Scholarlink

<p>Accurate segmentation of ventilator waveforms is essential for detecting patient–ventilator asynchronies (PVAs), yet current heuristic methods can fail in noisy, real-world data. We developed and validated a deep learning model using a one-dimensional attention-gated U-Net architecture to identify inspiratory and expiratory onsets in mechanical ventilation waveforms. The model was trained and tested on 9719 breaths from 33 patients and outperformed published rule-based methods, achieving F1 scores of &gt; 0.99 for both inspiratory and expiratory onset detection within a 0.1-s tolerance window. Performance remained robust in asynchronous breaths (F1 ≥ 0.98). When applied to quantify PVAs, the model reproduced reference standard asynchrony frequencies with no significant differences, whereas heuristic methods produced large deviations. Gradient-weighted class activation maps suggest that the model leveraged a diverse set of waveform features to inform segmentation. This computationally efficient model enables highly-accurate, clinically timely waveform analysis and provides a foundation for scalable, reproducible assessment of ventilator–patient interactions.</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

Deep learning for time-series segmentation of mechanical ventilator waveforms

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月28日

查看全文
  • Preeti Gupta,
  • Aditya Nemani,
  • Virginia R. de Sa,
  • Alex K. Pearce,
  • Shamim Nemati,
  • Atul Malhotra,
  • Jason Y. Adams

摘要

Accurate segmentation of ventilator waveforms is essential for detecting patient–ventilator asynchronies (PVAs), yet current heuristic methods can fail in noisy, real-world data. We developed and validated a deep learning model using a one-dimensional attention-gated U-Net architecture to identify inspiratory and expiratory onsets in mechanical ventilation waveforms. The model was trained and tested on 9719 breaths from 33 patients and outperformed published rule-based methods, achieving F1 scores of > 0.99 for both inspiratory and expiratory onset detection within a 0.1-s tolerance window. Performance remained robust in asynchronous breaths (F1 ≥ 0.98). When applied to quantify PVAs, the model reproduced reference standard asynchrony frequencies with no significant differences, whereas heuristic methods produced large deviations. Gradient-weighted class activation maps suggest that the model leveraged a diverse set of waveform features to inform segmentation. This computationally efficient model enables highly-accurate, clinically timely waveform analysis and provides a foundation for scalable, reproducible assessment of ventilator–patient interactions.