面向患者知识图谱的反馈鲁棒人工智能
Feedback-Robust AI for Patient Knowledge Graphs
- Roshan AI
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对床旁监测患者知识图谱中反馈混杂问题，提出反馈鲁棒图谱构建方法，通过阴性对照和证据指针减少虚假关系，优于相关性方法。
AI中文摘要：
来自床旁监测的患者知识图谱应对其关系进行类型化，并说明数据是否支持其体征。在麻醉和重症监护中，临床医生根据生理状况调整药物和通气，因此时间关系混合了患者的反应与临床医生的策略。我们引入了ClosedLoopBench：在3,442例VitalDB手术病例（12,653小时）中，包含29种关系，其符号由物理学、药理学或临床实践确定，并带有阴性对照动作流。当每位患者的动作被另一位患者的动作替换时，12个估计器中有6个在未校准的情况下平均将其19-29个不同关系估计中的11-18个声明为显著，而在校准后，互相关和格兰杰检验仍将呼吸机速率→呼气末二氧化碳赋值为临床医生策略的符号。我们提出了反馈鲁棒的患者图谱，将概念节点与证据指针相结合，对阴性对照进行类型化关系准入，以及心跳级耦合。在VitalDB的空流下，我们的图谱每个图谱包含0.06-0.10个虚假的概念级关系实例，而相关性构建为10-12个。对11种缓慢药物和呼吸机反应的患者特定估计对后续数据的预测并不优于群体估计，而脉搏到达时间-收缩压斜率为负，在2,884例中占94.3%，且具有患者特异性（早期-晚期相关性0.67 [0.63, 0.70]）。
英文摘要：
Patient knowledge graphs from bedside monitoring should type their relations and state whether the data support their signs. In anesthesia and intensive care, clinicians titrate drugs and ventilation in response to the physiology, so temporal relations mix the patient's response with the clinician's policy. We introduce ClosedLoopBench: 29 relations with signs fixed by physics, pharmacology or clinical practice, on 3,442 VitalDB surgical cases (12,653 h) with negative-control action streams. When each patient's actions are replaced by another patient's, six of 12 estimators declare on average 11-18 of their 19-29 distinct relation estimates significant without calibration, and after calibration cross-correlation and Granger tests still assign ventilator rate -> end-tidal CO2 the sign of the clinician's policy. We propose feedback-robust patient graphs that combine concept nodes with evidence pointers, typed relations admitted against negative controls, and beat-level couplings. On VitalDB under null streams, our graphs contain 0.06-0.10 false concept-level relation instances per graph, versus 10-12 for correlational construction. Patient-specific estimates of 11 slow drug and ventilator responses predict later data no better than population estimates, whereas the pulse-arrival-time-systolic-pressure slope is negative in 94.3% of 2,884 cases and patient-specific (early-late correlation 0.67 [0.63, 0.70]).
