This master’s thesis deals with methods for detection of myocardial ischemia in the ECG signal. There is explained the principle of spreading of electrical activity through the heart muscle and its manifestations on the ECG. There are also mentioned the causes of myocardial ischemia and various methods of its detection in the ECG signal. In great detail there is explained the process of implementation of the two selected detection methods of myocardial ischemia in MATLAB. These methods are tested on the data from The PTB Diagnostic ECG Database. Finally, there is the presentation of detection results on used data and overall assessment of created algorithms.

This thesis focuses on the issue of atrial fibrillation and the success of their detection in the ECG signal. It provides a description of electrical activity of the heart with the theoretical analysis of atrial fibrillation and methods for their detection. Additionally the work describes procedures for the implementation of three selected methods for the detection of atrial fibrillation in the MATLAB environment, presents the results of their tests on two atrial fibrillation signal databases and assesses the accuracy of each method.

L’électrocardiogramme (ECG) permet de mesurer l’activité électrique du cœur. Il est utilisé pendant les examens d’Imagerie par Résonance Magnétique (IRM) depuis plusieurs décennies pour améliorer la surveillance des patients et synchroniser les acquisitions des images. Néanmoins, cette technique est réalisée en utilisant des dispositifs électroniques avec une bande passante faible et un nombre limité d’électrodes ne permettant pas de fournir un signal de qualité diagnostic. En effet, un ECG diagnostic nécessite une large bande passante (0.05 – 150 Hz) ainsi que 10 électrodes de mesure qui permettent d’acquérir 12 dérivations. L’IRM est caractérisée par un environnement avec un champ magnétique statique intense, des champs électromagnétiques dynamiques à haute fréquence et à basse fréquence. La conception et le développement d’un capteur ECG compatible IRM nécessite de prendre en compte cet environnement afin de réduire les risques d’échauffements du dispositif pendant les séquences d’images et réduire les perturbations sur les signaux mesurés. L’utilisation de dispositifs avec des câbles courts réduit les risques d’échauffement par effet antenne, ce qui garantit la sécurité des patients, mais l’induction de bruit sur les signaux est inévitable. Le travail de thèse a été organisé en cinq parties principales. Les deux premières parties étaient orientées sur l’étude de la littérature et la conception d’un nouveau prototype de capteur avec une large bande passante d’ECG. L’objectif était de développer un dispositif doté d’une puissance de calcul suffisante pour intégrer les algorithmes de traitement du signal développés par le laboratoire IADI, afin d’éliminer le bruit superposé aux signaux. La troisième partie a été consacrée à la construction d’un réseau de capteurs à partir de N capteurs. L’objectif était de multiplier le nombre d’électrodes de mesure pour augmenter la résolution spatiale de l’ECG et reconstruire un ECG 12 dérivations pendant l’examen IRM. La finalité de ce travail est l’imagerie ECG non invasive à partir de cartes de potentiel électrique de surface et à partir de modèles anatomiques de patients obtenus simultanément par IRM. La quatrième partie expose un nouveau procédé de correction en temps réel des signaux ECG à partir d’une acquisition à haute fréquence d’échantillonnage, sur la base du dispositif développé. La cinquième et dernière partie présente une autre application de ce capteur en salle d’électrophysiologie interventionnelle, pendant l’activation d’un système de Navigation Magnétique à distance (NMD) du cathéter, qui génère des perturbations similaires à celles observées en IRM. / The electrocardiogram (ECG) is used to measure heart electrical activity. It has been used during Magnetic Resonance Imaging (MRI) examinations for several decades to improve patient monitoring and synchronize image acquisition. Nevertheless, this technique is performed using electronic devices with a low bandwidth and a limited number of electrodes that do not provide a diagnostic signal quality. Indeed, a diagnostic ECG requires a wide bandwidth (0.05 - 150 Hz) and 10 measuring electrodes that allow 12 leads to be acquired. MRI is characterized by an environment with an intense static magnetic field, high frequency and low frequency dynamic electromagnetic fields. The design and development of an MRI-compatible ECG sensor needs to take into account this environment to reduce the risk of overheating of the device during image sequences and to reduce disturbances on the measured signals. The use of devices with short cables reduces the risk of overheating by antenna effect, which ensures patient safety, but the induction of noise on the signals is inevitable. This thesis is organized in five parts. The first two parts were oriented towards the study of the literature and the design of a new sensor prototype with a broad bandwidth of ECG. The objective was to develop a device with sufficient computing power to integrate the signal processing algorithms developed by the IADI laboratory, to eliminate the noise superimposed on the signals. The third part was dedicated to the construction of a sensor network from N sensors. The goal was to multiply the number of measurement electrodes to increase the spatial resolution of the ECG and reconstruct a 12-lead ECG during MRI examination. The purpose of this work is noninvasive ECG imaging from surface electrical potential maps and from anatomical models of patients obtained simultaneously by MRI. The fourth part presents a new method of real-time correction of ECG signals from a high frequency sampling acquisition, based on the device developed. The fifth and last part presents another application of this sensor in the interventional electrophysiology room, during the activation of a Magnetic Navigation System of the catheter, which generates disturbances similar to those observed in MRI.

