RESULTS: The oocyte AI model demonstrated area under the curve (AUC) up to 0.65 on two blind test datasets. High sensitivity for predicting competent oocytes (83-88%) was offset by lower specificity (26-36%). Exclusion of confounding biological variables (male factor infertility and maternal age ≥35 years) improved AUC up to 14%, primarily due to increased specificity. AI score correlated with size of the zona pellucida and perivitelline space, and ooplasm appearance. AI score also correlated with blastocyst expansion grade and morphological quality. The sum of AI scores from oocytes in group culture images predicted the formation of two or more usable blastocysts (AUC 0.77).
CONCLUSION: An AI model to evaluate oocyte competence was developed using federated learning, representing an essential step in protecting patient data. The AI model was significantly predictive of oocyte competence, as defined by usable blastocyst formation, which is a critical factor for IVF success. Potential clinical utility ranges from selective oocyte fertilization to guiding treatment decisions regarding additional rounds of oocyte retrieval.
DESIGN: In total, 10,677 oocyte images with associated metadata were collected prospectively by eight IVF clinics across six countries. AI training used federated learning, where data were retained on regional servers to comply with data privacy laws. The final AI model required a single image as input to evaluate oocyte competence, which was defined by the formation of a usable blastocyst (≥expansion grade 3 by day 5 or 6 post ICSI).
AIM OF THE STUDY: This study was aimed to reveal three different PBs' aqueous extracts(viz. PB-A, PB-B, PB-C) chemical constituent's profile using GC-MS analysis, anticancer property on A375, HeLa and MCF7 cancer cells, toxicity profile on zebrafish embryo morphology, EC50, LC50 and teratogenicity index.
MATERIALS AND METHODS: PBs' extracts characterization was performed through GC-MS analysis, in vitro anticancer effect was carried out on A375, HeLa and MCF7 cancer cell lines and finally and toxicity properties on three different PBs aqueous extracts (viz. PB-A, PB-B, PB-C) were determined using zebrafish embryo model.
RESULTS: The GC-MS analysis revealed 10 similar compounds in all PBs' extracts. Dilauryl thiodipropionate was found to be a major compound in all PBs' extracts followed by tetradecanoic acid. An in vitro anticancer study revealed PB extracts exerted median inhibition concentration (IC50) <50 μg/mL, on cancer cells viz. A375, HeLa and MCF7 with no significant toxicity on normal cells viz. NHDF cells. In vivo toxicity of PBs extracts found affecting tail detachment, hatching, craniofacial, brain morphology, soft tissues, edema, spinal, somites, notochord and cardiovascular system (brachycardia, disruption of blood circulation) deformities. The LC50 and EC50 demonstrated PB extracts effect as dose and time dependent with median concentration <150.0 μg/mL. Additionally, teratogenicity index (TI) viz. >1.0 revealed teratogenic property for PB extracts.
CONCLUSIONS: The findings revealed that all three PBs aqueous extracts possessed anticancer activity and exhibited significant toxicological effects on zebrafish embryos with high teratogenicity index. Hence, its use as an anticancer agent requires further investigation and medical attentions to determine its safe dose.