Automated classification of benign paroxysmal positional vertigo from video-nystagmography using a delay-aware neural network
Kunal Chaturvedi, Nicholas Yang, Imelda Hannigan, Nicole Reid, Andrew Bradshaw, Karthick Thiyagarajan, Tony Jan, Ali Braytee, Miriam S Welgampola, Mukesh Prasad · 2026
Read Automated classification of benign paroxysmal positional vertigo from video-nystagmography using a delay-aware neural network by Kunal Chaturvedi, Nicholas Yang, Imelda Hannigan, Nicole Reid, Andrew Bradshaw, Karthick Thiyagarajan, Tony Jan, Ali Braytee, Miriam S Welgampola, Mukesh Prasad (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13381937.txt.
Description
Kunal Chaturvedi and co-authors build a neural network in 2026 that diagnoses a common cause of spinning dizziness from eye movement videos. The condition stems from loose crystals in the inner ear and can be cured with specific head maneuvers, but reading the telltale eye jerks is subjective and hard to standardize.
Their network accounts for signal delays, combining timed convolutions, delayed feedback, and refinement steps. It trained on 3,111 traces from 705 patients and was checked in repeated folds against known models. In the strict patient-independent test it scored best overall. Extra analyses show which time spans the model leans on, which may help clinicians trust its calls.
Catalog record
| CREATOR | Kunal Chaturvedi, Nicholas Yang, Imelda Hannigan, Nicole Reid, Andrew Bradshaw, Karthick Thiyagarajan, Tony Jan, Ali Braytee, Miriam S Welgampola, Mukesh Prasad |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |