Machine learning models help differentiate between causes of recurrent spontaneous vertigo

Chao Wang; Allison S Young; Chahat Raj; Andrew P Bradshaw; Benjamin Nham; Sally M Rosengren; Zeljka Calic; David Burke; G Michael Halmagyi; Gnana K Bharathy; Mukesh Prasad; Miriam S Welgampola

doi:10.1007/s00415-023-11997-4

Machine learning models help differentiate between causes of recurrent spontaneous vertigo

J Neurol. 2024 Mar 23. doi: 10.1007/s00415-023-11997-4. Online ahead of print.

Authors

Chao Wang^{1

2}, Allison S Young², Chahat Raj³, Andrew P Bradshaw¹, Benjamin Nham^{1

2}, Sally M Rosengren^{1

2}, Zeljka Calic^{4

5}, David Burke^{1

2}, G Michael Halmagyi^{1

2}, Gnana K Bharathy³, Mukesh Prasad³, Miriam S Welgampola^{6

7}

Affiliations

¹ Institute of Clinical Neurosciences, Royal Prince Alfred Hospital, Sydney, Australia.
² Central Clinical School, University of Sydney, Sydney, Australia.
³ School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia.
⁴ Department of Neurophysiology, Liverpool Hospital, Sydney, Australia.
⁵ South Western Sydney Clinical School, University of New South Wales, Sydney, Australia.
⁶ Institute of Clinical Neurosciences, Royal Prince Alfred Hospital, Sydney, Australia. miriam@icn.usyd.edu.au.
⁷ Central Clinical School, University of Sydney, Sydney, Australia. miriam@icn.usyd.edu.au.

PMID: 38520520
DOI: 10.1007/s00415-023-11997-4

Abstract

Background: Vestibular migraine (VM) and Menière's disease (MD) are two common causes of recurrent spontaneous vertigo. Using history, video-nystagmography and audiovestibular tests, we developed machine learning models to separate these two disorders.

Methods: We recruited patients with VM or MD from a neurology outpatient facility. One hundred features from six "feature subsets": history, acute video-nystagmography and four laboratory tests (video head impulse test, vestibular-evoked myogenic potentials, caloric testing and audiogram) were used. We applied ten machine learning algorithms to develop classification models. Modelling was performed using three "tiers" of data availability to simulate three clinical settings. "Tier 1" used all available data to simulate the neuro-otology clinic, "Tier 2" used only history, audiogram and caloric test data, representing the general neurology clinic, and "Tier 3" used history alone as occurs in primary care. Model performance was evaluated using tenfold cross-validation.

Results: Data from 160 patients with VM and 114 with MD were used for model development. All models effectively separated the two disorders for all three tiers, with accuracies of 85.77-97.81%. The best performing algorithms (AdaBoost and Random Forest) yielded accuracies of 97.81% (95% CI 95.24-99.60), 94.53% (91.09-99.52%) and 92.34% (92.28-96.76%) for tiers 1, 2 and 3. The best feature subset combination was history, acute video-nystagmography, video head impulse test and caloric testing, and the best single feature subset was history.

Conclusions: Machine learning models can accurately differentiate between VM and MD and are promising tools to assist diagnosis by medical practitioners with diverse levels of expertise and resources.

Keywords: Artificial intelligence; Menière’s disease; Vestibular migraine.

Grants and funding

2021_RS_Wang/Garnett Passe and Rodney Williams Memorial Foundation