Objective To establish a flow cytometric assay for detecting heat shock protein A2(HSPA2)in sperm and explore the role of HSPA2 expression levels in predicting low fertilization rates in in vitro fertilization(IVF).Methods The principle of in-direct immunofluorescence(IIF)was used to fluorescently stain sperm HSPA2.After the sperm sample was permeabilized and sealed,rabbit anti-human HSPA2 antibody(primary antibody)and fluorescein isothiocyanate(FITC)labeled goat anti-rabbit IgG antibody(secondary antibody)were sequentially added as detection tubes.At the same time,a sample without primary anti-body was set up as a control tube,and the positive rates of the two tubes were measured by flow cytometer.The ratio of the posi-tive rate of the detection tube to the control tube(positive rate ratio)was calculated.The optimal number of sperm for detection and the optimal working dilutions of primary and secondary antibodies were explored using the chessboard method.Under the optimal conditions,the repeatability,linear range and reference range of the method were evaluated separately,in order to estab-lish a preliminary method for detecting sperm HSPA2 expression levels using flow cytometry.After the establishment of the method,preliminary testing was conducted on a total of 85 sperm samples from couples who underwent IVF at the Reproductive Medicine Center of Jiangmen Central Hospital in 2023.The ratio of HSPA2 positivity rates between the group with IVF success-ful(n=63)and the group with low fertilization rate(n=22)was compared,and the receiver operating characteristic(ROC)curve was used to analyze the threshold.Results The positive rate of HSPA2 in the control tube was relatively low,showing a low background signal,while the fluorescence signal of the detection tube was significantly enhanced,indicating that this method can effectively detect HSPA2.The optimal number of sperm samples for detection determined by the chessboard method was 2×106,and the optimal working dilutions for primary and secondary antibodies were 1∶300 and 1∶400,respectively.Evaluation of repeatability and linear range showed good methodological performance.Comparative analysis between the group with IVF success-ful and the group with low fertilization rate showed that the ratio of sperm HSPA2 positivity rate in the group with low fertilization rate(6.19±4.07)was lower than successful fertilization group(10.69±8.26),the difference was statistically significant(t=2.446,P<0.05).The ROC curve and Youden index showed that the best predictive power was achieved when the cutoffvalue for the ratio of positivity rate was 5.5067,with a sensitivity and a specificity of 71.4%,55.5%,respectively.Conclusion A flow cytometric method for detecting HSPA2 in sperm is successfully established.The expression level of sperm HSPA2 detected by this method suggests its predictive value for low fertilization rate in IVF,providing a basis for future clinical scientific selection of fertilization methods.

Objective To establish a flow cytometric assay for detecting heat shock protein A2(HSPA2)in sperm and explore the role of HSPA2 expression levels in predicting low fertilization rates in in vitro fertilization(IVF).Methods The principle of in-direct immunofluorescence(IIF)was used to fluorescently stain sperm HSPA2.After the sperm sample was permeabilized and sealed,rabbit anti-human HSPA2 antibody(primary antibody)and fluorescein isothiocyanate(FITC)labeled goat anti-rabbit IgG antibody(secondary antibody)were sequentially added as detection tubes.At the same time,a sample without primary anti-body was set up as a control tube,and the positive rates of the two tubes were measured by flow cytometer.The ratio of the posi-tive rate of the detection tube to the control tube(positive rate ratio)was calculated.The optimal number of sperm for detection and the optimal working dilutions of primary and secondary antibodies were explored using the chessboard method.Under the optimal conditions,the repeatability,linear range and reference range of the method were evaluated separately,in order to estab-lish a preliminary method for detecting sperm HSPA2 expression levels using flow cytometry.After the establishment of the method,preliminary testing was conducted on a total of 85 sperm samples from couples who underwent IVF at the Reproductive Medicine Center of Jiangmen Central Hospital in 2023.The ratio of HSPA2 positivity rates between the group with IVF success-ful(n=63)and the group with low fertilization rate(n=22)was compared,and the receiver operating characteristic(ROC)curve was used to analyze the threshold.Results The positive rate of HSPA2 in the control tube was relatively low,showing a low background signal,while the fluorescence signal of the detection tube was significantly enhanced,indicating that this method can effectively detect HSPA2.The optimal number of sperm samples for detection determined by the chessboard method was 2×106,and the optimal working dilutions for primary and secondary antibodies were 1∶300 and 1∶400,respectively.Evaluation of repeatability and linear range showed good methodological performance.Comparative analysis between the group with IVF success-ful and the group with low fertilization rate showed that the ratio of sperm HSPA2 positivity rate in the group with low fertilization rate(6.19±4.07)was lower than successful fertilization group(10.69±8.26),the difference was statistically significant(t=2.446,P<0.05).The ROC curve and Youden index showed that the best predictive power was achieved when the cutoffvalue for the ratio of positivity rate was 5.5067,with a sensitivity and a specificity of 71.4%,55.5%,respectively.Conclusion A flow cytometric method for detecting HSPA2 in sperm is successfully established.The expression level of sperm HSPA2 detected by this method suggests its predictive value for low fertilization rate in IVF,providing a basis for future clinical scientific selection of fertilization methods.

Background::In vitro fertilization (IVF) has emerged as a transformative solution for infertility. However, achieving favorable live-birth outcomes remains challenging. Current clinical IVF practices in IVF involve the collection of heterogeneous embryo data through diverse methods, including static images and temporal videos. However, traditional embryo selection methods, primarily reliant on visual inspection of morphology, exhibit variability and are contingent on the experience of practitioners. Therefore, an automated system that can evaluate heterogeneous embryo data to predict the final outcomes of live births is highly desirable. Methods::We employed artificial intelligence (AI) for embryo morphological grading, blastocyst embryo selection, aneuploidy prediction, and final live-birth outcome prediction. We developed and validated the AI models using multitask learning for embryo morphological assessment, including pronucleus type on day 1 and the number of blastomeres, asymmetry, and fragmentation of blastomeres on day 3, using 19,201 embryo photographs from 8271 patients. A neural network was trained on embryo and clinical metadata to identify good-quality embryos for implantation on day 3 or day 5, and predict live-birth outcomes. Additionally, a 3D convolutional neural network was trained on 418 time-lapse videos of preimplantation genetic testing (PGT)-based ploidy outcomes for the prediction of aneuploidy and consequent live-birth outcomes.Results::These two approaches enabled us to automatically assess the implantation potential. By combining embryo and maternal metrics in an ensemble AI model, we evaluated live-birth outcomes in a prospective cohort that achieved higher accuracy than experienced embryologists (46.1% vs. 30.7% on day 3, 55.0% vs. 40.7% on day 5). Our results demonstrate the potential for AI-based selection of embryos based on characteristics beyond the observational abilities of human clinicians (area under the curve: 0.769, 95% confidence interval: 0.709–0.820). These findings could potentially provide a noninvasive, high-throughput, and low-cost screening tool to facilitate embryo selection and achieve better outcomes. Conclusions::Our study underscores the AI model’s ability to provide interpretable evidence for clinicians in assisted reproduction, highlighting its potential as a noninvasive, efficient, and cost-effective tool for improved embryo selection and enhanced IVF outcomes. The convergence of cutting-edge technology and reproductive medicine has opened new avenues for addressing infertility challenges and optimizing IVF success rates.