Scholarlink

<p>To evaluate the feasibility of a smartphone-based deep learning artificial intelligence (AI) tool for detecting post-swallow airway compromise through brief acoustic analysis of voice recordings obtained before and after swallowing. This multicenter prospective study employed a simple 1.5-second sustained phonation (“a~”) recorded on a smartphone in patients referred for videofluoroscopic swallowing studies (VFSS). Cases were classified using the Penetration–Aspiration Scale (PAS), with PAS 1 defined as normal and PAS 2–8 as abnormal (penetration–aspiration events). An autoencoder-based anomaly detection model was trained on normal data (PAS 1) and validated using sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC). Among 208 participants, the AI model achieved a sensitivity of 90.9% and specificity of 87.5% in the validation set, with an accuracy of 90.4% and an AUC of 0.98. In the independent test set, sensitivity was 91.9%, specificity 50.0%, accuracy 85.2%, and AUC 0.76. A brief 1.5-second voice recording analyzed with a deep learning AI model showed promising internal performance for screening post-swallow airway compromise. This approach may serve as a practical and accessible adjunct to identify individuals requiring further instrumental assessment.</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–Based Acoustic Screening for Penetration–Aspiration Events Using Short Voice Recordings

  • 期刊论文

  • 发表日期：

    2026年6月2日

查看全文
  • Yong Jae Na,
  • Jun Hyeok Lee,
  • Eunyoung Choi,
  • Jong Yoon Chang,
  • Kyung Cheon Seo,
  • Jaeho Lee,
  • Hunseok Ko,
  • Sang-Ick Kang,
  • Myungeun Yoo,
  • Yoon Ghil Park,
  • Jinyoung Park,
  • Jiyoung Kim,
  • Ju Kang Lee,
  • Kyounghyo Choi

摘要

To evaluate the feasibility of a smartphone-based deep learning artificial intelligence (AI) tool for detecting post-swallow airway compromise through brief acoustic analysis of voice recordings obtained before and after swallowing. This multicenter prospective study employed a simple 1.5-second sustained phonation (“a~”) recorded on a smartphone in patients referred for videofluoroscopic swallowing studies (VFSS). Cases were classified using the Penetration–Aspiration Scale (PAS), with PAS 1 defined as normal and PAS 2–8 as abnormal (penetration–aspiration events). An autoencoder-based anomaly detection model was trained on normal data (PAS 1) and validated using sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC). Among 208 participants, the AI model achieved a sensitivity of 90.9% and specificity of 87.5% in the validation set, with an accuracy of 90.4% and an AUC of 0.98. In the independent test set, sensitivity was 91.9%, specificity 50.0%, accuracy 85.2%, and AUC 0.76. A brief 1.5-second voice recording analyzed with a deep learning AI model showed promising internal performance for screening post-swallow airway compromise. This approach may serve as a practical and accessible adjunct to identify individuals requiring further instrumental assessment.