Computational Diagnostic Techniques for Electrocardiogram Signal Analysis

A coordinated adaptive multiscale enhanced spatio-temporal fusion network for multi-lead electrocardiogram arrhythmia detection

The multi-lead electrocardiogram (ECG) is widely utilized in clinical diagnosis and monitoring of cardiac conditions. The advancement of deep learning has led to the emergence of automated multi-lead ECG diagnostic networks, which have become essential in the fields of biomedical engineering and clinical cardiac disease diagnosis. Intelligent ECG diagnosis techniques encompass Recurrent Neural Networks (RNN), Transformers, and Convolutional Neural Networks (CNN). While CNN is capable of extracting local spatial information from images, it lacks the ability to learn global spatial features and temporal memory features. Conversely, RNN relies on time and can retain significant sequential features. However, they are not proficient in extracting lengthy dependencies of sequence data in practical scenarios. The self-attention mechanism in the Transformer model has the capability of global feature extraction, but it does not adequately prioritize local features and cannot extract spatial and channel features. This paper proposes STFAC-ECGNet, a model that incorporates CAMV-RNN block, CBMV-CNN block, and TSEF block to enhance the performance of the model by integrating the strengths of CNN, RNN, and Transformer. The CAMV-RNN block incorporates a coordinated adaptive simplified self-attention module that adaptively carries out global sequence feature retention and enhances spatial-temporal information. The CBMV-CNN block integrates spatial and channel attentional mechanism modules in a skip connection, enabling the fusion of spatial and channel information. The TSEF block implements enhanced multi-scale fusion of image spatial and sequence temporal features. In this study, comprehensive experiments were conducted using the PTB-XL large publicly available ECG dataset and the China Physiological Signal Challenge 2018 (CPSC2018) database. The results indicate that STFAC-ECGNet surpasses other cutting-edge techniques in multiple tasks, showcasing robustness and generalization.

Development and Validation of a Real-Time Service Model for Noise Removal and Arrhythmia Classification Using Electrocardiogram Signals

Arrhythmias range from mild nuisances to potentially fatal conditions, detectable through electrocardiograms (ECGs). With advancements in wearable technology, ECGs can now be monitored on-the-go, although these devices often capture noisy data, complicating accurate arrhythmia detection. This study aims to create a new deep learning model that utilizes generative adversarial networks (GANs) for effective noise removal and ResNet for precise arrhythmia classification from wearable ECG data. We developed a deep learning model that cleans ECG measurements from wearable devices and detects arrhythmias using refined data. We pretrained our model using the MIT-BIH Arrhythmia and Noise databases. Least squares GANs were used for noise reduction, maintaining the integrity of the original ECG signal, while a residual network classified the type of arrhythmia. After initial training, we applied transfer learning with actual ECG data. Our noise removal model significantly enhanced data clarity, achieving over 30 dB in a signal-to-noise ratio. The arrhythmia detection model was highly accurate, with an F1-score of 99.10% for noise-free data. The developed model is capable of real-time, accurate arrhythmia detection using wearable ECG devices, allowing for immediate patient notification and facilitating timely medical response.

Pain prediction model based on machine learning and SHAP values for elders with dementia in Taiwan

INTRODUCTION

Pain conditions are common in elderly individuals, including those with dementia. However, symptoms associated with dementia may lead to poor recognition, assessment and management of pain. In this study, we incorporated the variables based on questionnaires into a machine learning algorithm to build a prediction model for the pain index of elderly individuals with dementia.

MATERIALS AND METHODS

In this study, 113 cases were collected through questionnaires and used to build prediction models for the patient's pain index. Three machine learning algorithms were incorporated for comparison in this study. To interpret the prediction model, SHapley additive explanations values were used to depict the ranking importance of variables and the relationship between features and pain index.

RESULTS

In the comparison of models, random forests with feature selection outperformed in terms of root mean square error and mean absolute error. A total of 11 features were selected based on embedded method. The results showed that the Karnofsky scale played a key role in predicting pain index for elderly individuals with dementia and was positively associated with pain index. Arthritis is the most important disease to predicting the pain index.

CONCLUSIONS

Our findings provided the key insights to predict the pain index of elderly patients with dementia. In the future, it can be used to develop an application system or webpage, which can reduce the use of labour and improve the efficiency.

