Article record

利用病史、体格检查和前庭功能检查区分卒中和急性单侧前庭病：一种机器学习方法

Separating stroke and acute unilateral vestibulopathy using history, examination and vestibular tests: a machine learning approach.

AI/ML耳科IF 5.3Q1

文献信息

PMID	42709223
原文	在 PubMed 查看原文 ↗
发表日期	2026
作者	Chao Wang 查看其他 12 位作者 Kunal Chaturvedi；Benjamin Nham；Nicole Reid；Andrew P Bradshaw；Sally M Rosengren；Deborah A Black；Kendall J Bein；G Michael Halmagyi；Ali Braytee；Gnana K Bharathy；Mukesh Prasad；Miriam S Welgampola
作者单位	Central Clinical School, University of Sydney, Sydney, Australia. 查看其他 8 条单位信息 Institute of Clinical Neurosciences, Royal Prince Alfred Hospital, Sydney, Australia.；School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia.；St George and Sutherland Clinical School, University of New South Wales, Sydney, Australia.；Faculty of Medicine and Health, University of Sydney, Sydney, Australia.；Department of Emergency Medicine, Royal Prince Alfred Hospital, Sydney, Australia.；Royal Prince Alfred Green Light Institute for Emergency Care, Sydney, Australia.；Central Clinical School, University of Sydney, Sydney, Australia. miriam@icn.usyd.edu.au.；Institute of Clinical Neurosciences, Royal Prince Alfred Hospital, Sydney, Australia. miriam@icn.usyd.edu.au.
期刊	Journal of neurology
SCI 分区	Q1
IF	5.3
研究类型	AI/ML · 临床
所属专科	耳科

中文摘要

背景： 急性单侧前庭病（AUVP）和后循环卒中（PCS）是急性前庭综合征的两种常见病因。我们开发并评估了机器学习模型，利用患者病史、体格检查和前庭功能检查的组合来区分AUVP和PCS。
方法： 我们招募了294例因急性前庭综合征就诊于急诊科（ER）的患者（AUVP：n = 163，PCS：n = 131）。病史、床旁检查和前庭功能检查（视频眼震图（VNG）、视频头脉冲试验（VHIT）、前庭诱发肌源性电位（VEMP）和主观视觉水平）的数据被用于机器学习模型的开发。不同的数据子集模拟了三种情景，分层反映了不同水平的临床专业知识和资源：第1层代表有神经耳科支持的急诊科（病史、神经耳科检查、VNG、VHIT、眼性VEMP），第2层代表有VHIT的急诊科（病史、基本检查、VHIT），第3层代表仅依赖病史和基本检查的急诊科。模型性能还与HINTS试验（头脉冲、眼震、偏斜试验）进行了比较。
结果： 我们表现最佳的模型使用CatBoost或XGBoost算法，在第1、2和3层识别PCS的准确率分别为96.6%（95% CI：93.3-99.9%）、94.6%（95% CI：90.5-98.6%）和88.8%（95% CI：86.0-91.6%）。专家进行的HINTS试验达到94.6%的准确率。最重要的变量在第1层为床旁头脉冲试验、局灶性神经系统症状的存在和自发性眼震慢相速度；在第2层为局灶性神经系统症状；在第3层为年龄。
结论： 机器学习模型能够准确区分PCS和AUVP，并有望作为一线临床医生的诊断辅助工具。

英文摘要

BACKGROUND: Acute unilateral vestibulopathy (AUVP) and posterior circulation stroke (PCS) are the two common causes of the acute vestibular syndrome. We developed and evaluated machine learning models to differentiate AUVP and PCS using combinations of patient history, examination, and vestibular tests.
METHODS: We recruited 294 patients presenting to the Emergency Room (ER) with acute vestibular syndrome (AUVP: n = 163, PCS: n = 131). Data from history, bedside examination and vestibular tests (video-nystagmography (VNG), video head-impulse test (VHIT), vestibular-evoked myogenic potentials (VEMP) and subjective visual horizontal) were used for machine learning model development. Different subsets of data simulated three scenarios hierarchically reflecting different levels of clinical expertise and resources: Tier 1 represented an ER with neuro-otology support (history, neuro-otological examination, VNG, VHIT, ocular VEMP), Tier 2 an ER with VHIT (history, basic examination, VHIT) and Tier 3 an ER reliant on history and basic examination only. Model performance was also compared against the HINTS test (head impulse, nystagmus, test-of-skew).
RESULTS: Our best-performing models used the CatBoost or XGBoost algorithms and identified PCS with accuracies of 96.6% (95% CI: 93.3-99.9%), 94.6% (95% CI: 90.5-98.6%) and 88.8% (95% CI: 86.0-91.6%) for Tiers 1, 2 and 3. HINTS by experts achieved 94.6% accuracy. The most important variables were the bedside head-impulse test, presence of focal neurological symptoms and spontaneous nystagmus slow phase velocity in Tier 1; focal neurological symptoms in Tier 2; and age in Tier 3.
CONCLUSION: Machine learning models can accurately separate PCS and AUVP and hold promise as diagnostic aids for frontline clinicians.