In today’s research and market, IT applications for health-care are gaining huge interest of both IT and medical researchers. Cardiovascular diseases (CVDs) are considered the largest cause of death for both men and women regardless of ethnic backgrounds. More efficient treatments and most importantly efficient methods of cardiac diagnosis that examine heart diseases are desired. Electrocardiography (ECG) is an essential method used to diagnose heart diseases. However, diagnosing any cardiovascular disease based on the 12-lead ECG printout from an ECG machine using human eye might seriously impair analysis accuracy. To meet this challenge of today’s ECG analysis methodology, a more reliable solution that can analyze huge amount of patient’s data in real-time is desired. The software solution presented in this article is aimed to reduce the risk while diagnosing cardiovascular diseases (CVDs) by human eye, computation of large-scale patient’s data in real-time at the patient’s location and sending the required results or summary to the doctor/nurse. Keeping in mind the importance of real-time analysis of patient’s data, the software system has built upon small individual algorithms/modules designed for multi-core architecture, where each module is supposed to be processed by an individual core/processor in parallel. All the input and output processes to the analysis system are made automated, which reduces operator’s interaction to the system and thus reducing the cost. The outputs/results of the processing are summarized to smaller files in both ASCII and binary formats to meet the requirement of exchanging the data over Voice and Data Networks.

No description available.

No description available.

В данной магистерской работе мы исследуем возможности построения словаря волн биомедицинских сигналов электрокардиограммы, который в дальнейшем позволит применять методы NLP для обработки временных рядов биомедицинских сигналов. В частности, мы сосредоточимся на анализе структуры пиков и интервалов электрокардиограммы здоровых и больных аритмией и другими заболеваниями людей, средствами языка python и автоматизации этого процесса для извлечения значимой информации из биомедицинских временных рядов ЭКГ. Наша конечная цель – улучшение точности и эффективности обработки и анализа биомедицинских сигналов, что имеет важное значение как для клинической диагностики, так и для научных исследований. Решение этой задачи имеет большое практическое значение для различных областей, таких как медицина, биология и фармакология, где обработка и анализ временных рядов играют важную роль. / In this master's thesis, we are exploring the possibility of constructing a dictionary of waves of biomedical electrocardiogram signals, which in the future will allow the use of NLP methods for processing time series of biomedical signals. In particular, we will focus on analyzing the structure of peaks and intervals of the electrocardiogram of healthy people and patients with arrhythmia and other diseases, using the Python language and automating this process to extract meaningful information from biomedical ECG time series. Our ultimate goal is to improve the accuracy and efficiency of biomedical signal processing and analysis, which is important for both clinical diagnostics and scientific research. The solution to this problem is of great practical importance for various fields, such as medicine, biology and pharmacology, where processing and analysis of time series play an important role.

