P-101 The dual AI system including 3D-AI showed high performance for predicting implantation
Bibliographic record
Abstract
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.005 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
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".