MétaCan
Menu
Back to cohort
Record W4411750364 · doi:10.1093/humrep/deaf097.459

P-150 Differential contributions of sperm and oocyte to fertilization and embryo development: Insights from a recent AI-driven study

2025· article· en· W4411750364 on OpenAlexaboutno aff
L. Carrión, Fernando Meseguer, Lucía Murria, Lucía Alegre, T Carrión, Carla Giménez, M Meseguer

Bibliographic record

VenueHuman Reproduction · 2025
Typearticle
Languageen
FieldDecision Sciences
TopicImpact of AI and Big Data on Business and Society
Canadian institutionsnot available
Fundersnot available
KeywordsHuman fertilizationOocyteAndrologySpermEmbryoEmbryogenesisBiologyMedicineCell biologyGenetics

Abstract

fetched live from OpenAlex

Abstract Study question Do sperm and oocytes have equivalent roles in fertilization and embryo development, according to Artificial Intelligence algorithms? Summary answer Female gamete plays a more significant role in the fertilization process than sperm; but differential effect on the formation of the blastocyst remains unclear. What is known already The contributions of the oocyte and sperm to fertilization and embryo development are distinct yet complementary, influencing early embryogenesis through their unique genetic and cytoplasmic components. Recent advancements in AI have enabled real-time assessment of gamete quality, providing unprecedented insights into their roles. AI-driven algorithms analyze key parameters such as sperm motility, sperm morphology or oocyte morphology, with unparalleled precision, allowing for the identification of subtle patterns associated with successful fertilization and optimal embryo development. This integration of AI-technology into reproductive medicine offers a transformative approach to improve outcomes in assisted reproduction. Study design, size, duration Single-centre, non-interventional and blind study including 165 ICSI procedures. Real-time semen analysis was performed using SiDTM v2.0 (IVF2.0, Ltd, Mexico), providing categorical and numerical individual scores. Oocytes were retrospectively assessed by Magenta IVF R3.0 (FutureFertility, Canada), giving also a numerical score to each one. Oocyte-sperm pairs were individually followed up to assess fertilisation status, blastocyst formation, and embryo quality according to ASEBIR criteria and embryo scoring AI-algorithms, over a period of ten months. Participants/materials, setting, methods 1023 oocyte-sperm pairs were studied. ICSI procedures were recorded using a digitizer attached to an optical microscope. Numerical SiD scores ranged from 0 to 700, with lower scores indicating better quality. Oocytes’ images were retrospectively taken from time-lapse incubators (0h after microinjection). Two groups were formed based on whether the microinjected sperm score was below or above 100. Additionally, two more groups were created based on the average oocyte score (<5 or > 5). Main results and the role of chance Outcomes in patients with poor oocyte quality shown slightly higher fertilization (FR) and blastocyst rates (BR) per MII, in oocytes microinjected with good-quality sperm (SiD score<100) compared to poor-quality sperm (SiD score>100) (FR = 73.33% vs 69.83%; BR = 46.67% vs 41.32%); whereas usable blastocyst rates (UBR) were similar (33.33% vs 33.47%). Embryo quality evaluated using ASEBIR criteria and AI-based scoring, showed modestly better results with the microinjection of good-quality sperm [top-quality embryos(A+B)=60.71% vs 47.00%; KIDScore = 5.27 vs 4.92; IDAScore = 5.13 vs 4.65; Embryoaid = 5.22 vs 4.92]. However, these differences were not statistically significant (p > 0.05). In patients with good oocyte quality, outcomes were almost identical regardless of sperm quality (SiD score < or > 100) [FR = 84.58% vs 82.73%; BR = 55.60% vs 57.55%; UBR = 43.45% vs 45.08%; top-quality embryos (A+B) = 59.66% vs 62.55%; KIDScore = 4.51 vs 4.96; IDAScore = 4.60 vs 4.77; Embryoaid = 5.46 vs 5.44] (p > 0.05). Differences on FR achieve by good quality sperm (SiD score<100) on poor and good oocyte quality were significantly higher in the last ones (73.33 % vs 84.58%; p < 0.05). BR and UBR were approximately 10% higher in good-quality oocytes, but these differences were not statistically significant (p > 0.05). Limitations, reasons for caution This study relies on AI-based tools, which, while promising, require further validation across larger and more diverse cohorts. SiDTM v2.0 do not assess sperm morphology, which is a key factor for selecting best sperm to microinject. Finally, the sample size and retrospective nature may introduce biases. Wider implications of the findings These findings highlight the critical role of oocyte quality in assisted reproduction outcomes, emphasizing the need to prioritize female gamete assessment to evaluate male factor contribution. Integrating AI tools can refine embryo selection processes and improve success rates. 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)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.822
Threshold uncertainty score0.329

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.075
GPT teacher head0.383
Teacher spread0.307 · 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.

The models applied no category: nothing in the taxonomy fit this work.
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 topicImpact of AI and Big Data on Business and SocietyFrench-language works237,207