文献速递睡眠呼吸障碍咽喉与嗓音

超声利用机器学习模型预测药物诱导睡眠内镜所见

Ultrasound Predicts Drug-Induced Sleep Endoscopy Findings Using Machine Learning Models.
PubMed 文献 · Laryngoscope · 2025-01-29

本研究对20例成人患者清醒及镇静状态下行超声检查,同期在药物诱导睡眠中行内镜,以VOTE标准评估塌陷。广义最小二乘回归模型显示超声特征与塌陷百分比中度至强相关(校正R² 0.53-0.82),机器学习模型在五个VOTE亚区中的四个能准确预测二值化VOTE评分(F1评分>0.65),侧软腭塌陷预测最准(F1评分0.93)。结论认为超声是可靠影像方法,回归与机器学习模型在预测DISE塌陷严重度方面有前景。

要点

  • 超声可测量气道解剖并预测DISE中VOTE各亚区塌陷模式与位置。
  • 广义最小二乘回归模型显示超声特征与塌陷百分比中度至强相关(校正R² 0.53-0.82)。
  • 机器学习模型在四个VOTE亚区准确预测二值化评分(F1>0.65),侧软腭最佳(F1=0.93)。

核心结论

  • 超声是可靠影像方法,可识别药物诱导睡眠中气道塌陷特征。
  • 回归(GLS)与机器学习模型在分析气道超声测量预测DISE塌陷严重度方面有前景。

研究设计与样本

  • 对20例不同气道亚区的成人患者,在清醒及镇静状态下行超声检查,同期在药物诱导睡眠中行内镜。
  • 从超声图像获取测量值并估算塌陷百分比(Pc),再以标准VOTE评分分级。
  • 采用广义最小二乘回归(GLS)建立连续尺度Pc预测模型,并训练多种机器学习(ML)模型从超声测量预测各VOTE评分(二值化,>50%塌陷)。

主要发现

  • 多个超声气道亚区测量与内镜塌陷通过Kendall Tau相关显示关联。
  • GLS模型显示多个超声特征与Pc在所有VOTE亚区呈中度至强相关(校正R² 0.53-0.82)。
  • ML模型在五个VOTE亚区中的四个能准确从超声测量预测二值化VOTE评分(F1评分>0.65)。
  • 预测塌陷最准确的VOTE亚区为侧软腭塌陷,所有模型平均F1评分为0.93。

关键数值与推荐

  • 塌陷百分比(Pc)通过超声图像估算并以标准VOTE评分分级。
  • 二值化VOTE评分定义为>50%塌陷。
  • GLS模型校正R²范围为0.53-0.82。
  • ML模型准确预测定义为F1评分>0.65。
  • 侧软腭塌陷平均F1评分为0.93。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES: Ultrasound is a promising low-risk imaging modality that can provide objective airway measurements that may circumvent limitations of drug-induced sleep endoscopy (DISE). This study was devised to identify ultrasound-derived anatomical measurements that could accurately predict collapse pattern and location based on the VOTE criteria (VOTE: Velum, Oropharynx, Tongue, and Epiglottis). METHODS: Ultrasonography was performed on 20 adult patients of various airway subsites while awake and sedated with concurrent endoscopy performed during drug-induced sleep. Measurements were obtained from the ultrasonographic images, and percent collapse (Pc) was estimated then graded using a standard VOTE score. Generalized Least Squares regression (GLS) was used to establish models predictive of Pc on a continuous scale, while multiple machine learning (ML) models were trained to predict each VOTE score (binary, >50% collapse) from ultrasound measurements. RESULTS: Measurements of multiple ultrasonographic airway subsites demonstrated associations with endoscopic collapse using Kendall Tau correlation. The GLS models showed moderate to strong correlation between multiple ultrasound features and Pc (R2 adj 0.53-0.82) across all VOTE subsites. ML models accurately predicted binarized VOTE scores from ultrasound measurements in four out of five VOTE subsites (F1 score >0.65), while the VOTE subsite with the most accurately predicted collapse was lateral velum collapse with an F1 score of 0.93 averaged across all models. CONCLUSIONS: Ultrasound is a reliable imaging modality and can identify features of airway collapse during drug-induced sleep. Regression (GLS) and ML models show promise in predicting severity of collapse during DISE with analysis of airway ultrasonographic measurements. LEVEL OF EVIDENCE: 3 Laryngoscope, 135:1642-1651, 2025.

来源:Laryngoscope,查看原文。版权归原作者所有。

引用

  1. Jones SE, Aw N, Acord M, et al. Ultrasound Predicts Drug-Induced Sleep Endoscopy Findings Using Machine Learning Models. Laryngoscope. 2025. PMID: 39876795. doi:10.1002/lary.31950

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。