ObGyn Intelligence
Evidence Matters
Prepare
Evidence LibraryPregnancy and prenatal testingWhat it delivers
Evidence Library · What it delivers

The three new tests that were actually put to a trial

One was compared against the standard and failed to show it was not worse. One has never been randomised at all. One made scans faster without finding more.

Most of what is sold in this space has never been tested against anything. Three technologies have real comparative data. Here is what it showed.

1. Testing an embryo without touching it. Instead of biopsying cells, the laboratory reads the DNA the embryo has shed into the drop of fluid it was grown in. The largest study collected 1,301 blastocysts across eight IVF centres on four continents.

78.2%
Agreement with the biopsy result
866 of 1,108
12.4%
False positives
Normal embryo called abnormal
8.3%
False negatives
Abnormal embryo called normal

A false positive here can mean a normal embryo is set aside. Roughly one result in eight in that study was a false positive, in the largest and most favourable study of the method.

A smaller study went further and compared each sample against the inner cell mass, the part of the embryo that actually becomes the baby. In 35 donated research embryos, the fluid sample matched the inner cell mass in 14 of 24 comparisons. The standard biopsy did better but not by much: 22 of 32. Those are small numbers and one case moving changes them, which is why they are given as fractions. They make one point clearly: the biopsy everyone treats as the reference is not itself a perfect picture of the baby.

The current systematic review concludes: General concordance rates in comparison with biopsy-based PGT-A are promising, but it is clear that additional research and understanding are needed before adopting noninvasive and minimally invasive PGT-A as a widely used tool with strong clinical utility. No randomised trial has reported whether using it changes anyone's chance of having a baby. Three are registered and recruiting.

2. Artificial intelligence choosing the embryo. This one has a completed randomised trial: 14 IVF clinics in Australia and Europe, 1,066 women, double blind, comparing a deep learning algorithm against an embryologist looking down a microscope.

OutcomeAIEmbryologistDifference (95% confidence interval)
Clinical pregnancy46.5%48.2%1.7 points lower (7.7 lower to 4.3 higher)
Live birth39.8%43.5%3.9 points lower (9.9 lower to 2.2 higher)

The trial's own conclusion: This study was not able to demonstrate noninferiority of deep learning for clinical pregnancy rate when compared to standard morphology and a predefined prioritization scheme.

Be precise about what that means. The trial did not show the software is worse. It failed to show that it is not worse. The interval for live birth still allows a real loss of nearly ten percentage points. Every point estimate favoured the human. The accompanying editorial in the field's own journal: Good blastocyst morphology has again proven itself as a high bar in predicting live birth.

3. Artificial intelligence in the anomaly scan. One randomised trial exists. It is important to say how this guide knows its numbers: the published journal version could not be opened, so every figure below comes from the trial's preprint, which has not been peer reviewed. Treat them as provisional.

The trial randomised 78 pregnancies at a single hospital, deliberately enriched so that 26 of them, about a third, involved congenital heart disease. Scans were much faster with the software, a median of 11.4 minutes against 19.7 minutes, and the sonographers' measured workload was lower. Sensitivity for picking up a malformation was 88.9% with the software and 81.5% without, a difference that was not statistically significant.

The authors' own conclusion claims a time saving and a workload reduction without a reduction in diagnostic performance. That is not a claim that more was found.

Everything else in this area is retrospective. In the largest review of AI for spotting fetal heart problems, 15 studies covering pictures from 30,121 fetuses, 14 of the 15 teams built and tested their own model, only one model was checked by anyone else, the risk of bias was rated moderate to high, and adherence to AI reporting standards was low. No study was found in which AI improved anomaly detection in a real screening population, and none reporting whether it changed anything for a baby.

The pattern worth noticingThree technologies with real comparative data. One was not able to demonstrate that it is no worse than the person it was meant to replace. One has never been randomised. One made the scan faster and did not find more. Every other test in this stage has less evidence than these three, not more.
If a clinic offers you any of these"Has this been compared against standard care in a randomised trial? What did it show?"
"If the answer is agreement rates, agreement with what, and how often is it wrong in each direction?"
"Does faster or easier for the operator mean better for my baby, and how would we know?"
Where this comes from:
597. Rubio C, Navarro-Sanchez L, Garcia-Pascual CM, Ocali O, Cimadomo D, Venier W, et al. Multicenter prospective study of concordance between embryonic cell-free DNA and trophectoderm biopsies from 1301 human blastocysts. Am J Obstet Gynecol. 2020;223(5):751.e1-751.e13.
598. Xu CL, Wei YQ, Tan QY, Huang Y, Wu JJ, Li CY, et al. Concordance of PGT for aneuploidies between blastocyst biopsies and spent blastocyst culture medium. Reprod Biomed Online. 2023;46(3):483-490.
599. Cinnioglu C, Glessner H, Jordan A, Bunshaft S. A systematic review of noninvasive preimplantation genetic testing for aneuploidy. Fertil Steril. 2023;120(2):235-239.
600. Illingworth PJ, Venetis C, Gardner DK, Nelson SM, Berntsen J, Larman MG, et al. Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial. Nat Med. 2024;30(11):3114-3120.
601. Sakkas D. The golden fleece of embryology eludes us once again: a recent RCT using artificial intelligence reveals again that blastocyst morphology remains the standard to beat. Hum Reprod. 2025;40(1):4-8.
602. Day TG, Matthew J, Budd SF, Farruggia A, Venturini L, Wright R, et al. AI to assist in the fetal anomaly ultrasound scan: a randomized controlled trial. NEJM AI. 2025;2(4).
603. Day TG, Matthew J, Budd SF, Farruggia A, Venturini L, Wright R, et al. Artificial intelligence to assist in the screening fetal anomaly ultrasound scan (PROMETHEUS): a randomised controlled trial. medRxiv preprint. 2024.
604. D'Alberti E, Patey O, Smith C, Salovic B, Hernandez-Cruz N, Noble JA, et al. Artificial intelligence-enabled prenatal ultrasound for the detection of fetal cardiac abnormalities: a systematic review and meta-analysis. EClinicalMedicine. 2025;84:103250.

Covered in the essential classes

Continue

More from The newest tests

This page is educational. It supports the conversation with your own clinicians. It is not consent to any treatment, and it cannot assess you. If you are worried about a symptom now, see urgent warning signs.