更新版深度学习胚胎选择模型在妊娠预测性能上的提升:一项回顾性独立验证研究
该回顾性研究分析了3960个单囊胚冻融移植周期,比较iDAScore v2.0(训练数据较v1.0增加15%)、v1.0与Gardner评分对持续妊娠的预测性能。全队列中iDA-V2的AUC为0.736,显著高于iDA-V1的0.720和Gardner评分的0.702(P<0.0001)。结论认为增加训练数据量可提升深度学习模型的妊娠预测性能。
要点
- 全队列中iDA-V2的AUC为0.736,显著高于iDA-V1的0.720和Gardner评分的0.702(P<0.0001)。
- 年龄>35岁组iDA-V2的AUC为0.718,显著高于Gardner评分的0.694(P=0.015)。
- 年龄35-37岁组iDA-V2的AUC为0.712,显著高于iDA-V1的0.696(P=0.035)。
核心结论
- 增加训练数据量可提升深度学习模型对单囊胚冻融移植后持续妊娠的预测性能。
研究设计与样本
- 回顾性分析3960个单囊胚冻融移植周期,胚胎按美国辅助生殖技术学会年龄组分层。
- 胚胎分别由iDAScore v1.0、iDAScore v2.0(训练数据较v1.0增加15%)和Gardner评分进行评分。
- 采用受试者工作特征曲线下面积(AUC)在各母亲年龄组中比较各评分模型的妊娠预测判别性能。
主要发现
- 全队列中iDA-V2、iDA-V1和Gardner评分的AUC分别为0.736、0.720和0.702,iDA-V2显著高于iDA-V1和Gardner评分(P<0.0001)。
- 年龄>35岁组(n=757)中iDA-V2的AUC为0.718,显著高于Gardner评分的0.694(P=0.015)。
- 年龄35-37岁组(n=821)中iDA-V2的AUC为0.712,显著高于iDA-V1的0.696(P=0.035)。
- 年龄41-42岁组(n=715)中iDA-V2的AUC为0.745,显著高于Gardner评分的0.696(P=0.007)。
- 年龄>42岁组(n=660)和年龄38-40岁组(n=1007)中,各评分模型间未发现显著差异。
关键数值与推荐
- 全队列中iDA-V2的AUC为0.736,iDA-V1为0.720,Gardner评分为0.702(P<0.0001)。
- 年龄>35岁组中iDA-V2的AUC为0.718,Gardner评分为0.694(P=0.015)。
- 年龄35-37岁组中iDA-V2的AUC为0.712,iDA-V1为0.696(P=0.035)。
- 年龄41-42岁组中iDA-V2的AUC为0.745,Gardner评分为0.696(P=0.007)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
RESEARCH QUESTION: What is the effect of increasing training data on the performance of ongoing pregnancy prediction after single vitrified-warmed blastocyst transfer (SVBT) in a deep-learning model? DESIGN: A total of 3960 SVBT cycles were retrospectively analysed. Embryos were stratified according to the Society for Assisted Reproductive Technology age groups. Embryos were scored by deep-learning models iDAScore v1.0 (IDA-V1) and iDAScore v2.0 (IDA-V2) (15% more training data than v1.0) and by Gardner grading. The discriminative performance of the pregnancy prediction for each embryo scoring model was compared using the area under the curve (AUC) of the receiver operating characteristic curve for each maternal age group. RESULTS: The AUC of iDA-V2, iDA-V1 and Gardener grading in all cohort were 0.736, 0.720 and 0.702, respectively. iDA-V2 was significantly higher than iDA-V1 and Gardener grading (P < 0.0001). Group > 35 years (n = 757): the AUC of iDA-V2 was significantly higher than Gardener grading (0.718 versus 0.694, P = 0.015); group aged 35-37 years (n = 821), the AUC of iDA-V2 was significantly higher than iDA-V1 (0.712 versus 0.696, P = 0.035); group aged 41-42 years (n = 715, the AUC of iDA-V2 was significantly higher than Gardener grading (0.745 versus 0.696, P = 0.007); group > 42 years (n = 660) and group aged 38-40 years (n = 1007), no significant differences were found between the groups. CONCLUSION: The performance of deep learning models for pregnancy prediction will be improved by increasing the size of the training data.
引用
- Ueno S, Berntsen J, Okimura T, et al. Improved pregnancy prediction performance in an updated deep-learning embryo selection model: a retrospective independent validation study. Reprod Biomed Online. 2023. PMID: 37914559. doi:10.1016/j.rbmo.2023.103308
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。