Objectif : L’épilepsie est l’un des troubles neurologiques les plus courants, caractérisée par des crises récurrentes imprévisibles dues à des décharges neuronales excessives. En fonction de la localisation, l’intensité et la propagation des décharges ictales, les crises peuvent s’accompagner de signes et de symptômes divers tels qu’une altération de l’état de conscience, mouvements tonico-cloniques et variations du rythme cardiaque. Les crises non contrôlées augmentent le risque de blessures, et même le risque de mort subite inattendue en épilepsie. Une intervention rapide pourrait minimiser les complications et réduire le risque de mortalité lié aux crises. Les objets connectés capables de détecter les crises d’épilepsie pourraient offrir une solution précieuse pour assurer une surveillance continue des patients vivant avec l’épilepsie. L’objectif de cette étude était de développer et d’évaluer un système de détection automatique des crises focales à bilatérales tonico-cloniques (FBTCS) avec un chandail multimodal connecté. Méthodes : En utilisant le chandail connecté Hexoskin, nous avons collecté les données d’électrocardiogramme et d’accélération chez les patients avec épilepsie admis à l’unité de monitoring d’épilepsie du Centre Hospitalier de l’Université de Montréal (CHUM). Nous avons développé un système automatisé pour analyser les enregistrements continus. Nous avons ensuite entraîné un algorithme d’apprentissage automatique pour détecter automatiquement les FBTCS. Nous avons validé les performances à l’aide d’une approche de validation croisée imbriquée. Résultats : Nous avons enregistré 66 crises FBTCS chez 42 patients qui ont porté le chandail connecté pendant un total de 8067 heures. L’algorithme de détection des crises a atteint une sensibilité de 84.8%, avec un taux médian de fausses alarmes de 0.55/24h. L’aire sous la courbe caractéristique opérationnelle du récepteur (ROC-AUC) était de 0.90 (IC à 95% : 0.88 - 0.91). Conclusion : Nous proposons le premier système basé sur un chandail connecté pour la détection des FBTCS. Notre étude montre des résultats prometteurs en utilisant une approche rétrospective dans un environnement hospitalier. Des études prospectives sont nécessaires pour valider les résultats dans un environnement résidentiel en utilisant un algorithme de détection des crises en temps réel. / Objective: Epilepsy is one of the most common neurological disorders, characterized by recurrent unpredictable seizures due to excessive neuronal discharges. Depending on the location, intensity and propagation of the ictal discharge, seizures may be accompanied by various symptoms and signs such as impaired awareness, involuntary tonic-clonic movements, and abnormal heart rate changes. Uncontrolled seizures increase the risk for seizure-related injuries and even the risk for sudden unexpected death in epilepsy. Rapid intervention could potentially reduce seizure-related complications and mortality risk. Wearable devices capable of detecting epileptic seizures could provide a valuable solution for the continuous monitoring of patients with epilepsy. The aim of this study was to develop and evaluate an automated system for the detection of focal to bilateral tonic-clonic seizures (FBTCS) using a novel multimodal connected shirt. Methods: We used the Hexoskin connected shirt to collect electrocardiogram and accelerometry data from patients with epilepsy admitted to the epilepsy monitoring unit of University of Montreal Hospital Centre (CHUM). We developed an automated system to analyze continuous recordings. Then, we trained a machine learning algorithm to automatically detect FBTCS. We validated the performances using a nested cross-validation approach. Results: We recorded 66 FBTCS from 42 patients who wore the connected shirt during a total of 8067 hours. The seizure detection algorithm reached a sensitivity of 84.8%, with a median false alarm rate of 0.55/24h. The area under the receiver operating characteristic curve (ROC-AUC) was 0.90 (95% CI: 0.88 - 0.91). Conclusion: We propose the first shirt-based system for the detection of FBTCS. Our study shows promising findings with a retrospective approach in a hospital setting. Prospective studies are required to validate the findings in a residential setting using a real-time online seizure detection algorithm.

The survival rate for a suddent cardiac arrest (SCA) is incredibly low, with less than one in ten surviving; most SCAs occur outside of a hospital setting. There is a need to develop an effective and efficient system that can sense, communicate and remediate potential SCA situations on a near real-time basis. This research presents a novel Zeolite-PDMS-based optically unobtrusive flexible dry electrodes for biosignal acquisition from various subjects while at rest and in motion. Two zeolite crystals (4A and 13X) are used to fabricate the electrodes. Three different sizes and two different filler concentrations are compared to identify the better performing electrode suited for electrocardiogram (ECG) data acquisition. A low-power, low-noise amplifier with chopper modulation is designed and implemented using the standard 180nm CMOS process. A commercial off-the-shelf (COTS) based wireless system is designed for transmitting ECG signals. Further, this dissertation provides a framework for Machine Learning Classification algorithms on large, open-source Arrhythmia and SCA datasets. Supervised models with features as the input data and deep learning models with raw ECG as input are compared using different methods. The machine learning tool classifies the datasets within a few minutes, saving time and effort for the physicians. The experimental results show promising progress towards advancing the development of a wireless ECG recording system combined with efficient machine learning models that can positively impact SCA outcomes.

Insider threat is one of the greatest concerns for information security that could cause more significant financial losses and damages than any other attack. However, implementing an efficient detection system is a very challenging task. It has long been recognized that solutions to insider threats are mainly user-centric and several psychological and psychosocial models have been proposed. A user's psychophysiological behavior measures can provide an excellent source of information for detecting user's malicious behaviors and mitigating insider threats. In this dissertation, we propose a multi-modal framework based on the user's psychophysiological measures and computer-based behaviors to distinguish between a user's behaviors during regular activities versus malicious activities. We utilize several psychophysiological measures such as electroencephalogram (EEG), electrocardiogram (ECG), and eye movement and pupil behaviors along with the computer-based behaviors such as the mouse movement dynamics, and keystrokes dynamics to build our framework for detecting malicious insiders. We conduct human subject experiments to capture the psychophysiological measures and the computer-based behaviors for a group of participants while performing several computer-based activities in different scenarios. We analyze the behavioral measures, extract useful features, and evaluate their capability in detecting insider threats. We investigate each measure separately, then we use data fusion techniques to build two modules and a comprehensive multi-modal framework. The first module combines the synchronized EEG and ECG psychophysiological measures, and the second module combines the eye movement and pupil behaviors with the computer-based behaviors to detect the malicious insiders. The multi-modal framework utilizes all the measures and behaviors in one model to achieve better detection accuracy. Our findings demonstrate that psychophysiological measures can reveal valuable knowledge about a user's malicious intent and can be used as an effective indicator in designing insider threat monitoring and detection frameworks. Our work lays out the necessary foundation to establish a new generation of insider threat detection and mitigation mechanisms that are based on a user's involuntary behaviors, such as psychophysiological measures, and learn from the real-time data to determine whether a user is malicious.