The present dissertation details a sequence of studies in mild traumatic brain injury, the progression of its effects on the human brain as recorded by event-related electroencephalography, and potential applications of machine learning algorithms in detecting such effects. The work investigated data collected from two populations (in addition to healthy controls): 1) a recently-concussed adolescent group, and 2) a group of retired football athletes who sustained head trauma a number of years prior to testing. Neurophysiological effects of concussion were assessed across both groups with the same experimental design using a multi-deviant auditory oddball paradigm designed to elicit the P300 and other earlier components. Explainable machine learning models were trained to classify concussed individuals from healthy controls. Cross-validation performance accuracies on the recently-concussed (chapter 4) and retired athletes (chapter 3) were 80% and 85%, respectively. Features showed to be most useful in the two studies were different, motivating a study of potential differences between the different injury-stage/age groups (chapter 5). Results showed event-related functional connectivity to modulate differentially between the two groups compared to healthy controls. Leveraging results from the presented work a theoretical model of mild traumatic brain injury progression was proposed to form a framework for synthesizing hypotheses in future research. / Dissertation / Doctor of Philosophy (PhD)

Les tachycardies ventriculaires (TV) et atriales (TA) sont les arythmies les plus fréquemment diagnostiquées en clinique. En vue d’ablater les tissus pathologiques, deux techniques de diagnostic sont utilisées : la cartographie électro-anatomique pour un diagnostic précis à l’aide d’électrogrammes (EGM) mesurés par cathéters intracardiaques et repérés sur la géométrie tridimensionnelle (3-D) de la cavité étudiée ; et l’imagerie électrocardiographique non-invasive (ECGi) pour une vision globale de l’arythmie, avec des EGM reconstruits mathématiquement à partir des électrocardiogrammes et des géométries cardio-thoraciques 3-D obtenues par CT-Scan. Les TV et TA sont alors diagnostiquées en étudiant les cartes d’activation qui sont des représentations des temps de passage locaux de l’onde d’activation sur la géométrie 3-D cardiaque. Cependant, les zones de ralentissement favorisant les TV et TA, et leurs motifs de propagation spécifiques n’y sont pas facilement identifiables. Ainsi, la caractérisation locale de la propagation de l’onde d’activation peut être utile pour améliorer le diagnostic. L’objet de cette thèse est le développement d’une méthode de caractérisation locale de la propagation de l’onde d’activation. Pour cela, un champ vectoriel de vitesse est estimé et analysé. La méthode a en premier lieu été validée sur des données simulées issues de modélisation, puis appliquée 1) à des données cliniques issues de l’ECGi pour la localisation des cicatrices d’infarctus et pour améliorer le diagnostic des TA; et 2) sur des données obtenues par cartographie électro-anatomique pour caractériser les zones pathogènes. / Ventricular (VT) and atrial (AT) tachycardias are some of the most common clinical cardiac arrhythmias. For ablation of tachycardia substrates, two clinical diagnosis methods are used : electro-anatomical mapping for an accurate diagnosis using electrograms (EGMs) acquired with intracardiac catheters and localized on the three-dimensional (3-D) mesh of the studied cavities ; and non-invasive electrocardiographic imaging (ECGi) for a global view of the arrhythmia, with EGMs mathematically reconstructed from body surface electrocardiograms and the 3-D cardio-thoracic meshes obtained with CT-scan. VT and AT are diagnosed studying activation time maps ; that are 3-D representations of the transit time of the activation wavefront on the cardiac mesh. Nevertheless, slow conduction areas, a well-known pro-arrhythmic feature for tachycardias, and the tachycardias specific propagation patterns are not easily identifiable with these maps. Hence, local characterization of the activation wavefront propagation can be helpful for improving VT and AT diagnosis. The purpose of this thesis is to develop a method to locally characterize the activation wavefront propagation. For that, a conduction velocity vector field is estimated and analyzed. The method was first validated on a simulated database from computer models, then applied to 1) a clinical database obtained from ECGi to localize infarct tissues and improve AT diagnosis ; and 2) a clinical database acquired with electro-anatomical mapping systems to define pathological areas.