Exploring a new frontier in cardiac diagnosis: ECG analysis enhanced by machine learning and parametric quartic spline modeling

The heart's study holds paramount importance in human physiology, driving valuable research in cardiovascular health. However, assessing Electrocardiogram (ECG) analysis techniques poses challenges due to noise and artifacts in authentic recordings. The advent of machine learning systems for automated diagnosis has heightened the demand for extensive data, yet accessing medical data is hindered by privacy concerns. Consequently, generating artificial ECG signals faithful to real ones is a formidable task in biomedical signal processing. This paper introduces a method for ECG signal modeling using parametric quartic splines and generating a new dataset based on the modeled signals. Additionally, it explores ECG classification using three machine learning techniques facilitated by Orange software, addressing both normal and abnormal sinus rhythms. The classification enables early detection and prediction of heart-related ailments, facilitating timely clinical interventions and improving patient outcomes. The assessment of synthetic signal quality is conducted through power spectrum analysis and cross-correlation analysis, power spectrum analysis of both real and synthetic ECG waves provides a quantitative assessment of their frequency content, aiding in the validation and evaluation of synthetic ECG signal generation techniques. Cross-correlation analysis revealing a robust correlation coefficient of 0.974 and precise alignment with a negligible time lag of 0.000 s between the synthetic and real ECG signals. Overall, the adoption of quartic spline interpolation in ECG modeling enhances the precision, smoothness, and fidelity of signal representation, thereby improving the effectiveness of diagnostic and analytical tasks in cardiology. Three prominent machine learning algorithms, namely Decision Tree, Logistic Regression, and Gradient Boosting, effectively classify the modeled ECG signals with classification accuracies of 0.98620, 0.98965, and 0.99137, respectively. Notably, all models exhibit robust performance, characterized by high AUC values and classification accuracy. While Gradient Boosting and Logistic Regression demonstrate marginally superior performance compared to the Decision Tree model across most metrics, all models showcase commendable efficacy in ECG signal classification. The study underscores the significance of accurate ECG modeling in health sciences and biomedical technology, offering enhanced accuracy and flexibility for improved cardiovascular health understanding and diagnostic tools.

Super-resolution techniques for biomedical applications and challenges

Super-resolution (SR) techniques have revolutionized the field of biomedical applications by detailing the structures at resolutions beyond the limits of imaging or measuring tools. These techniques have been applied in various biomedical applications, including microscopy, magnetic resonance imaging (MRI), computed tomography (CT), X-ray, electroencephalogram (EEG), ultrasound, etc. SR methods are categorized into two main types: traditional non-learning-based methods and modern learning-based approaches. In both applications, SR methodologies have been effectively utilized on biomedical images, enhancing the visualization of complex biological structures. Additionally, these methods have been employed on biomedical data, leading to improvements in computational precision and efficiency for biomedical simulations. The use of SR techniques has resulted in more detailed and accurate analyses in diagnostics and research, essential for early disease detection and treatment planning. However, challenges such as computational demands, data interpretation complexities, and the lack of unified high-quality data persist. The article emphasizes these issues, underscoring the need for ongoing development in SR technologies to further improve biomedical research and patient care outcomes.

Arrhythmia detection by the graph convolution network and a proposed structure for communication between cardiac leads

One of the most common causes of death worldwide is heart disease, including arrhythmia. Today, sciences such as artificial intelligence and medical statistics are looking for methods and models for correct and automatic diagnosis of cardiac arrhythmia. In pursuit of increasing the accuracy of automated methods, many studies have been conducted. However, in none of the previous articles, the relationship and structure between the heart leads have not been included in the model. It seems that the structure of ECG data can help develop the accuracy of arrhythmia detection. Therefore, in this study, a new structure of Electrocardiogram (ECG) data was introduced, and the Graph Convolution Network (GCN), which has the possibility of learning the structure, was used to develop the accuracy of cardiac arrhythmia diagnosis. Considering the relationship between the heart leads and clusters based on different ECG poles, a new structure was introduced. In this structure, the Mutual Information(MI) index was used to evaluate the relationship between the leads, and weight was given based on the poles of the leads. Weighted Mutual Information (WMI) matrices (new structure) were formed by R software. Finally, the 15-layer GCN network was adjusted by this structure and the arrhythmia of people was detected and classified by it. To evaluate the performance of the proposed new network, sensitivity, precision, specificity, accuracy, and confusion matrix indices were used. Also, the accuracy of GCN networks was compared by three different structures, including WMI, MI, and Identity. Chapman's 12-lead ECG Dataset was used in this study. The results showed that the values of sensitivity, precision, specificity, and accuracy of the GCN-WMI network with 15 intermediate layers were equal to 98.74%, 99.08%, 99.97% & 99.82%, respectively. This new proposed network was more accurate than the Graph Convolution Network-Mutual Information (GCN-MI) with an accuracy equal to 99.71% and GCN-Id with an accuracy equal to 92.68%. Therefore, utilizing this network, the types of arrhythmia were recognized and classified. Also, the new network proposed by the Graph Convolution Network-Weighted Mutual Information (GCN-WMI) was more accurate than those conducted in other studies on the same data set (Chapman). Based on the obtained results, the structure proposed in this study increased the accuracy of cardiac arrhythmia diagnosis and classification on the Chapman data set. Achieving such accuracy for arrhythmia diagnosis is a great achievement in clinical sciences.

