Abstract

Concussion is a global health concern. Despite its high prevalence, a sound understanding of the mechanisms underlying this type of diffuse brain injury remains elusive. It is, however, well established that concussions cause significant functional deficits; that children and youths are disproportionately affected and have longer recovery time than adults; and that individuals suffering from a concussion are more prone to experience additional concussions, with each successive injury increasing the risk of long term neurological and mental health complications. Currently, the most significant challenge in concussion management is the lack of objective, clinically- accepted, brain-based approaches for determining whether an athlete has suffered a concussion. Here, we report on our efforts to address this challenge. Specifically, we introduce a deep learning long short-term memory (LSTM)-based recurrent neural network that is able to distinguish between non-concussed and acute post-concussed adolescent athletes using only short (i.e. 90 s long) samples of resting state EEG data as input. The athletes were neither required to perform a specific task nor expected to respond to a stimulus during data collection. The acquired EEG data were neither filtered, cleaned of artefacts, nor subjected to explicit feature extraction. The LSTM network was trained and validated using data from 27 male, adolescent athletes with sports related concussion, benchmarked against 35 non-concussed adolescent athletes. During rigorous testing, the classifier consistently identified concussions with an accuracy of > 90% and achieved an ensemble median Area Under the Receiver Operating Characteristic Curve (ROC/AUC) equal to 0.971. This is the first instance of a high-performing classifier that relies only on easy-to-acquire resting state, raw EEG data. Our concussion classifier represents a promising first step towards the development of an easy-to-use, objective, brain-based, automatic classification of concussion at an individual level.

Highlights

  • Studies show that children and youths who have sustained a concussion are at a higher risk of sustaining additional concussions, which can lead to neuro-psychiatric and neuro-degenerative d­ isorders[26,27]

  • We examined the Receiver Operating Characteristic (ROC) curve and the corresponding Area Under the Curve (AUC) for ConcNet 2

  • The results presented here demonstrate that an long short-term memory (LSTM)-based deep learning network for concussion classification is a promising engine for an objective, brain-based platform, which can identify acute post-concussed individuals within 1 month of injury

Read more

Summary

Introduction

Because the brain injury due to mTBI is diffuse and the resulting changes in the brain structure and function are subtle, the summary measures cannot be used to statistically differentiate between non-concussed and injured at the individual level This has led the Radiological Society of North America to advise that “in pediatric patients, imaging should not be routinely obtained to diagnose mild TBI” because “there is insufficient evidence [to support] the routine clinical use of advanced neuroimaging techniques for diagnosis and/or prognostication at the individual patient level”[37]

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call