A lo largo de la última década hemos asistido a un desarrollo sin precedentes de las tecnologías de la salud. Los avances en la informatización, la creación de redes, las técnicas de imagen, la robótica, las micro/nano tecnologías, y la genómica, han contribuido a aumentar significativamente la cantidad y diversidad de información al alcance del personal clínico para el diagnóstico, pronóstico, tratamiento y seguimiento de los pacientes. Este aumento en la cantidad y diversidad de datos clínicos requiere del continuo desarrollo de técnicas y metodologías capaces de integrar estos datos, procesarlos, y dar soporte en su interpretación de una forma robusta y eficiente. En este contexto, esta Tesis se focaliza en el análisis y procesado de señales biomédicas y su uso en problemas de clasificación automática. Es decir, se focaliza en: el diseño e integración de algoritmos para el procesado automático de señales biomédicas, el desarrollo de nuevos métodos de extracción de características para señales, la evaluación de compatibilidad entre señales biomédicas, y el diseño de modelos de clasificación para problemas clínicos específicos. En la mayoría de casos contenidos en esta Tesis, estos problemas se sitúan en el ámbito de los sistemas de apoyo a la decisión clínica, es decir, de sistemas computacionales que proporcionan conocimiento experto para la decisión en el diagnóstico, pronóstico y tratamiento de los pacientes. Una de las principales contribuciones de esta tesis consiste en la evaluación de la compatibilidad entre espectros de resonancia magnética (ERM) obtenidos mediante dos tecnologías de escáneres de resonancia magnética coexistentes en la actualidad (escáneres de 1.5T y de 3T). Esta compatibilidad se evalúa en el contexto de clasificación automática de tumores cerebrales. Los resultados obtenidos en este trabajo sugieren que los clasificadores existentes basados en datos de ERM de 1.5T pueden ser aplicables a casos obtenidos con la nueva tecnolog / Fuster García, E. (2012). Biomedical signal analysis in automatic classification problems [Tesis doctoral]. Editorial Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/17176 / Palancia

Personal telehealth plays a crucial role in addressing global challenges of aging population and rising cost for health care. Tiny and wirelessly connected medical sensors, for example embedded in clothes or on the body, will be an integrated part of lifestyle, and will allow hospitals to remotely diagnose patients in their home.  In this thesis, a wireless bio-sensing with smart phone based monitoring system is proposed to provide a home based telehealth care for continuous monitoring. The system consists of two main parts: a wireless sensor and a health application on the smart phone. This thesis is to design the first part of the system - a wireless temperature and electrocardiography (ECG) sensor. The sensor integrates ECG front-end analog block, a micro-controller and a Bluetooth low energy (BLE) connectivity IC on a single board. To achieve the miniaturization of the sensor and users’ comfort in mind, the sensor is designed as a miniaturized hybrid system utilizing flexible batteries and printed electrodes. This can efficiently detect ECG signals and transfer them to a smart phone through BLE link.

Many animal models have been established for the study of myocardial remodeling and heart failure due to its status as the number one cause of mortality worldwide. In humans, a pathologic occlusion forms in a coronary artery and reperfusion of that occluded artery is considered essential to maintain viability of the myocardium at risk. Although essential for myocardial recovery, reperfusion of the ischemic myocardium creates its own tissue injury. The physiologic response and healing of an ischemia/reperfusion injury is different from a chronic occlusion injury. Myocardial ischemia/reperfusion injury is gaining recognition as a clinically relevant model for myocardial infarction studies. For this reason, parallel animal models of ischemia/reperfusion are vital in advancing the knowledge base regarding myocardial injury. Typically, ischemia of the mouse heart after left anterior descending (LAD) coronary artery occlusion is confirmed by visible pallor of the myocardium below the occlusion (ligature). However, this offers only a subjective way of confirming correct or consistent ligature placement, as there are multiple major arteries that could cause pallor in different myocardial regions. A method of recording electrocardiographic changes to assess correct ligature placement and resultant ischemia as well as reperfusion, to supplement observed myocardial pallor, would help yield consistent infarct sizes in mouse models. In turn, this would help decrease the number of mice used. Additionally, electrocardiographic changes can continue to be recorded non-invasively in a time-dependent fashion after the surgery. This article will demonstrate a method of electrocardiographically confirming myocardial ischemia and reperfusion in real time.

In this thesis, many machine learning algorithms were applied to electrocardiogram (ECG), spectral analysis, and Field Programmable Gate Arrays (FPGAs). In ECG, QRS complexes are useful for measuring the heart rate and for the segmentation of ECG signals. QRS complexes were detected using WaveletCNN Autoencoder filters and ConvLSTM detectors. The WaveletCNN Autoencoders filters the ECG signals using the wavelet filters, while the ConvLSTM detects the spatial temporal patterns of the QRS complexes. For the spectral analysis topic, the detection of chemical compounds using spectral analysis is useful for identifying unknown substances. However, spectral analysis algorithms require vast amounts of data. To solve this problem, B-spline neural networks were developed for the generation of infrared and ultraviolet/visible spectras. This allowed for the generation of large training datasets from a few experimental measurements. Graphical Processing Units (GPUs) are good for training and testing neural networks. However, using multiple GPUs together is hard because PCIe bus is not suited for scattering operations and reduce operations. FPGAs are more flexible as they can be arranged in a mesh or toroid or hypercube configuration on the PCB. These configurations provide higher data throughput and results in faster computations. A general neural network framework was written in VHDL for Xilinx FPGAs. It allows for any neural network to be trained or tested on FPGAs. / Graduate

No description available.