A Low-Noise Low-Power 0.001Hz-1kHz Neural Recording System-on-Chip With Sample-Level Duty-Cycling

Advances in brain-machine interfaces and wearable biomedical sensors for healthcare and human-computer interactions call for precision electrophysiology to resolve a variety of biopotential signals across the body that cover a wide range of frequencies, from the mHz-range electrogastrogram (EGG) to the kHz-range electroneurogram (ENG). Existing integrated wearable solutions for minimally invasive biopotential recordings are limited in detection range and accuracy due to trade-offs in bandwidth, noise, input impedance, and power consumption. This article presents a 16-channel wide-band ultra-low-noise neural recording system-on-chip (SoC) fabricated in 65nm CMOS for chronic use in mobile healthcare settings that spans a bandwidth of 0.001 Hz to 1 kHz through a featured sample-level duty-cycling (SLDC) mode. Each recording channel is implemented by a delta-sigma analog-to-digital converter (ADC) achieving 1.0 μ V rms input-referred noise over 1Hz-1kHz bandwidth with a Noise Efficiency Factor (NEF) of 2.93 in continuous operation mode. In SLDC mode, the power supply is duty-cycled while maintaining consistently low input-referred noise levels at ultra-low frequencies (1.1 μV rms over 0.001Hz-1Hz) and 435 M Ω input impedance. The functionalities of the proposed SoC are validated with two human electrophysiology applications: recording low-amplitude electroencephalogram (EEG) through electrodes fixated on the forehead to monitor brain waves, and ultra-slow-wave electrogastrogram (EGG) through electrodes fixated on the abdomen to monitor digestion.

Snippet Policy Network V2: Knee-Guided Neuroevolution for Multi-Lead ECG Early Classification

Early time series classification predicts the class label of a given time series before it is completely observed. In time-critical applications, such as arrhythmia monitoring in ICU, early treatment contributes to the patient's fast recovery, and early warning could even save lives. Hence, in these cases, it is worthy of trading, to some extent, classification accuracy in favor of earlier decisions when the time series data are collected over time. In this article, we propose a novel deep reinforcement learning-based framework, snippet policy network V2 (SPN-V2), for long and varied-length multi-lead electrocardiogram (ECG) early classification. The proposed SNP-V2 contains two main components: snippet representation learning (SRL) and early classification timing learning (ECTL). The SRL is proposed to encode inner-snippet spatial correlations and inter-snippet temporal correlations into the hidden representations of the subsegment (snippet) of the input ECG. ECTL aims to learn a decision agent to classify the time series early and accurately. To optimize the proposed framework, we design a novel knee-guided neuroevolution algorithm (KGNA) to solve cardiovascular diseases' early classification problem, automatically optimizing the proposed SPN-V2 regarding the tradeoff between accuracy and earliness. In addition, we conduct a series of experiments on two real-world ECG datasets. The experimental results show the superiority of the proposed algorithm over the state-of-the-art competing methods.

A piecewise spline approach for modeling of ECG signals

This paper presents a new spline-based modeling method of electrocardiogram (ECG) signal that can reproduce normal as well as abnormal ECG beats. Large volume ECG data is required for automatic machine learning diagnostic systems, medical education, research and testing purposes but due to privacy issues, access to this medical data is very difficult. Given this, modeling an ECG signal is a very challenging task in the field of biomedical signal processing. Spline-based modeling is the latest and one of the most efficient methods with very low computational complexity in the domain of ECG signal generation. In this paper, healthy ECG and arrhythmia conditions have been considered for the synthetic generation, (namely Atrial fibrillation and Congestive heart failure ECG beats) because these are the leading causes of death globally. To validate the performance of the presented modeling method, it is tested on 100 signals, also the percentage root mean square difference (PRD) and the root mean square error (RMSE) have been determined. These calculated values are analyzed and the results are found to be very promising and show that the presented method is one of the best methods in the field of synthetic ECG signal generation. A comparison amongst relevant existing techniques and the proposed method is also presented. The performance merit values PRD and RMSE, for the proposed method obtained are 38.99 and 0.10092, respectively, which are lower than the values obtained in other compared methods. To ensure fidelity of the proposed modeling technique with respect to IEC60601 standard, few Conformance Testing Services (CTS)database signals have also been modelled with a very close resemblance with the standard signals.

