Convolutional neural networks for quantitative smartphone video nystagmography: ConVNG.
Friedrich, M. U.; Schneider, E.; Buerklein, M.; Taeger, J.; Hartig, J.; Volkmann, J.; Peach, R.; Zeller, D.
Show abstract
BackgroundEye movement abnormalities are paramount in neurological disorders. However, unaided eye movement assessments lack granularity. Although videooculography (VOG) improves diagnostic accuracy, resource intensiveness preclude its broad use. To bridge this care gap, we here validate a framework for smartphone video-based nystagmography capitalizing on recent computer vision advances. MethodsA recurrent convolutional network was fine-tuned for pupil tracking using >550 annotated frames: ConVNG. Slow phase velocity of optokinetic nystagmus was calculated in 10 subjects using both ConVNG and VOG. Equivalence of accuracy and precision was assessed using the "two one-sample t-test" (TOST) and Bayesian interval-null approaches. ResultsConVNG tracking accuracy reached 9-15% of an average pupil diameter. SPV measurement accuracy was equivalent to VOG (p< .017; Bayes factors (BF) > 24). Average precision was 0.30{degrees} for ConVNG and 0.12{degrees} for VOG. ConclusionsConVNG enables smartphone video nystagmography with an accuracy comparable to VOG and precision approximately one order of magnitude higher than comparable ARKit applications. This serves as a blueprint for highly accessible tools with potential to accelerate progress toward precise and personalized Medicine.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Digital gait biomarkers, but not clinical ataxia scores, allow to capture 1-year longitudinal change in Spinocerebellar ataxia type 3 (SCA3) 89%
- Phenotypical differentiation of tremor using time series feature extraction and machine learning 89%
- The final blink: intact cerebellar associative learning in isolated dystonia 88%
Similar papers in this journal
- Neuromotor Prosthetic to Treat Stroke-Related Paresis 90%
- Prospective validation of smartphone-based heart rate and respiratory rate measurement algorithms 89%
- The 5-HT1A receptor antagonist WAY-100635 maleate reprograms metabolism to promote RGC differentiation and regeneration in retino-visual centers 88%
Similar papers in this journal
- Machine learning approach for ambient-light-corrected parameters and the Neuro-Pupillary Index (NPx) in smartphone-based pupillometry 93%
- Application of Digital Tools and Artificial Intelligence to the Myasthenia Gravis Core Examination 92%
- Eye movement evaluation in Multiple Sclerosis and Parkinson's Disease using a Standardized Oculomotor and Neuro-ophthalmic Disorder Assessment (SONDA) 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.