisted reproduction and genetics· Aug 2026

Machine learning-enabled prediction of ART pregnancy outcomes: a systematic review and meta-analysis.

Biying Li, Hong Liu, Fan Yu … Li Chen

Read paper

Maternal-Fetal MedicineAI / informaticsQ1IF 2.6

Machine learning models show moderate accuracy predicting pregnancy after assisted reproductive technology.

Machine learning-enabled prediction of ART pregnancy outcomes: a systematic review and meta-analysis.

Biying Li … Li Chen

Journal of assisted reproduction and genetics · Aug 2026 · Q1 in Obstetrics & Gynecology

Purpose

To systematically evaluate the diagnostic accuracy and methodological quality of machine learning (machine learning) prediction models for pregnancy outcomes after assisted reproductive technology (assisted reproductive technology).

Methods

PubMed, Embase, the Cochrane Library, IEEE Xplore, MEDLINE, ClinicalTrials.gov, CNKI, Wanfang, and VIP were searched from inception to July 2026.

n = 11 studies

Results

correctly separates likely from unlikely pregnancy about 10 times more often than by chance

DOR 10.49 (95% CI 6.28 to 17.53)

null 0

6.28

17.53

CI excludes the null - significant

More results

Overall risk of bias was low in 1 study (5.0%), high in 8 studies (40.0%), and unclear in 11 studies (55.0%).

The pooled sensitivity was 0.737 (95% CI, 0.662-0.799) and the pooled specificity was 0.789 (95% CI, 0.709-0.851), with substantial heterogeneity (I 2 = 97.7% and 99.0%, respectively).

More results

Exploratory diagnostic odds ratio subgroup analyses showed comparable performance for clinical pregnancy and live birth.

“

Conclusion · 1 of 2

Machine learning models show moderate diagnostic accuracy for predicting assisted reproductive technology pregnancy outcomes, but the evidence base is limited by substantial heterogeneity and frequent high or unclear risk of bias.

Conclusion · 2 of 2

Future studies should follow TRIPOD + AI and PROBAST-aligned standards, report calibration and clinical utility, and prioritize prospective multi-center external validation before clinical implementation.

Machine learning-enabled prediction of ART pregnancy outcomes: a systematic review and meta-analysis.

Machine learning-enabled prediction of ART pregnancy outcomes: a systematic review and meta-analysis.

Related papers