Analysis of Publication Activity and Research Trends in the Field of AI Medical Applications: Network Approach

Artificial intelligence (AI) has revolutionized numerous industries, including medicine. In recent years, the integration of AI into medical practices has shown great promise in enhancing the accuracy and efficiency of diagnosing diseases, predicting patient outcomes, and personalizing treatment plans. This paper aims at the exploration of the AI-based medicine research using network approach and analysis of existing trends based on PubMed. Our findings are based on the results of PubMed search queries and analysis of the number of papers obtained by the different search queries. Our goal is to explore how are the AI-based methods used in healthcare research, which approaches and techniques are the most popular, and to discuss the potential reasoning behind the obtained results. Using analysis of the co-occurrence network constructed using VOSviewer software, we detected the main clusters of interest in AI-based healthcare research. Then, we proceeded with the thorough analysis of publication activity in various categories of medical AI research, including research on different AI-based methods applied to different types of medical data. We analyzed the results of query processing in the PubMed database over the past 5 years obtained via a specifically designed strategy for generating search queries based on the thorough selection of keywords from different categories of interest. We provide a comprehensive analysis of existing applications of AI-based methods to medical data of different modalities, including the context of various medical fields and specific diseases that carry the greatest danger to the human population.

From Data to Diagnosis: How Machine Learning Is Changing Heart Health Monitoring

The rapid advances in science and technology in the field of artificial neural networks have led to noticeable interest in the application of this technology in medicine. Given the need to develop medical sensors that monitor vital signs to meet both people's needs in real life and in clinical research, the use of computer-based techniques should be considered. This paper describes the latest progress in heart rate sensors empowered by machine learning methods. The paper is based on a review of the literature and patents from recent years, and is reported according to the PRISMA 2020 statement. The most important challenges and prospects in this field are presented. Key applications of machine learning are discussed in medical sensors used for medical diagnostics in the area of data collection, processing, and interpretation of results. Although current solutions are not yet able to operate independently, especially in the diagnostic context, it is likely that medical sensors will be further developed using advanced artificial intelligence methods.

Knowledge graph analysis and visualization of artificial intelligence applied in electrocardiogram

Background: Electrocardiogram (ECG) provides a straightforward and non-invasive approach for various applications, such as disease classification, biometric identification, emotion recognition, and so on. In recent years, artificial intelligence (AI) shows excellent performance and plays an increasingly important role in electrocardiogram research as well. Objective: This study mainly adopts the literature on the applications of artificial intelligence in electrocardiogram research to focus on the development process through bibliometric and visual knowledge graph methods. Methods: The 2,229 publications collected from the Web of Science Core Collection (WoSCC) database until 2021 are employed as the research objects, and a comprehensive metrology and visualization analysis based on CiteSpace (version 6.1. R3) and VOSviewer (version 1.6.18) platform, which were conducted to explore the co-authorship, co-occurrence and co-citation of countries/regions, institutions, authors, journals, categories, references and keywords regarding artificial intelligence applied in electrocardiogram. Results: In the recent 4 years, both the annual publications and citations of artificial intelligence in electrocardiogram sharply increased. China published the most articles while Singapore had the highest ACP (average citations per article). The most productive institution and authors were Ngee Ann Polytech from Singapore and Acharya U. Rajendra from the University of Technology Sydney. The journal Computers in Biology and Medicine published the most influential publications, and the subject with the most published articles are distributed in Engineering Electrical Electronic. The evolution of research hotspots was analyzed by co-citation references' cluster knowledge visualization domain map. In addition, deep learning, attention mechanism, data augmentation, and so on were the focuses of recent research through the co-occurrence of keywords.

ECG classification using 1-D convolutional deep residual neural network

An electrocardiograph (ECG) is widely used in diagnosis and prediction of cardiovascular diseases (CVDs). The traditional ECG classification methods have complex signal processing phases that leads to expensive designs. This paper provides a deep learning (DL) based system that employs the convolutional neural networks (CNNs) for classification of ECG signals present in PhysioNet MIT-BIH Arrhythmia database. The proposed system implements 1-D convolutional deep residual neural network (ResNet) model that performs feature extraction by directly using the input heartbeats. We have used synthetic minority oversampling technique (SMOTE) that process class-imbalance problem in the training dataset and effectively classifies the five heartbeat types in the test dataset. The classifier's performance is evaluated with ten-fold cross validation (CV) using accuracy, precision, sensitivity, F1-score, and kappa. We have obtained an average accuracy of 98.63%, precision of 92.86%, sensitivity of 92.41%, and specificity of 99.06%. The average F1-score and Kappa obtained were 92.63% and 95.5% respectively. The study shows that proposed ResNet performs well with deep layers compared to other 1-D CNNs.

