Deep learning assisted cognitive diagnosis for the D-Riska application

Abstract In this article, we expose a system developed that extends the Acquired Brain Injury (ABI) diagnostic application known as D-Riska with an artificial intelligence module supports diagnosis of ABI enabling therapists to evaluate patients in assisted way. The is charge collecting data tests patients, and due multi-class Convolutional Neural Network classifier (CNN), it capable making predictions facilitate final score obtained test by patient. To find out best solution problem, different classifiers are used compare performance proposed model based on various classification metrics. CNN makes 93 % Accuracy, 94 Precision, 91 %, Recall 92% F1-Score.