Analysis of Smooth Pursuit Assessment in Virtual Reality and Concussion Detection using BiLSTM

TL;DR

This paper introduces a novel LSTM-based method using VR oculomotor data to improve the accuracy of concussion detection, aiming to provide more objective assessments than traditional symptom reporting.

Contribution

It presents a new approach employing BiLSTM neural networks and a novel error metric to enhance concussion detection accuracy from VR-based smooth pursuit tests.

Findings

BiLSTM outperforms symptom provocation in concussion prediction

Proposed error metric improves model accuracy

VR oculomotor data effectively detects concussion

Abstract

The sport-related concussion (SRC) battery relies heavily upon subjective symptom reporting in order to determine the diagnosis of a concussion. Unfortunately, athletes with SRC may return-to-play (RTP) too soon if they are untruthful of their symptoms. It is critical to provide accurate assessments that can overcome underreporting to prevent further injury. To lower the risk of injury, a more robust and precise method for detecting concussion is needed to produce reliable and objective results. In this paper, we propose a novel approach to detect SRC using long short-term memory (LSTM) recurrent neural network (RNN) architectures from oculomotor data. In particular, we propose a new error metric that incorporates mean squared error in different proportions. The experimental results on the smooth pursuit test of the VR-VOMS dataset suggest that the proposed approach can predict concussion symptoms with higher accuracy compared to symptom provocation on the vestibular ocular motor screening (VOMS).