MétaCan
Menu
Back to cohort
Record W4411753619 · doi:10.1093/humrep/deaf097.410

P-101 The dual AI system including 3D-AI showed high performance for predicting implantation

2025· article· en· W4411753619 on OpenAlexaff
Yasunari Miyagi, Roberto Hirata, Toshihiro Habara, Nobuyuki Hayashi

Bibliographic record

VenueHuman Reproduction · 2025
Typearticle
Languageen
FieldHealth Professions
TopicArtificial Intelligence in Healthcare
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsDual (grammatical number)MedicineComputer scienceArt

Abstract

fetched live from OpenAlex

Abstract Study question Is the dual AI system for predicting implantation success using 3D reconstructed blastocyst images superior to the current reported AI? Summary answer The dual AI system for predicting implantation success using the reconstructed 3D images showed a good performance to date. What is known already The AUC for the implantation prediction by AI using planar images of blastocyst was reported 0.662-0.759. Study design, size, duration This was a retrospective noninterventional study of a total of eleven consecutive tomographic blastocyst images acquired in the time-lapse system (acquired from June 2022 to July 2023). This study provides patients with the option to opt-out with additional information on the clinic’s website. The number of enrolled blastocysts were 977. A total of 10,747 images were obtained. Participants/materials, setting, methods The number of implantation and non-implantation blastocysts were 458 and 519, respectively. A total of eleven tomographic blastocyst images at 10-μm pitch intervals were taken with a time-lapse equipment and their backgrounds were eliminated by the first AI. Then both the reconstructed 3D image and the conventional embryo evaluation (CEE) parameters, such as female age, avoiding multicollinearity were input to the second AI with an original 3D convolutional neural network architecture. Main results and the role of chance The value of the AUC by the best dual AI system were 0.791, 0.775, 0.720, 0.752, 0.744 and 0.749 for AUC, sensitivity, specificity, predictive value of positive test, predictive value of negative test, and accuracy, respectively. Limitations, reasons for caution A time-lapse equipment with a slice imaging function is necessary. It is expected that the performance will be further improved if the number of slices is more than eleven or the slice pitch is made narrower. Wider implications of the findings The superiority of dual AI in predicting implantation of blastocyst in handling 3D data with CEE information was demonstrated, and the future potential of time-varying 3D data, i.e., 4D-AI research, was anticipated. Trial registration number No

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.148
Threshold uncertainty score0.996

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0050.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.172
GPT teacher head0.481
Teacher spread0.309 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueHuman ReproductionSame topicArtificial Intelligence in HealthcareFrench-language works237,207