发表机构
The University of Sydney; Charles Darwin University; Molly Wardaguga Institute for First Nations Birth Rights（悉尼大学; 查尔斯达尔文大学; 莫莉·沃达古加原住民生育权利研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出NeoTriFuse框架，将缺失值作为可靠性信号动态调整模态贡献，联合优化死亡率与住院时长预测，在新生儿死亡率风险预测任务中取得优异性能。
AI 中文摘要
从床边监测数据预测新生儿死亡率风险仍面临挑战，存在极端类别不平衡、异质性临床风险因素、多尺度时间动态性及大量缺失值等问题。本文提出NeoTriFuse，这是一种针对缺失异质性新生儿监测数据的可靠性感知多模态融合框架。与传统多模态方法将缺失主要视为预处理问题不同，NeoTriFuse将缺失建模为显式可靠性信号，在融合过程中动态调整各模态的贡献。该框架通过可靠性引导门控机制整合静态围产期变量、局部-全局时间编码器及患者层面统计摘要，同时联合优化死亡率预测与辅助住院时长目标。NeoTriFuse取得了具有竞争力的性能，F1分数为0.6736±0.0216，AUROC为0.9454±0.0056。 ablation研究表明，局部-全局时间架构与患者层面摘要分支对预测性能贡献最大，而可靠性感知门控在异质性观测完整性下为阈值依赖指标提供了额外提升。敏感性分析进一步显示，在相近超参数设置下性能稳定。总体而言，研究结果支持可靠性感知多模态融合作为真实临床缺失条件下新生儿死亡率预测的实用方法。
英文摘要
Neonatal mortality risk prediction from bedside monitoring data remains challenging due to extreme class imbalance, heterogeneous clinical risk factors, multi-scale temporal dynamics, and substantial missingness. We propose NeoTriFuse, a reliability-aware multimodal fusion framework for missingness-heterogeneous neonatal monitoring data. Unlike conventional multimodal approaches that treat missingness primarily as a preprocessing issue, NeoTriFuse models missingness as an explicit reliability signal that dynamically modulates modality contributions during fusion. The framework integrates static perinatal variables, local-global temporal encoders, and patient-level statistical summaries through reliability-guided gating mechanisms, while jointly optimizing mortality prediction and an auxiliary length-of-stay objective. NeoTriFuse achieves competitive performance, with an F1 score of 0.6736 +/- 0.0216 and an AUROC of 0.9454 +/- 0.0056. Ablation studies indicate that the local-global temporal architecture and patient-level summary branch contribute most substantially to predictive performance, while reliability-aware gating provides additional improvements on threshold-dependent metrics under heterogeneous observation completeness. Sensitivity analyses further suggest stable performance across nearby hyperparameter settings. Overall, the findings support reliability-aware multimodal fusion as a practical approach for neonatal mortality prediction under realistic clinical missingness conditions.
CommentsICONIP 2026
