The AI is not registered as an intervention — watching embryos in 30-second video
An observational study recording embryos of patients undergoing in vitro fertilization in 30-second video, analysing the movement with AI and setting it against pregnancy outcomes. In this registration the AI is not an intervention.
Trial overview (primary data)
- StatusEnrolling by invitation
- ConditionsInfertility Assisted Reproductive Technology, Infertility (IVF Patients)
- SponsorViable Biosciences
- Target enrollment1,000 participants
- Period2026-03-05 〜 2029-03-30
Key points
- An observational study recording embryos in 30-second video to evaluate whether real-time embryo activity can correlate with known outcomes.
- Embryo grading at present rests on direct observation under the microscope, using symmetry, developmental stage and growth pattern.
- Participating patients obtain no benefit from the recording and continue treatment as their provider decides.
- Those included are undergoing assisted reproductive technologies including in vitro fertilization, intracytoplasmic sperm injection and frozen-thawed embryo transfer.
- The target enrolment is 1,000, the sponsor Viable Biosciences, with completion expected 30 March 2029.
1Which box on the register the AI is put in
A clinical trial registration carries a field for the kind of intervention: drug, device, diagnostic test, procedure, radiation, behavioural, or other. This series follows eight registrations to show that the same AI, placed in a different box, is judged within a different framework.
2The first box is no intervention at all
Here the intervention field is empty. Patients receive their treatment as usual and embryos are selected by standard practice. The AI sits on the analysis side, working on video after the fact, outside the course of treatment. The AI is used, and the AI is not an intervention.
3What is being tested
That participants gain nothing from it is stated outright, which says much about the character of an observational study. Treatment is unchanged and the data gathered serves to generate hypotheses. The registration says a prospective study may be designed from it later.
4What the box settles
In the box marked no intervention, no phase is assigned. The framework for testing efficacy simply does not apply. Across these records, only 32 of 776 registrations (4.1%) carry a phase at all. The next article takes up an AI registered as a diagnostic test.
Why it matters
A trial registration carries a field for the kind of intervention, and what goes in it settles which framework of assessment applies. Where an AI works on data after the fact rather than within the course of treatment, that field stays empty and no phase is assigned. The same technology being handled differently according to the form of its registration is a premise for reading the register at all.
FAQ
Why is the AI not registered as an intervention?
What are embryo morphokinetics?
Do participants benefit?
Sources (primary)
Source: ClinicalTrials.gov (U.S. NIH/NLM, public domain). This site does not provide medical advice. Verify the latest and exact details with the official source. This site is not endorsed or certified by the NIH/NLM.
- ClinicalTrials.gov (study record, original)
- NCT ID: NCT07611448