Scholarlink

<p>Polysomnography is the standard tool for assessing obstructive sleep apnea (OSA) severity; however, it does not provide information regarding the anatomical site or extent of upper airway obstruction. Drug-induced sleep endoscopy (DISE) serves as a dynamic method to evaluate airway collapse under sleep-like conditions, thereby helping to bridge this gap. However, its clinical utility is limited by inter-observer variability and subjectivity in interpretation. We developed internally and externally validated deep learning models utilizing convolutional neural networks based on EfficientNet-B2 and Attention Multiple Instance Learning to predict the degree of airway obstruction (DISE-V-obs, DISE-OTE-obs) and the primary cause of obstruction (DISE-OTE-cause) using DISE videos from 1904 patients across five Korean hospitals. The F1 scores for DISE-V-obs, DISE-OTE-obs, and DISE-OTE-cause were 84.7%, 74.7%, and 88.2%, respectively. These objective predictions of obstruction degree and primary cause may enhance clinical decision-making and treatment planning for patients with OSA.</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 automatic scoring of drug-induced sleep endoscopy in obstructive sleep apnea

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月28日

查看全文
  • Jin Youp Kim,
  • Sue Jean Mun,
  • Young Seo Baik,
  • Young Seop Lee,
  • Young Jae Kim,
  • Jayoung Oh,
  • Gwanghui Ryu,
  • Chung-Man Sung,
  • Sung Jae Heo,
  • Hyung Chae Yang,
  • Hyun Jik Kim,
  • Hyo Yeol Kim,
  • Kyu-Sup Cho,
  • Kwang Gi Kim,
  • Chae-Seo Rhee

摘要

Polysomnography is the standard tool for assessing obstructive sleep apnea (OSA) severity; however, it does not provide information regarding the anatomical site or extent of upper airway obstruction. Drug-induced sleep endoscopy (DISE) serves as a dynamic method to evaluate airway collapse under sleep-like conditions, thereby helping to bridge this gap. However, its clinical utility is limited by inter-observer variability and subjectivity in interpretation. We developed internally and externally validated deep learning models utilizing convolutional neural networks based on EfficientNet-B2 and Attention Multiple Instance Learning to predict the degree of airway obstruction (DISE-V-obs, DISE-OTE-obs) and the primary cause of obstruction (DISE-OTE-cause) using DISE videos from 1904 patients across five Korean hospitals. The F1 scores for DISE-V-obs, DISE-OTE-obs, and DISE-OTE-cause were 84.7%, 74.7%, and 88.2%, respectively. These objective predictions of obstruction degree and primary cause may enhance clinical decision-making and treatment planning for patients with OSA.