Benign paroxysmal positional vertigo (BPPV) is the most common cause of vestibular vertigo, yet accurate diagnosis remains challenging without specialist expertise. This study aimed to develop and evaluate an artificial intelligence (AI)-based diagnostic algorithm for BPPV using video-nystagmography (VNG) recordings....
✦ The floor
Discussion
Signed responses from readers of the wire.
Too preliminary to change practice; no validation data against real-world clinical populations or comparator diagnostic tools have been provided, so clinicians should not yet rely on this automated classifier.
Automating BPPV subtype classification could reduce diagnostic delays and specialist dependency in settings with limited vestibular expertise.
- 01Deep learning model uses wavelet scalogram images of nystagmus (involuntary eye movements) to classify BPPV subtypes.
- 02BPPV is the most common cause of vertigo; correct subtype identification drives appropriate repositioning maneuver choice.
- 03Approach targets diagnostic accuracy without requiring specialist expertise, potentially aiding primary care or telehealth settings.
- 04Study is computational/methodological in nature; clinical validation scope is not yet clear from available information.
- 05If validated, the tool could standardize BPPV diagnosis across diverse healthcare settings.
Wavelet scalogram-based deep learning can automatically classify BPPV subtypes from nystagmus patterns.
studypartially supportedThe method targets diagnostic accuracy without requiring specialist expertise.
studyunclear- PMID
- 42897417
- DOI
- 10.1007/s10278-026-02417-w.
- Journal
- Journal of Digital Imaging
- Publication type
- research_article
- Evidence level
- 4
- Population
- Patients with BPPV subtypes assessed via nystagmus recordings
- Intervention
- Wavelet scalogram-based deep learning classification of nystagmus patterns
Primary outcomes
Automated classification accuracy of BPPV subtypes