Cardiac Arrhythmia Classification Using Advanced Deep Learning Techniques on Digitized ECG Datasets.

ECG classification or heartbeat classification is an extremely valuable tool in cardiology. Deep learning-based techniques for the analysis of ECG signals assist human experts in the timely diagnosis of cardiac diseases and help save precious lives. This research aims at digitizing a dataset of images of ECG records into time series signals and then applying deep learning (DL) techniques on the digitized dataset. State-of-the-art DL techniques are proposed for the classification of the ECG signals into different cardiac classes. Multiple DL models, including a convolutional neural network (CNN), a long short-term memory (LSTM) network, and a self-supervised learning (SSL)-based model using autoencoders are explored and compared in this study. The models are trained on the dataset generated from ECG plots of patients from various healthcare institutes in Pakistan. First, the ECG images are digitized, segmenting the lead II heartbeats, and then the digitized signals are passed to the proposed deep learning models for classification. Among the different DL models used in this study, the proposed CNN model achieves the highest accuracy of ∼92%. The proposed model is highly accurate and provides fast inference for real-time and direct monitoring of ECG signals that are captured from the electrodes (sensors) placed on different parts of the body. Using the digitized form of ECG signals instead of images for the classification of cardiac arrhythmia allows cardiologists to utilize DL models directly on ECG signals from an ECG machine for the real-time and accurate monitoring of ECGs.

A novel diagnosis method combined dual-channel SE-ResNet with expert features for inter-patient heartbeat classification.

As the number of patients with cardiovascular diseases (CVDs) increases annually, a reliable and automated system for detecting electrocardiogram (ECG) abnormalities is becoming increasingly essential. Scholars have developed numerous methods of arrhythmia classification using machine learning or deep learning. However, the issue of low classification rates of individual classes in inter-patient heartbeat classification remains a challenge. This study proposes a method for inter-patient heartbeat classification by fusing dual-channel squeeze-and-excitation residual neural networks (SE-ResNet) and expert features. In the preprocessing stage, ECG heartbeats extracted from both leads of ECG signals are filtered and normalized. Additionally, nine features representing waveform morphology and heartbeat contextual information are selected to be fused with the deep neural networks. Using different filter and kernel sizes for each block, the SE-residual block-based model can effectively learn long-term features between heartbeats. The divided ECG heartbeats and extracted features are then input to the improved SE-ResNet for training and testing according to the inter-patient scheme. The focal loss is utilized to handle the heartbeat of the imbalance category. The proposed arrhythmia classification method is evaluated on three open-source databases, and it achieved an overall F1-score of 83.39 % in the MIT-BIH database. This system can be applied in the scenario of daily monitoring of ECG and plays a significant role in diagnosing arrhythmias.

Energy-efficient dynamic sensor time series classification for edge health devices.

BACKGROUND AND OBJECTIVE: Time series data plays a crucial role in the realm of the Internet of Things Medical (IoMT). Through machine learning (ML) algorithms, online time series classification in IoMT systems enables reliable real-time disease detection. Deploying ML algorithms on edge health devices can reduce latency and safeguard patients' privacy. However, the limited computational resources of these devices underscore the need for more energy-efficient algorithms. Furthermore, online time series classification inevitably faces the challenges of concept drift (CD) and catastrophic forgetting (CF). To address these challenges, this study proposes an energy-efficient Online Time series classification algorithm that can solve CF and CD for health devices, called OTCD. METHODS: OTCD first detects the appearance of concept drift and performs prototype updates to mitigate its impact. Afterward, it standardizes the potential space distribution and selectively preserves key training parameters to address CF. This approach reduces the required memory and enhances energy efficiency. To evaluate the performance of the proposed model in real-time health monitoring tasks, we utilize electrocardiogram (ECG) and photoplethysmogram (PPG) data. By adopting various feature extractors, three arrhythmia classification models are compared. To assess the energy efficiency of OTCD, we conduct runtime tests on each dataset. Additionally, the OTCD is compared with state-of-the-art (SOTA) dynamic time series classification models for performance evaluation. RESULTS: The OTCD algorithm outperforms existing SOTA time series classification algorithms in IoMT. In particular, OTCD is on average 2.77% to 14.74% more accurate than other models on the MIT-BIH arrhythmia dataset. Additionally, it consumes low memory (1 KB) and performs computations at a rate of 0.004 GFLOPs per second, leading to energy savings and high time efficiency. CONCLUSION: Our proposed algorithm, OTCD, enables efficient real-time classification of medical time series on edge health devices. Experimental results demonstrate its significant competitiveness, offering promising prospects for safe and reliable healthcare.

S4D-ECG: A Shallow State-of-the-Art Model for Cardiac Abnormality Classification.