No description available.

Atrial fibrillation is one of the most common types of heart arrhythmias, which can cause irregular, weak and fast atrial contractions up to 600 beats per minute. Atrial fibrillation has increased prevalence with age and is associated with increased risks of ischemia, as blood clots can form due to the weak contractions. During prolonged periods of atrial fibrillation, the atria can undergo a process called atrial remodelling. This causes electrophysiological and structural changes to the atria such as increased atrial size and changes to calcium ion densities. These changes themselves promotes the initiation and propagation of atrial fibrillation, which makes early detection crucial. Fortunately, atrial fibrillation can be detected on an electrocardiogram. Electrocardiograms measures the electrical activity of the heart during its cardiac cycle. This includes the initiation of the action potential, the depolarization of the atria and ventricles and their repolarization. On the electrocardiogram recording, these are seen as peaks and valleys, where each peak and valley can be traced back to one of these events. This means that during atrial fibrillation, the weak, irregular and fast atrial contractions can all be detected and measured. The aim of this project was to develop a machine learning model that could predict onset of atrial fibrillation, and that could classify ongoing atrial fibrillation. This was achieved by training one multiclass classification machine learning model using XGBoost, and three binary classification machine learning models using ROSETTA, on electrocardiogram recordings of people with and without atrial fibrillation. XGBoost is a tree boosting system which uses tree-like structures to classify data, while ROSETTA is a rule-based classification model which creates rules in an IF and THEN format to make decisions. The recordings were labelled according to three different classes: no atrial fibrillation, atrial fibrillation or preceding atrial fibrillation. The XGBoost model had a prediction accuracy of 99.3%, outperforming the three ROSETTA models and other atrial fibrillation classification and prediction models found. The ROSETTA models had high accuracies on the learning set, however, the predictions were subpar, indicating faulty settings for this type of data. The results in this project indicate that the models created can be used to accurately classify and predict onset of and ongoing atrial fibrillation, serving as a tool for early detection and verification of diagnosis.

Federated learning is a framework in machine learning that allows for training a model while maintaining data privacy. Moreover, it allows clients with their own data to collaborate in order to build a stronger, shared model. Federated learning is of particular interest to healthcare data, since it is of the utmost importance to respect patient privacy while still building useful diagnostic tools. However, healthcare data can be complicated — data format might differ across providers, leading to unexpected inputs and incompatibility between different providers. For example, electrocardiograms might differ in sampling rate or number of leads used, meaning that a classifier trained at one hospital might be useless to another. We propose using autoencoders to address this problem, transforming important information contained in electrocardiograms to a uniform input, where federated learning can then be used to train a strong classifier for multiple healthcare providers. Furthermore, we propose using statistically-guided hyperparameter tuning to ensure fast convergence of the model.

The Apple Watch is capable of recording single-lead electrocardiograms (ECGs). To incorporate such devices in routine medical care, the reliability of such devices to obtain precordial leads needs to be validated. The purpose of this study was to assess the feasibility and reliability of a smartwatch (SW) to obtain precordial leads compared to standard ECGs. We included 100 participants (62 male, aged 62.8 ± 13.1 years) with sinus rhythm and recorded a standard 12-lead ECG and the precordial leads with the Apple Watch. The ECGs were quantitively compared. A total of 98 patients were able to record precordial leads without assistance. A strong correlation was observed between the amplitude of the standard and SW-ECGs’ waves, in terms of P waves, QRS-complexes, and T waves (all p-values < 0.01). A significant correlation was observed between the two methods regarding the duration of the ECG waves (all p-values < 0.01). Assessment of polarity showed a significant and a strong concordance between the ECGs’ waves in all six leads (91–100%, all p-values < 0.001). In conclusion, 98% of patients were able to record precordial leads using a SW without assistance. The SW is feasible and reliable for obtaining valid precordial-lead ECG recordings as a validated alternative to a standard ECG.

Some of the recently released smartwatch products feature a single-lead electrocardiogram (ECG) recording capability. The reliability of obtaining 3-lead ECG with smartwatches is yet to be confirmed in a large study. This study aimed to assess the feasibility and reliability of smartwatch to obtain 3-lead ECG recordings, the classical Einthoven ECG leads I-III compared to standard ECG. To record lead I, the watch was worn on the left wrist and the right index finger was placed on the digital crown for 30 s. For lead II, the watch was placed on the lower abdomen and the right index finger was placed on the digital crown for 30 s. For lead III, the same process was repeated with the left index finger. Spearman correlation and Bland-Altman tests were used for data analysis. A total of 300 smartwatch ECG tracings were successfully obtained. ECG waves’ characteristics of all three leads obtained from the smartwatch had a similar duration, amplitude, and polarity compared to standard ECG. The results of this study suggested that the examined smartwatch (Apple Watch Series 4) could obtain 3-lead ECG tracings, including Einthoven leads I, II, and III by placing the smartwatch on the described positions.