A robust multiple heartbeats classification with weight-based loss based on convolutional neural network and bidirectional long short-term memory

Background: Analysis of electrocardiogram (ECG) provides a straightforward and non-invasive approach for cardiologists to diagnose and classify the nature and severity of variant cardiac diseases including cardiac arrhythmia. However, the interpretation and analysis of ECG are highly working-load demanding, and the subjective may lead to false diagnoses and heartbeats classification. In recent years, many deep learning works showed an excellent role in accurate heartbeats classification. However, the imbalance of heartbeat classes is universal in most of the available ECG databases since abnormal heartbeats are always relatively rare in real life scenarios. In addition, many existing approaches achieved prominent results by removing noise and extracting features in data preprocessing, which relies heavily on powerful computers. It is a pressing need to develop efficient and automatic light weighted algorithms for accurate heartbeats classification that can be used in portable ECG sensors. Objective: This study aims at developing a robust and efficient deep learning method, which can be embedded into wearable or portable ECG monitors for classifying heartbeats. Methods: We proposed a novel and light weighted deep learning architecture with weight-based loss based on a convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM) that can automatically identify five types of ECG heartbeats according to the AAMI EC57 standard. It was also true that the raw ECG signals were simply segmented without noise removal and other feature extraction processing. Moreover, to tackle the challenge of classification bias due to imbalanced ECG datasets for different types of arrhythmias, we introduced a weight-based loss function to reduce the influence of over-weighted categories in the ECG dataset. For avoiding the influence of the division of validation dataset, k-fold method was adopted to improve the reliability of the model. Results: The proposed algorithm is trained and tested on MIT-BIH Arrhythmia Database, and achieves an average of 99.33% accuracy, 93.67% sensitivity, 99.18% specificity, 89.85% positive prediction, and 91.65% F₁ score.

Design and implementation of intelligent patient in-house monitoring system based on efficient XGBoost-CNN approach

Because of the scarcity of caregivers and the high cost of medical devices, it is difficult to keep track of the aging population and provide assistance. To avoid deterioration of health issues, continuous monitoring of personal health should be done prior to the intervention. If a problem is discovered, the IoT platform collects and presents the caretaker with graphical data. The death rates of older patients are reduced when projections are made ahead of time. Patients can die as a result of minor abnormalities in their ECG. The cardiac dysrhythmia/irregular heart rate is classified with several multilayer parameters using a deep convolutional neural network (CNN) approach in this paper. The key benefit of utilizing this CNN approach is that it can handle databases that have been purposefully oversampled. Using the XGBoost approach, these are oversampled to deal with difficulties like minority class and imbalance. XGBoost is a decision tree-based ensemble learning algorithm that uses a gradient boosting framework. It uses an artificial neural network and predicts the unstructured data in a structured manner. This CNN-based supervised learning model is tested and simulated on a real-time elderly heart patient IoT dataset. The proposed methodology has a recall value of 100%, an F1-Score of 94.8%, a precision of 98%, and an accuracy of 98%, which is higher than existing approaches like decision trees, random forests, and Support Vector Machine. The results reveal that the proposed model outperforms state-of-the-art methodologies and improves elderly heart disease patient monitoring with a low error rate.

Developing Graph Convolutional Networks and Mutual Information for Arrhythmic Diagnosis Based on Multichannel ECG Signals

Cardiovascular diseases, like arrhythmia, as the leading causes of death in the world, can be automatically diagnosed using an electrocardiogram (ECG). The ECG-based diagnostic has notably resulted in reducing human errors. The main aim of this study is to increase the accuracy of arrhythmia diagnosis and classify various types of arrhythmias in individuals (suffering from cardiovascular diseases) using a novel graph convolutional network (GCN) benefitting from mutual information (MI) indices extracted from the ECG leads. In this research, for the first time, the relationships of 12 ECG leads measured using MI as an adjacency matrix were illustrated by the developed GCN and included in the ECG-based diagnostic method. Cross-validation methods were applied to select both training and testing groups. The proposed methodology was validated in practice by applying it to the large ECG database, recently published by Chapman University. The GCN-MI structure with 15 layers was selected as the best model for the selected database, which illustrates a very high accuracy in classifying different types of rhythms. The classification indicators of sensitivity, precision, specificity, and accuracy for classifying heart rhythm type, using GCN-MI, were computed as 98.45%, 97.89%, 99.85%, and 99.71%, respectively. The results of the present study and its comparison with other studies showed that considering the MI index to measure the relationship between cardiac leads has led to the improvement of GCN performance for detecting and classifying the type of arrhythmias, in comparison to the existing methods. For example, the above classification indicators for the GCN with the identity adjacency matrix (or GCN-Id) were reported to be 68.24%, 72.83%, 95.24%, and 92.68%, respectively.

