Key result
Machine learning models identify posterior circulation stroke with up to ~97% accuracy.
Why the study?
Differentiating acute unilateral vestibulopathy and posterior circulation stroke in acute vestibular syndrome patients using clinical and vestibular tests remains challenging.
Do machine learning models trained on tiered combinations of clinical history, examination, and vestibular tests accurately differentiate posterior circulation stroke from acute unilateral vestibulopathy compared to the expert HINTS examination in patients with acute vestibular syndrome?
Observational (n=294)
No
Do machine learning models trained on tiered combinations of clinical history, examination, and vestibular tests accurately differentiate posterior circulation stroke from acute unilateral vestibulopathy compared to the expert HINTS examination in patients with acute vestibular syndrome?
Answers are grounded in this paper and cite their sources.
Machine learning models combining clinical history, basic neurological examination, and horizontal video head-impulse testing achieve diagnostic accuracy equivalent to expert HINTS (94.6%) in distinguishing posterior circulation stroke from acute unilateral vestibulopathy.
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.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) conducted an observational in Acute vestibular syndrome (acute unilateral vestibulopathy or posterior circulation stroke) (n=294). Machine learning diagnostic models (CatBoost, XGBoost, LightGBM) using tiered clinical history, bedside examination, and vestibular function tests vs. HINTS examination by neuro-otology experts and logistic regression was evaluated on Diagnostic accuracy for identifying posterior circulation stroke versus acute unilateral vestibulopathy (95% CI 93.3-99.9, p=0.16). CatBoost and XGBoost machine learning models differentiated posterior circulation stroke from acute unilateral vestibulopathy with 96.6% (Tier 1), 94.6% (Tier 2), and 88.8% (Tier 3) accuracy.
Synapse has enriched 10 related papers. Consider them for comparative context: