Scholarlink

<p>Left Ventricular Ejection Time (LVET) is a sensitive indicator of early cardiac dysfunction, yet its routine use in first-line population screening is hindered by the operational and time demands of operator-dependent modalities like echocardiography. In this study, we introduce a scalable, contactless approach using laser Doppler vibrometry (LDV) signals targeted at the suprasternal notch (SSN) to capture hemodynamic events without physical sensor attachment. We demonstrate in a cohort of 238 individuals that this rapid, zero-setup measurement yields LVET values statistically equivalent to pulsed-wave Doppler echocardiography (concordance within a 25 ms margin). Furthermore, an exploratory clinical analysis revealed that the LDV-derived LVET index (LVETI) was significantly prolonged in patients with aortic insufficiency and stenosis compared to low-risk controls, demonstrating the clinical plausibility of the measurement. To eliminate the bottleneck of expert interpretation, we developed and validated a deep learning model that automatically extracts LVET with high accuracy (mean absolute error of 8.08 ms). By combining easy LDV data acquisition with automated analysis, this approach may facilitate rapid, operator-independent cardiovascular assessment, potentially enhancing population-level screening and cardiovascular health management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automated measurement of left ventricular ejection time via contactless suprasternal notch laser vibrometry

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月14日

查看全文
  • Jonas Gonzalez-Billandon,
  • Matilda Andersson,
  • Benjamin Waubert,
  • Anders Ekman,
  • Lisa Bergin,
  • Linette Hartzell,
  • Johan Sahlén,
  • Simon Gustafsson,
  • Yuan Tan,
  • Andreea Valdman,
  • Mattias Windå,
  • Mattias Nilsson,
  • Jonas Spaak,
  • Henrik Hellqvist

摘要

Left Ventricular Ejection Time (LVET) is a sensitive indicator of early cardiac dysfunction, yet its routine use in first-line population screening is hindered by the operational and time demands of operator-dependent modalities like echocardiography. In this study, we introduce a scalable, contactless approach using laser Doppler vibrometry (LDV) signals targeted at the suprasternal notch (SSN) to capture hemodynamic events without physical sensor attachment. We demonstrate in a cohort of 238 individuals that this rapid, zero-setup measurement yields LVET values statistically equivalent to pulsed-wave Doppler echocardiography (concordance within a 25 ms margin). Furthermore, an exploratory clinical analysis revealed that the LDV-derived LVET index (LVETI) was significantly prolonged in patients with aortic insufficiency and stenosis compared to low-risk controls, demonstrating the clinical plausibility of the measurement. To eliminate the bottleneck of expert interpretation, we developed and validated a deep learning model that automatically extracts LVET with high accuracy (mean absolute error of 8.08 ms). By combining easy LDV data acquisition with automated analysis, this approach may facilitate rapid, operator-independent cardiovascular assessment, potentially enhancing population-level screening and cardiovascular health management.