AI 中文总结
本研究提出GRU-D-Static框架，结合汇总级科学知识与软标签微调，提升了代表性不足人群的母婴结局预测性能，减少了对大规模数据的依赖。
AI 中文摘要
将汇总级别的科学知识整合到神经网络模型中，提供了一种实用策略，可将在样本充足的源队列上训练的预测模型迁移到代表性不足的目标人群，目标域中的个体水平数据通常有限或不可用。本研究提出了结合外部汇总级科学知识的迁移预测策略，并在PRISMA母婴健康研究中说明其应用，在源数据上训练神经网络模型以预测目标队列的不良结局。此外，我们还通过整合静态特征嵌入和注意力权重扩展了现有GRU-D框架，以联合利用时间和静态信息来改进预测。我们的方法采用源自描述目标人群的汇总级统计数据的软标签，对最初在源人群上训练的GRU-D-Static模型进行微调。我们评估了6项母婴结局，包括死产、早产、低出生体重、弱小新生儿、新生儿死亡和产妇近危。在所有测试场景中，仅使用基本协变量的软标签进行微调，与在源样本上训练的深度学习模型相比，预测性能显著提升。此外，当将额外协变量纳入逻辑回归模型，或目标人群的部分输入特征可用于微调时，性能会进一步略有提升。这些发现表明，通过源神经网络模型的迁移预测整合文献中现有的科学知识，可提高代表性不足目标人群的预测性能，减少对大规模数据收集的依赖，并支持全球健康中的风险预测。
英文摘要
Integrating summary-level scientific knowledge into neural network models provides a practical strategy for transferring prediction models trained on adequately sampled source cohorts to underrepresented target populations, where individual-level data in the target domain are often limited or unavailable. In this study, we propose transfer prediction strategies incorporating external summary-level scientific knowledge and illustrate its application on the PRISMA Maternal and Neonatal Health Study, training a neural network model on the source data to predict adverse outcomes in the target cohorts. Besides, we also extend the existing GRU-D framework by incorporating static feature embeddings and attention weights to jointly leverage temporal and static information for improved prediction. Our approach employs soft labels derived from summary-level statistics describing the target population to fine-tune GRU-D-Static models that are initially trained on the source populations. We evaluate six maternal and neonatal outcomes, including stillbirth, preterm birth, low birth weight, small vulnerable newborn, neonatal death, and maternal near miss. Across all tested scenarios, fine-tuning using soft labels from just basic covariates substantially improved predictive performance compared with deep learning models trained on the source sample. Furthermore, the performance slightly improves more when additional covariates were incorporated into the logistic regression model or when partial input features from the target population were available for fine-tuning. These findings demonstrate that integrating existing scientific knowledge in the literature through transfer prediction of source neural network models can enhance prediction performance in underrepresented target populations, reducing reliance on large-scale data collection and supporting risk prediction in global health.
