Children and teens are disproportionately affected by concussions and have a longer recovery time than adults. Those who have suffered from a concussion are more prone to experience additional concussions — each time, increasing the risk of long-term physical and mental health complications. The biggest challenge in concussion management is the lack of objective, brain-based approaches for determining whether a young athlete has had a concussion. Dr. Naznin Virji-Babul, Dr. Karun Thanjavur and their collaborators developed a “deep learning long short-term memory (LSTM)-based” recurrent neural network capable of distinguishing between non-concussed and acute post-concussed adolescent athletes using only 90-second samples of resting state EEG data. Their classifier is able to identify concussions with over 90 per cent accuracy.
“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,” wrote Dr. Virji-Babul and her team in “Recurrent Neural Network-Based Acute Concussion Classifier Using Raw Resting State EEG Data.”
Read more in Scientific Reports.
Comments are closed, but trackbacks and pingbacks are open.