文献速递神经头颈US

床旁超声识别和预测缺血性卒中后吞咽困难严重程度:人工与人工智能对比

Bedside Ultrasound to Identify and Predict Severity of Dysphagia Following Ischemic Stroke: Human Versus Artificial Intelligence.
PubMed 文献 · Ultrasound Med Biol · 2023-10-18

前瞻性单盲观察性预试验纳入69例急性缺血性卒中患者,在吞咽时行正中矢状位气道超声,由语言治疗师盲法行视频荧光镜或纤维内镜吞咽评估并以穿透-误吸量表评分。人工测量舌骨运动无法预测穿透-误吸量表结果(P值0.36、0.13、0.11、0.32),机器学习算法与穿透-误吸量表结果呈高度一致(κ=0.79,95%CI 0.52-1.0)。

要点

  • 人工测量舌骨抬高、前移、总位移及下颌长度均不能预测穿透-误吸量表结果。
  • 机器学习算法预测穿透-误吸量表结果与人工评估高度一致(κ=0.79)。
  • 该算法基于实时超声视频,训练用90%视频,测试用10%未见视频。

核心结论

  • 人工超声测量卒中患者吞咽时舌骨运动未能预测穿透-误吸量表结果,而机器学习算法与穿透-误吸量表结果呈高度一致,尽管数据集较小。

研究设计与样本

  • 前瞻性单盲观察性预试验,2019年6月至2020年3月在综合性卒中中心便利抽样纳入69例急性缺血性卒中患者,行正中矢状位气道超声及视频荧光镜或纤维内镜吞咽评估,参考标准为穿透-误吸量表评分。

关键影像表现/征象

  • 正中矢状位气道超声测量吞咽时舌骨抬高、前移、总位移及下颌长度。
  • 人工测量舌骨抬高、前移、总位移及下颌长度均不能预测穿透-误吸量表评估结果(P值分别为0.36、0.13、0.11和0.32)。
  • 机器学习算法采用长短期记忆网络嵌入VGG16卷积神经网络进行实时视频分析。

诊断标准与关键数值

  • 以穿透-误吸量表评分判定视频荧光镜或纤维内镜吞咽评估的失败或成功。
  • 机器学习算法与穿透-误吸量表结果比较,Cohen κ=0.79(95%CI 0.52-1.0),呈高度一致。
  • 舌骨抬高、前移、总位移及下颌长度的P值分别为0.36、0.13、0.11和0.32。

临床应用与阅片要点

  • 人工测量舌骨运动未能预测穿透-误吸量表结果,不宜单独用于判断误吸风险。
  • 机器学习算法分析实时超声视频可能有助于改善吞咽困难评估的可及性(原文结论)。

局限性

  • 原文结论指出数据集较小。
  • 本研究为单盲观察性预试验(原文自述)。

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)。

英文原文(摘要)· 点击展开

OBJECTIVE: Dysphagia is a significant ischemic stroke complication that can lead to aspiration. Identification of at-risk patients can be logistically difficult and costly. Researchers investigated whether quantitative ultrasound assessment of hyoid bone movement during induced swallowing would predict failure of videofluoroscopy (VFS) or fiberoptic endoscopic evaluation of swallowing (FEES), as determined by a penetration-aspiration scale (PAS) score. Additionally, ability of a machine learning (ML) algorithm to predict PAS success or failure from real-time ultrasound video recordings was assessed.

METHODS: A prospective, single-blinded, observational pilot study was conducted from June 2019 through March 2020 at a comprehensive stroke center on a convenience sample of patients admitted with diagnosis of acute ischemic stroke undergoing VFS or FEES as part of dysphagia assessment. Researchers performed a midsagittal airway ultrasound during swallowing in patients receiving an objective swallowing assessment by speech language pathologists who were blinded to ultrasound results. Sonologists measured hyoid bone movement, and researchers then constructed an ML algorithm designed for real-time video analysis using a long short-term memory network with an embedded VGG16 convolutional neural network.

RESULTS: Videos from 69 patients were obtained with their respective PAS results. In total, 90% of available videos were used for algorithm training. After training, the ML algorithm was challenged with the 10% previously unseen videos and then compared with PAS outcomes. Statistical analysis included logistic regression and correlation matrix testing on human ultrasound measurements. Cohen's κ was calculated to compare deep learning algorithm prediction with PAS results. Measurement of hyoid bone elevation, forward displacement, total displacement and mandible length was unable to predict PAS assessment outcome (p values = 0.36, 0.13, 0.11 and 0.32, respectively). The ML algorithm showed substantial agreement with PAS testing results for predicting test outcome (κ = 0.79; 95% confidence interval: 0.52-1.0) CONCLUSION: Manual ultrasound measurement of hyoid movement during swallowing in stroke patients failed to predict PAS swallowing results. However, an ML algorithm showed substantial agreement with PAS results despite a small data set, which could greatly improve access to dysphagia assessment in the future.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Barron K, Blaivas M, Blaivas L, et al. Bedside Ultrasound to Identify and Predict Severity of Dysphagia Following Ischemic Stroke: Human Versus Artificial Intelligence. Ultrasound Med Biol. 2023. PMID: 37858370. doi:10.1016/j.ultrasmedbio.2023.09.008

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。