PURPOSE: This study introduces an algorithm specifically designed for processing unprocessed 12-lead electrocardiogram (ECG) data, with the primary aim of detecting cardiac abnormalities. METHODS: The proposed model integrates Diagonal State Space Sequence (S4D) model into its architecture, leveraging its effectiveness in capturing dynamics within time-series data. The S4D model is designed with stacked S4D layers for processing raw input data and a simplified decoder using a dense layer for predicting abnormality types. Experimental optimization determines the optimal number of S4D layers, striking a balance between computational efficiency and predictive performance. This comprehensive approach ensures the model's suitability for real-time processing on hardware devices with limited capabilities, offering a streamlined yet effective solution for heart monitoring. RESULTS: Among the notable features of this algorithm is its strong resilience to noise, enabling the algorithm to achieve an average F1-score of 81.2% and an AUROC of 95.5% in generalization. The model underwent testing specifically on the lead II ECG signal, exhibiting consistent performance with an F1-score of 79.5% and an AUROC of 95.7%. CONCLUSION: It is characterized by the elimination of pre-processing features and the availability of a low-complexity architecture that makes it suitable for implementation on numerous computing devices because it is easily implementable. Consequently, this algorithm exhibits considerable potential for practical applications in analyzing real-world ECG data. This model can be placed on the cloud for diagnosis. The model was also tested on lead II of the ECG alone and has demonstrated promising results, supporting its potential for on-device application.

Arrhythmia classification based on multi-feature multi-path parallel deep convolutional neural networks and improved focal loss.

Early diagnosis of abnormal electrocardiogram (ECG) signals can provide useful information for the prevention and detection of arrhythmia diseases. Due to the similarities in Normal beat (N) and Supraventricular Premature Beat (S) categories and imbalance of ECG categories, arrhythmia classification cannot achieve satisfactory classification results under the inter-patient assessment paradigm. In this paper, a multi-path parallel deep convolutional neural network was proposed for arrhythmia classification. Furthermore, a global average RR interval was introduced to address the issue of similarities between N vs. S categories, and a weighted loss function was developed to solve the imbalance problem using the dynamically adjusted weights based on the proportion of each class in the input batch. The MIT-BIH arrhythmia dataset was used to validate the classification performances of the proposed method. Experimental results under the intra-patient evaluation paradigm and inter-patient evaluation paradigm showed that the proposed method could achieve better classification results than other methods. Among them, the accuracy, average sensitivity, average precision, and average specificity under the intra-patient paradigm were 98.73%, 94.89%, 89.38%, and 98.24%, respectively. The accuracy, average sensitivity, average precision, and average specificity under the inter-patient paradigm were 91.22%, 89.91%, 68.23%, and 95.23%, respectively.

Manuseio atual das arritmias ventriculares na fase aguda do infarto do miocárdio / Management of ventricular arrhythmias in the setting of acute myocardial infarction

As arritmias ventriculares sustentadas são o principal mecanismo de morte súbita. Frequentemente são a primeira manifestação da doença arterial coronariana, e mesmo quando eficazmente revertidas estão associadas a maior mortalidade intra-hospitalar. Várias anormalidades eletrofisiológicas resultam da isquemia miocárdica. Mecanismos como reentrada, automatismo aumentado e atividade deflagrada estão envolvidos na gênese das arritmias ventriculares na fase aguda do infarto. O conhecimento dos mecanismos e das estratégias de prevenção e tratamento dessas arritmias é essencial no manejo bem-sucedido dos pacientes na fase aguda do infarto do miocárdio.

Arritmias cardíacas: incidência, classificaçäo e correlaçäo clínico-eletrocardiográfica / Cardiac arrhythmias: ocorrence, classification and clinical and eletrocardiogram analyses

Arritmias cardíacas podem ser um achado casual durante o exame cardiológico ambulatorial, nÝo havendo, necessariamente, queixas relacionadas a distúrbios do ritmo cardíaco. Objetivando identificar arritmias mais frequentes nos pacientes de primeira consulta no ambulatório de cardiologia do HU, utilizou-se o eletrocardiograma convencional para a análise, no período de maio/93 a maio/94. Os resultados mostram arritmias em 713 de 4116 pacientes (17.32 por cento). Bradicardia sinusal foi, isoladamente, mais frequente (28.46 por cento). De maneira associada foi mais frequente a extrassistole supra e ventricular (38.09 por cento). Estes achados, ocorrendo sobretudo na faixa etária entre 40-60 anos, podem estar relacionados com complicaçöes da Hipertensäo Arterial e aterosclerose coronariana

Arritmias no infarto agudo do miocárdio / Arrhythmias in acute myocardial infarction

Há alta incidência de arritmias no pós-infarto agudo do miocárdio. Distúrbios no ritmo e na condução estão entre as primeiras complicaçöes descritas. Embora eses distúrbios sejam claramente menos comuns em pacientes tratados com terapia fibrinolítica, permanecem uma contínua fonte de problemas para os clínicos que cuidam de pacientes com infarto agudo do miocárdio. Além disso, incertezas acerca da utilização de medidas terapêuticas, medidas profiláticas e prognóstico a curto e longo prazos têm estimulado a realização de vários estudos no sentido de definição de prognóstico a curto e longo prazos têm estimulado a realização de vários estudos no sentido de definição de prognóstico, prevenção e tratamento das arritmias no infarto agudo do miocárdio. Neste artigo, os autores abordam o manuseio clínico das arritmias no infarto agudo do miocárdio, com ênfase na incidência, no prognóstico, na prevenção e no tratamento.

