用可穿戴设备信号提前预警脑血管失稳，防中风于未然
Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework
- 融合心率变异性等多模态信号，用轻量模型生成脑血管失稳评分
- 在临床数据上达AUC 0.755，优于传统模型，且检测灵敏度高
- 适合长期居家监测，为社区早期筛查提供可靠工具
我们提出Melaguard，一种轻量级多模态机器学习框架（Transformer-lite，120万参数，4头自注意力），用于从可穿戴设备兼容的生理信号中提前检测神经血管失稳（NVI），在结构性中风发生前预警。该模型融合心率变异性（HRV）、外周灌注指数、SpO2及双侧相位同步性，生成综合NVI评分，支持边缘计算推理（最坏情况执行时间≤4毫秒，基于Cortex-M4）。NVI是中风前脑血管自主调节功能紊乱的早期表现，现有单模态可穿戴设备无法检测。每年全球有1220万例新发中风，持续多模态监测为社区级筛查提供了可行路径。三阶段独立验证：(1) 合成基准（n=10,000），AUC=0.88 [0.83–0.92]；(2) 临床队列PhysioNet CVES（n=172；84例中风，88例对照），Transformer-lite达AUC=0.755 [0.630–0.778]，优于LSTM（0.643）、随机森林（0.665）、SVM（0.472）；HRV-SDNN可显著区分中风患者（p=0.011）；(3) PPG管道PhysioNet BIDMC（n=53），脉搏率相关系数r=0.748，HRV代理指标r=0.690，与ECG金标准高度一致。跨模态验证显示，PPG形态学在识别脑血管疾病上达AUC=0.923 [0.869–0.968]。多模态融合始终优于单模态基线。代码已开源。
原文摘要 · Abstract (English)
We propose Melaguard, a multimodal ML framework (Transformer-lite, 1.2M parameters, 4-head self-attention) for detecting neurovascular instability (NVI) from wearable-compatible physiological signals prior to structural stroke pathology. The model fuses heart rate variability (HRV), peripheral perfusion index, SpO2, and bilateral phase coherence into a composite NVI Score, designed for edge inference (WCET <=4 ms on Cortex-M4). NVI - the pre-structural dysregulation of cerebrovascular autoregulation preceding overt stroke - remains undetectable by existing single-modality wearables. With 12.2 million incident strokes annually, continuous multimodal physiological monitoring offers a practical path to community-scale screening. Three-stage independent validation: (1) synthetic benchmark (n=10,000), AUC=0.88 [0.83-0.92]; (2) clinical cohort PhysioNet CVES (n=172; 84 stroke, 88 control) - Transformer-lite achieves AUC=0.755 [0.630-0.778], outperforming LSTM (0.643), Random Forest (0.665), SVM (0.472); HRV-SDNN discriminates stroke (p=0.011); (3) PPG pipeline PhysioNet BIDMC (n=53) -- pulse rate r=0.748 and HRV surrogate r=0.690 vs. ECG ground truth. Cross-modality validation on PPG-BP (n=219) confirms PPG morphology classifies cerebrovascular disease at AUC=0.923 [0.869-0.968]. Multimodal fusion consistently outperforms single-modality baselines. Code: https://github.com/ClevixLab/Melaguard
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。