AI Navigate
インサイト最新記事一覧AI大全

Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework

arXiv cs.LG / 2026/3/24

💬 オピニオンSignals & Early TrendsModels & Research
原文を読む →
共有:

要点

  • Melaguard is a lightweight multimodal ML framework that detects neurovascular instability (NVI) using wearable-compatible signals, combining HRV, peripheral perfusion index, SpO2, and bilateral phase coherence into a single NVI Score.
  • The proposed Transformer-lite model (about 1.2M parameters) targets edge deployment with reported worst-case execution time (WCET) ≤ 4 ms on Cortex-M4, enabling near-real-time screening.
  • Validation is performed across multiple stages and datasets, including a synthetic benchmark (AUC 0.88), a clinical cohort (AUC 0.755, outperforming LSTM/RF/SVM baselines), and additional PPG-related pipelines demonstrating strong cross-modality performance.
  • The work argues that continuous multimodal physiological monitoring can detect pre-structural cerebrovascular dysregulation that single-modality wearables currently miss.
  • The authors provide code for Melaguard to support reproducibility and further research into responsible edge AI for healthcare screening.

Abstract

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

💡 この記事が使われたインサイト

AIの最新ニュースをまとめた「今日の要点」で、この記事が取り上げられています。

📅 3/24Dailyインサイトを見る →

関連おすすめサービス

※当サイトはアフィリエイト広告を利用しています
🎧

Notta搭載AI議事録イヤホン ZENCHORD1

AI時代の仕事術。Notta搭載で会議の議事録を自動生成するスマートイヤホン。

🎙️

AI搭載ボイスレコーダー Plaud

世界100万人が愛用。AIで文字起こし・要約を自動化するボイスレコーダー。

🖼️

画像高画質化AIツール Aiarty Image Enhancer

AIで画像を高画質化。写真・イラストを簡単にアップスケール。