JBRA Assisted Reproduction 2025;29(Suppl.2 SBRA 2025):253
29th Annual Congress of the SBRA. São Paulo/SP - Brazil, 2025
doi: 10.5935/1518-0557.20263828
JBRA Assisted Reproduction 2025;29(Suppl.2 SBRA 2025):253
Poster Presentation
29th Annual Congress of the SBRA. São Paulo/SP - Brazil, 2025
doi: 10.5935/1518-0557.20263828
P-241. Unlocking Oocyte Quality and Competence in Poor Ovarian Reserve Through AI, Morphokinetics, and Ploidy Analysis
1 Clínica Hope Reprodução Humana - São Paulo - Brasil,
2 Fertility-FertGroup Medicina Reprodutiva, - São Paulo – Brasil
3 Science For Everymind - São Paulo – SP - Brasil
Objective: There remains ongoing debate about whether women with poor ovarian reserve (POR) also exhibit impaired oocyte quality. The integration of artificial intelligence (AI)-based tools for evaluating oocyte and embryo quality, together with detailed analyses of embryonic morphokinetics and ploidy status, provides novel insights into oocyte quality and competence in assisted reproduction cycles. This study aimed to investigate the impact of poor ovarian reserve on oocyte quality and competence by utilizing AI-derived metrics, detailed morphokinetic parameters, and embryonic ploidy data.
Methods: In this retrospective cohort study, data from ICSI cycles conducted between 2020 and 2024 were collected and categorized into two groups: the control group (CTR; AMH ≥ 1.2 ng/mL and/or AFC ≥ 5) and the poor ovarian reserve group (POR; AMH<1.2 ng/mL and/or AFC<5), comprising 171 and 143 cycles, respectively. Oocyte quality was assessed using the artificial intelligence-based tool, Magenta Score (MS). Embryonic morphokinetics, KIDScore, laboratory outcomes, and ploidy rates were also analyzed. A propensity score matching (PSM) was performed to adjust for female age, using a 1:1 matching ratio, resulting in 143 matched cycles per group. In the matched cohort, a total of 917 oocytes were retrieved in the CTR group and 465 oocytes in the POR group. After oocyte quality assessment by MS, cycles with male factor infertility were excluded to reduce confounding. Comparisons between the CTR and POR groups were carried out in two steps: baseline categorical variables were analyzed using Fisher's exact test or the Chi-square test, while continuous variables were assessed using the Mann-Whitney U test. Oocyte/embryo-related variables were analyzed using generalized linear mixed models (GLMMs). Results are presented as mean±standard error of the mean (SEM). All analyses were performed using R software (version 4.5.1), and a p-value<0.05 was considered statistically significant.
Results: After PSM, a female and male age, gonadotropin total dose and COS type did not differ between group. MS, as an oocyte quality assessment tool, did not differ between groups (CTR: 5.82±0.1 vs 5.83±0.13). Regarding laboratory outcomes, no significant differences were observed between the CTR and POR groups on maturation rate (76.37%±1.84 vs. 75.82%±2.01) fertilization rates (73.13%±2.19 vs. 71.62%±2.42), or blastocyst formation rates (57.28%±2.87 vs. 54.16±3.42). Embryo ploidy was also not affected, with euploid rates per biopsied blastocyst of 31.095%±03.56 vs. 34.73%±05.65, and euploid rates per injected oocyte of 18.32%±2.26 vs. 16.17%±3.35, for the CTR and POR groups, respectively. Except for the synchronized cell division parameter S3, where the POR group showed a longer time (8.68±0.74) compared to the CTR group (6.47±0.40), no significant differences were observed in the timings of tPNf, t2, t3, t4, t5, t6, t7, t8, tm, tB, and tSB, nor in synchronized cell divisions S1 or S2, or cell cycles cc2 and cc3. Embryo quality assessed by KIDScore did not differ between groups (CTR: 4.22±0.12 vs POR: 4.13±0.18)
Conclusion: The results of this study suggest that poor ovarian reserve primarily affects the quantity of oocytes retrieved, with no significant detrimental effects on oocyte quality, as measured by the Magenta Score, laboratory performance rates, embryonic morphokinetic parameters, embryo quality assessed by KIDScore, or euploidy rates. These findings indicate that, although ovarian reserve may limit the number of oocytes available, it does not seem to compromise their competence or the developmental potential of the resulting embryos.