A Review of Hybrid Approaches for Quantitative Assessment of Crop Traits Using Optical Remote Sensing: Research Trends and Future Directions

Remote sensing technology allows to provide information about biochemical and biophysical crop traits and monitor their spatiotemporal dynamics of agriculture ecosystems. Among multiple retrieval techniques, hybrid approaches have been found to provide outstanding accuracy, for instance, for the inference of leaf area index (LAI), fractional vegetation cover (fCover), and leaf and canopy chlorophyll content (LCC and CCC). The combination of radiative transfer models (RTMs) and data-driven models creates an advantage in the use of hybrid methods. Through this review paper, we aim to provide state-of-the-art hybrid retrieval schemes and theoretical frameworks. To achieve this, we reviewed and systematically analyzed publications over the past 22 years. We identified two hybrid-based parametric and hybrid-based nonparametric regression models and evaluated their performance for each variable of interest. From the results of our extensive literature survey, most research directions are now moving towards combining RTM and machine learning (ML) methods in a symbiotic manner. In particular, the development of ML will open up new ways to integrate innovative approaches such as integrating shallow or deep neural networks with RTM using remote sensing data to reduce errors in crop trait estimations and improve control of crop growth conditions in very large areas serving precision agriculture applications.

[Artificial intelligence-based ECG analysis: current status and future perspectives : Part 2: Recent studies and future]

Während grundlegende Aspekte der Anwendung von künstlicher Intelligenz (KI) zur Elektrokardiogramm(EKG)-Analyse in Teil 1 dieser Übersicht behandelt wurden, beschäftigt sich die vorliegende Arbeit (Teil 2) mit einer Besprechung von aktuellen Studien zum praktischen Einsatz dieser neuen Technologien und Aspekte ihrer aktuellen und möglichen zukünftigen Anwendung. Die Anzahl der zum Thema KI-basierte EKG-Analyse publizierten Studien steigt seit 2017 rasant an. Dies gilt vor allem für Untersuchungen, die Deep Learning (DL) mit künstlichen neuronalen Netzen (KNN) einsetzen. Inhaltlich geht es nicht nur darum, die Schwächen der klassischen EKG-Diagnostik mit Hilfe von KI zu überwinden und die diagnostische Güte des Verfahrens zu verbessern, sondern auch die Funktionalität des EKGs zu erweitern. Angestrebt wird die Erkennung spezieller kardiologischer und nichtkardiologischer Krankheitsbilder sowie die Vorhersage zukünftiger Krankheitszustände, z. B. die zukünftige Entwicklung einer linksventrikulären Dysfunktion oder das zukünftige Auftreten von Vorhofflimmern. Möglich wird dies, indem KI mittels DL in riesigen EKG-Datensätzen subklinische Muster findet und für die Algorithmen-Entwicklung nutzt. Die KI-unterstützte EKG-Analyse wird somit zu einem Screening-Instrument und geht weit darüber hinaus, nur besser als ein Kardiologe zu sein. Die erzielten Fortschritte sind bemerkenswert und sorgen in Fachwelt und Öffentlichkeit für Aufmerksamkeit und Euphorie. Bei den meisten Studien handelt es sich allerdings um Proof-of-Concept-Studien. Häufig werden private (institutionseigene) Daten verwendet, deren Qualität unklar ist. Bislang ist nur selten eine klinische Validierung der entwickelten Algorithmen in anderen Kollektiven und Szenarien erfolgt. Besonders problematisch ist, dass der Weg, wie KI eine Lösung findet, bislang meistens verborgen bleibt (Blackbox-Charakter). Damit steckt die KI-basierte Elektrokardiographie noch in den Kinderschuhen. Unbestritten ist aber schon absehbar, dass das EKG als einfach anzuwendendes und beliebig oft wiederholbares diagnostisches Verfahren auch in Zukunft nicht nur weiterhin unverzichtbar sein wird, sondern durch KI an klinischer Bedeutung gewinnen wird.

Deep Learning for Detecting and Locating Myocardial Infarction by Electrocardiogram: A Literature Review

Myocardial infarction is a common cardiovascular disorder caused by prolonged ischemia, and early diagnosis of myocardial infarction (MI) is critical for lifesaving. ECG is a simple and non-invasive approach in MI detection, localization, diagnosis, and prognosis. Population-based screening with ECG can detect MI early and help prevent it but this method is too labor-intensive and time-consuming to carry out in practice unless artificial intelligence (AI) would be able to reduce the workload. Recent advances in using deep learning (DL) for ECG screening might rekindle this hope. This review aims to take stock of 59 major DL studies applied to the ECG for MI detection and localization published in recent 5 years, covering convolutional neural network (CNN), long short-term memory (LSTM), convolutional recurrent neural network (CRNN), gated recurrent unit (GRU), residual neural network (ResNet), and autoencoder (AE). In this period, CNN obtained the best popularity in both MI detection and localization, and the highest performance has been obtained from CNN and ResNet model. The reported maximum accuracies of the six different methods are all beyond 97%. Considering the usage of different datasets and ECG leads, the network that trained on 12 leads ECG data of PTB database has obtained higher accuracy than that on smaller number leads data of other datasets. In addition, some limitations and challenges of the DL techniques are also discussed in this review.

