Automatic nystagmus detection and quantification in long-term continuous eye-movement data

Abstract

Symptoms of dizziness or imbalance are frequently reported by people over 65. Dizziness is usually episodic and can have many causes, making diagnosis problematic. When it is due to inner-ear malfunctions, it is usually accompanied by abnormal eye-movements called nystagmus. The CAVA (Continuous Ambulatory Vestibular Assessment) device has been developed to provide continuous monitoring of eye-movements to gain insight into the physiological parameters present during a dizziness attack. In this paper, we describe novel algorithms for detecting short periods of artificially induced nystagmus from the long-term eye movement data collected by the CAVA device. In a blinded trial involving 17 healthy subjects, each participant induced nystagmus artificially on up to eight occasions by watching a short video on a VR headset. Our algorithms detected these short periods with an accuracy of 98.77%. Additionally, data relating to vestibular induced nystagmus was collected, analysed and then compared to a conventional technique for assessing nystagmus during caloric testing. The results show that a range of nystagmus can be identified and quantified using computational methods applied to long-term eye-movement data captured by the CAVA device.