发表机构
Superior University Lahore（拉合尔卓越大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对跨队列哮喘风险预测中模型校准不佳的问题，提出校准优先的多模态时序框架CALIBRA，通过可靠性门控和分层校准提升可迁移性，在半合成基准上验证了有效性。
AI 中文摘要
当患者群体、传感器生态系统和可用模态在不同队列间发生变化时，哮喘恶化预测必须保持可靠。现有模型通常优化队列内的判别性能，可能在迁移后产生校准不良的概率。我们提出CALIBRA，一个校准优先的多模态时序框架，用于处理数据不完整的短期风险预测。专用的循环编码器处理环境、肺部、症状、药物、可穿戴和上下文数据流；可靠性条件门控抑制过时或缺失的模态，而梯度反转训练减少可避免的队列特征。基于收缩的分层逻辑层使用患者不相交的目标子集校准概率，分裂共形预测提供可弃权（不执行）的预测集。为避免捏造临床证据，我们在一个有据可查的三队列半合成基准上评估完整实现，该基准具有受控分布偏移、信息性缺失和密封的目标患者。在五个配置的种子下，CALIBRA的平均目标测试AUPRC为0.224，而最强的非消融比较器TemporalTransformer为0.240；平均AUROC为0.717，Brier分数为0.098。实验还评估了完整模态失败、校准、共形覆盖率、决策曲线、子组行为、消融、运行时间和参数数量。结果验证了在受控偏移下的方法和可复现流程，但未确立临床有效性。在协调的真实哮喘数据上进行外部验证。总体而言，该工件为谨慎治理的真实队列验证提供了证据。
英文摘要
Asthma deterioration forecasting must remain reli- able when patient populations, sensor ecosystems, and available modalities change across cohorts. Existing models commonly optimize within-cohort discrimination and may produce poorly calibrated probabilities after transfer. We present CALIBRA, a calibration-first multimodal temporal framework for short- horizon risk prediction with incomplete data. Dedicated recurrent encoders process environmental, pulmonary, symptom, medication, wearable, and context streams; a reliability-conditioned gate suppresses stale or absent modalities, while gradient-reversal training discourages avoidable cohort signatures. A shrinkage- based hierarchical logistic layer calibrates probabilities using a patient-disjoint target subset, and split conformal prediction provides abstention-capable prediction sets. To avoid fabricating clinical evidence, we evaluate the complete implementation on a documented three-cohort semi-synthetic benchmark with controlled distribution shift, informative missingness, and sealed target patients. Across five configured seeds, CALIBRA achieved mean target-test AUPRC 0.224 versus 0.240 for the strongest non-ablation comparator, TemporalTransformer; mean AUROC was 0.717, and Brier score was 0.098. Experiments additionally assess complete-modality failures, calibration, conformal coverage, decision curves, subgroup behavior, ablations, runtime, and parameter count. The results verify the method and reproducible pipeline under controlled shift, but do not establish clinical effectiveness. External validation on harmonized real asthma. Overall this artifact provides evidence for carefully governed real-cohort validation.