A machine learning-based risk stratification tool for in-hospital mortality of intensive care unit patients with heart failure

BACKGROUND

Predicting hospital mortality risk is essential for the care of heart failure patients, especially for those in intensive care units.

METHODS

Using a novel machine learning algorithm, we constructed a risk stratification tool that correlated patients' clinical features and in-hospital mortality. We used the extreme gradient boosting algorithm to generate a model predicting the mortality risk of heart failure patients in the intensive care unit in the derivation dataset of 5676 patients from the Medical Information Mart for Intensive Care III database. The logistic regression model and a common risk score for mortality were used for comparison. The eICU Collaborative Research Database dataset was used for external validation.

RESULTS

The performance of the machine learning model was superior to that of conventional risk predictive methods, with the area under curve 0.831 (95% CI 0.820-0.843) and acceptable calibration. In external validation, the model had an area under the curve of 0.809 (95% CI 0.805-0.814). Risk stratification through the model was specific when the hospital mortality was very low, low, moderate, high, and very high (2.0%, 10.2%, 11.5%, 21.2% and 56.2%, respectively). The decision curve analysis verified that the machine learning model is the best clinically valuable in predicting mortality risk.

CONCLUSION

Using readily available clinical data in the intensive care unit, we built a machine learning-based mortality risk tool with prediction accuracy superior to that of linear regression model and common risk scores. The risk tool may support clinicians in assessing individual patients and making individualized treatment.

Weighted Time Warping Improves T-wave Morphology Markers Clinical Significance

Background: T-wave (TW) morphology indices based on time-warping (d_w) have shown significant cardiovascular risk stratification value. However, errors in the location of TW boundaries may impact their prognostic power. Our aim was to test the hypothesis that a weighted time-warping function (WF) would reduce the sensitivity of d_w to these errors and improve their clinical significance. Methods: The WFs were proportional to (i) the reference TW (T), and (ii) the absolute value of its derivative (D). The index d_w was recalculated using these WFs, and its performance was compared to the unweighted control case (C) in four different scenarios: 1) robustness against simulated TW boundaries location errors; 2) ability to retain physiological information in an electrophysiological cardiac model; 3) ability to monitor blood potassium concentration changes ([K⁺]) in 29 hemodialysis (HD) patients; 4) and the sudden cardiac death (SCD) risk stratification value of the TW morphology restitution (TMR) index, derived from d_w, in 651 chronic heart failure (CHF) patients. Results and Discussion: The WFs led to a reduced sensitivity (R) of d_w to TW boundary location errors as compared to C (median R=0.19 and 0.22 and 0.35 for T, D and C, respectively). They also preserved the physiological relationship between d_w and repolarization dispersion changes at ventricular level. No improvements in [K⁺] tracking were observed for the HD patients (Pearsons median correlation [r] between [K⁺] and d_w was 0.86r0.90 for T, D and C). In CHF patients, the SCD risk stratification value of TMR was improved by applying T (hazard ratio, HAR, of 2.80), followed by D (HAR=2.32) and C (HAR=2.23). Conclusions and Significance: The proposed WFs, with T showing the best performance, increased the robustness of time-warping based markers against TW location errors preserving their physiological information content and boosting their SCD risk stratification value. Results from this work support the use of T when deriving d_w for future clinical applications.

Redundancy cancellation of compressed measurements by QRS complex alignment

The demand for long-term continuous care has led healthcare experts to focus on development challenges. On-chip energy consumption as a key challenge can be addressed by data reduction techniques. In this paper, the pseudo periodic nature of ElectroCardioGram(ECG) signals has been used to completely remove redundancy from frames. Compressing aligned QRS complexes by Compressed Sensing (CS), result in highly redundant measurement vectors. By removing this redundancy, a high cluster of near zero samples is gained. The efficiency of the proposed algorithm is assessed using the standard MIT-BIH database. The results indicate that by aligning ECG frames, the proposed technique can achieve superior reconstruction quality compared to state-of-the-art techniques for all compression ratios. This study proves that by aligning ECG frames with a 0.05% unaligned frame rate(R-peak detection error), more compression could be gained for PRD > 5% when 5-bit non-uniform quantizer is used. Furthermore, analysis done on power consumption of the proposed technique, indicates that a very good recovery performance can be gained by only consuming 4.9μW more energy per frame compared to traditional CS.