Arritmias cardíacas / Cardiac arrhythmias

As arritmias cardíacas são responsáveis por uma taxa significativa de mortalidade em doenças cardiovasculares. A decisão sobre o tratamento é freqüentemente tomada na unidade de emergência. O eletrocardiograma (ECG) é um exame importante, que pode proporcionar informações diagnósticas precisas na avaliação de pacientes com arritmias. Os autores apresentam uma abordagem atualizada para o diagnóstico, avaliação clínica e tratamentos farmacológico e não-farmacológico das arritmias ventriculares e supreventriculares.

Enfoque Práctico de las Arritmias de Urgencia

Existen ciertas reglas de oro que facilitan la evaluación de un pacientecon arritmia y encausan hacia el adecuado manejo de estos pacientes según el tipo de arritmia que padezcan ya sea ventricuar o supraventricular y si se trata de una emergencia o no. Este último criterrio se evalúa con base en el estado hemodinámico del paciente; es por esto que una arritmia supraventricular catalogada como emergencia se trata con cardioversión eléctrica, si no lo es se debe determinar el ritmo, evaluar los síntomas del paciente manejar la respuesta ventricular, intervalo R-R, restaurar el ritmo sinusal, prevenir la recurrencia y curar la arritmia en los casos en que sea posible. Si se está frente a una arritmia ventricular y es una emergencia la conducta a seguir es cardioversión eléctrica; si no es emergencia pero es maligna se debe optar por un manejo agresivo y si no es maligna se debe estudiar al paciente de manera íntegra

Electrocardiografía clínica. Parte III: Arritmias

En esta tercera parte de electrocardiográfia clínica se revisan los principios fisiopatológicos y los patrones electrográficos de las arritmias, tanto supraventriculares como ventriculares: Taquicardía sinusual, bradicardia sinusual, paro sinusual, taquicardia auricular paroxística, flutter auricular, fibrilación auricular, taquicardia ventricular, fibrilación ventricular, y las extrasístoles auriculares y ventriculares

Arritmias cardíacas / Cardiac arrhythmias

The autor makes a reviesw about genesis of cardiac arrhytmias, diagnostic and management of arrhytmias

Arritmias perioperatorias: diagnostico y manejo / Perioperatory arrhythmias: diagnosis and management

Las arritmias durante procedimientos anestesicos son muy frecuentes, reportan incidencias de 18% hasta 84% segun el tipo de estudio. Los factores etiopatogenicos incluyen el tipo de cirugia (de torax, de cuello, cirugias prolongadas, neurocirugia) cardiopatias previas, uso de drogas como digitalicos en el preoperatorio, alteraciones hidroelectroliticas y acidobasicas, anestesicos y otras drogas utilizadas, profundidad anestesica, etc. Dentro de las arritmias mas frecuentes se reportan: marcapaso auricular migratorio, diasociacion AV isorritmica, ritmo nodal, extrasistoles supraventriculares, taquicardia parovistica supraventricular y ventricular. Se revisa la actividad electrica normal del corazon y los mecanismos de arritmogenesis: automaticidad anormal (incluyendo la actividad gatillo), alteraciones de la conduccin, y mezclas de los dos, como la reentrada y la parasitolia

Bradiarritmias: abordagem clínica e tratamento / Bradiarrhythmias: clinical approach and treatment

Este artigo revisa a abordagem clínica das bradiarritmias, com ênfase no diagnóstico, ressaltando a importância da anamnese, exame físico e das alteraçöes eletrocardiográficas como principais orientadores da terapêutica

Arritmias cardíacas: enfoque general / Cardiac arrhymias: general focus

Las arritmias cardíacas constituyen una causa importante de morbimortalidad, sobre todo, las arritmias ventriculares en pacientes con enfermedad isquémica y disfunción del ventrículo izquierdo. Diferentes procedimientos de estudio han permitido definir varios mecanismos de arritmogénesis y diseñar estrategias de manejo más adecuadas tomando en cuenta la forma de producción, la enfermedad de base, su asociación con síntomas y no sólo la presencia de la arritmia. En este trabajo hacemos una revisión de las formas de presentación clínica electrocardiográfica, mecanismos de producción, aproximación diagnóstica y terapéutica para manejo a largo plazo y de emergencia de los diferentes tipos de arritmias, tanto supraventriculares como ventriculares. Se discute de manera escueta los resultados de los grandes estudios sobre tratamiento de arritmias ventriculares ya publicados por diferentes tipos en poblaciones diversas de pacientes (insuficiencia cardíaca, post-infarto agudo del miocardio, sobrevivientes de arresto cardíaco, etc.). Hacemos énfasis en la utilidad de las nuevas formas de manejo no farmacológico de las arritmias (ablación por energía de radiofrecuencia, desfibriladores cardio-vertores automáticos implantables)