Recurrent neural networkbased acute concussion classifier ...
· · 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 This is the first instance of a highperforming classifier that relies only on easytoacquire resting state, raw EEG data. Our concussion classifier represents .
![whatsapp](/images/whatsapp.png)