Reduction of Artifacts in Capacitive Electrocardiogram Signals of Driving Subjects

The development of smart cars with e-health services allows monitoring of the health condition of the driver. Driver comfort is preserved by the use of capacitive electrodes, but the recorded signal is characterized by large artifacts. This paper proposes a method for reducing artifacts from the ECG signal recorded by capacitive electrodes (cECG) in moving subjects. Two dominant artifact types are coarse and slow-changing artifacts. Slow-changing artifacts removal by classical filtering is not feasible as the spectral bands of artifacts and cECG overlap, mostly in the band from 0.5 to 15 Hz. We developed a method for artifact removal, based on estimating the fluctuation around linear trend, for both artifact types, including a condition for determining the presence of coarse artifacts. The method was validated on cECG recorded while driving, with the artifacts predominantly due to the movements, as well as on cECG recorded while lying, where the movements were performed according to a predefined protocol. The proposed method eliminates 96% to 100% of the coarse artifacts, while the slow-changing artifacts are completely reduced for the recorded cECG signals larger than 0.3 V. The obtained results are in accordance with the opinion of medical experts. The method is intended for reliable extraction of cardiovascular parameters to monitor driver fatigue status.

Arrhythmia detection and classification using ECG and PPG techniques: a review

Electrocardiogram (ECG) and photoplethysmograph (PPG) are non-invasive techniques that provide electrical and hemodynamic information of the heart, respectively. This information is advantageous in the diagnosis of various cardiac abnormalities. Arrhythmia is the most common cardiovascular disease, manifested as single or multiple irregular heartbeats. However, due to the continuous manual observation, it becomes troublesome for experts sometimes to identify the paroxysmal nature of arrhythmia correctly. Moreover, due to advancements in technology, there is an inclination towards wearable sensors which monitor such patients continuously. Thus, there is a need for automatic detection techniques for the identification of arrhythmia. In the presented work, ECG and PPG-based state-of-the-art methods have been described, including preprocessing, feature extraction, and classification techniques for the detection of various arrhythmias. Additionally, this review exhibits various wearable sensors used in the literature and public databases available for the evaluation of results. The study also highlights the limitations of the current techniques and pragmatic solutions to improvise the ongoing effort.

Gaussian process-based kernel as a diagnostic model for prediction of type 2 diabetes mellitus risk using non-linear heart rate variability features

The main objective of the study was to develop a low-cost, non-invasive diagnostic model for the early prediction of T2DM risk and validation of this model on patients. The model was designed based on the machine learning classification technique using non-linear Heart rate variability (HRV) features. The electrocardiogram of the healthy subjects (n = 35) and T2DM subjects (n = 100) were recorded in the supine position for 15 min, and HRV features were extracted. The significant non-linear HRV features were identified through statistical analysis. It was found that Poincare plot features (SD1 and SD2) can differentiate the T2DM subject data from healthy subject data. Several machine learning classifiers, such as Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis, Naïve Bayes, and Gaussian Process Classifier (GPC), have classified the data based on the cross-validation approach. A GP classifier was implemented using three kernels, namely radial basis, linear, and polynomial kernel, considering the ability to handle the non-linear data. The classifier performance was evaluated and compared using performance metrics such as accuracy(AC), sensitivity(SN), specificity(SP), precision(PR), F1 score, and area under the receiver operating characteristic curve(AUC). Initially, all non-linear HRV features were selected for classification, but the specificity of the model was the limitation. Thus, only two Poincare plot features were used to design the diagnostic model. Our diagnostic model shows the performance using GPC based linear kernel as AC of 92.59%, SN of 96.07%, SP of 81.81%, PR of 94.23%, F1 score of 0.95, and AUC of 0.89, which are more extensive compared to other classification models. Further, the diagnostic model was deployed on the hardware module. Its performance on unknown/test data was validated on 65 subjects (healthy n = 15 and T2DM n = 50). Considering the desirable performance of the diagnostic model, it can be used as an initial screening test tool for a healthcare practitioner to predict T2DM risk.

ECG Heartbeat Classification Based on an Improved ResNet-18 Model

Based on a convolutional neural network (CNN) approach, this article proposes an improved ResNet-18 model for heartbeat classification of electrocardiogram (ECG) signals through appropriate model training and parameter adjustment. Due to the unique residual structure of the model, the utilized CNN layered structure can be deepened in order to achieve better classification performance. The results of applying the proposed model to the MIT-BIH arrhythmia database demonstrate that the model achieves higher accuracy (96.50%) compared to other state-of-the-art classification models, while specifically for the ventricular ectopic heartbeat class, its sensitivity is 93.83% and the precision is 97.44%.