ECG Monitoring Systems: Review, Architecture, Processes, and Key Challenges

Emergence of Artificial Intelligence and Machine Learning Models in Sudden Cardiac Arrest: A Comprehensive Review of Predictive Performance and Clinical Decision Support

Sudden cardiac death/sudden cardiac arrest (SCD/SCA) is an increasingly prevalent cause of mortality globally, particularly in individuals with preexisting cardiac conditions. The ambiguous premortem warnings and the restricted interventional window related to SCD account for the complexity of the condition. Current reports suggest SCD to be accountable for 20% of all deaths hence accurately predicting SCD risk is an imminent concern. Traditional approaches for predicting SCA, particularly "track-and-trigger" warning systems have demonstrated considerable inadequacies, including low sensitivity, false alarms, decreased diagnostic liability, reliance on clinician involvement, and human errors. Artificial intelligence (AI) and machine learning (ML) models have demonstrated near-perfect accuracy in predicting SCA risk, allowing clinicians to intervene timely. Given the constraints of current diagnostics, exploring the benefits of AI and ML models in enhancing outcomes for SCA/SCD is imperative. This review article aims to investigate the efficacy of AI and ML models in predicting and managing SCD, particularly targeting accuracy in prediction.

A Smartphone-Based M-Health Monitoring System for Arrhythmia Diagnosis

Deep learning technology has been widely adopted in the research of automatic arrhythmia detection. However, there are several limitations in existing diagnostic models, e.g., difficulties in extracting temporal information from long-term ECG signals, a plethora of parameters, and sluggish operation speed. Additionally, the diagnosis performance of arrhythmia is prone to mistakes from signal noise. This paper proposes a smartphone-based m-health system for arrhythmia diagnosis. First, we design a cycle-GAN-based ECG denoising model which takes real-world noise signals as input and aims to produce clean ECG signals. In order to train its two generators and two discriminators simultaneously, we explore an unsupervised pre-training strategy to initialize the generator and accelerate the convergence speed during training. Second, we propose an arrhythmia diagnosis model based on the time convolution network (TCN). This model can identify 34 common arrhythmia events using eight-lead ECG signals, and we deploy such a model on the Android platform to develop an at-home ECG monitoring system. Experimental results have demonstrated that our approach outperforms the existing noise reduction methods and arrhythmia diagnosis models in terms of denoising effect, recognition accuracy, model size, and operation speed, making it more suitable for deployment on mobile devices for m-health monitoring services.

Biometric contrastive learning for data-efficient deep learning from electrocardiographic images

OBJECTIVE

Artificial intelligence (AI) detects heart disease from images of electrocardiograms (ECGs). However, traditional supervised learning is limited by the need for large amounts of labeled data. We report the development of Biometric Contrastive Learning (BCL), a self-supervised pretraining approach for label-efficient deep learning on ECG images.

MATERIALS AND METHODS

Using pairs of ECGs from 78 288 individuals from Yale (2000-2015), we trained a convolutional neural network to identify temporally separated ECG pairs that varied in layouts from the same patient. We fine-tuned BCL-pretrained models to detect atrial fibrillation (AF), gender, and LVEF < 40%, using ECGs from 2015 to 2021. We externally tested the models in cohorts from Germany and the United States. We compared BCL with ImageNet initialization and general-purpose self-supervised contrastive learning for images (simCLR).

RESULTS

While with 100% labeled training data, BCL performed similarly to other approaches for detecting AF/Gender/LVEF < 40% with an AUROC of 0.98/0.90/0.90 in the held-out test sets, it consistently outperformed other methods with smaller proportions of labeled data, reaching equivalent performance at 50% of data. With 0.1% data, BCL achieved AUROC of 0.88/0.79/0.75, compared with 0.51/0.52/0.60 (ImageNet) and 0.61/0.53/0.49 (simCLR). In external validation, BCL outperformed other methods even at 100% labeled training data, with an AUROC of 0.88/0.88 for Gender and LVEF < 40% compared with 0.83/0.83 (ImageNet) and 0.84/0.83 (simCLR).

DISCUSSION AND CONCLUSION

A pretraining strategy that leverages biometric signatures of different ECGs from the same patient enhances the efficiency of developing AI models for ECG images. This represents a major advance in detecting disorders from ECG images with limited labeled data.

Development and validation of an assessment index for quantifying cognitive task load in pilots under simulated flight conditions using heart rate variability and principal component analysis

To investigate whether high cognitive task load (CTL) for aircraft pilots can be identified by analysing heart-rate variability, electrocardiograms were recorded while cadet pilots (n = 68) performed the plane tracking, anti-gravity pedalling, and reaction tasks during simulated flight missions. Data for standard electrocardiogram parameters were extracted from the R-R-interval series. In the research phase, low frequency power (LF), high frequency power (HF), normalised HF, and LF/HF differed significantly between high and low CTL conditions (p < .05 for all). A principal component analysis identified three components contributing 90.62% of cumulative heart-rate variance. These principal components were incorporated into a composite index. Validation in a separate group of cadet pilots (n = 139) under similar conditions showed that the index value significantly increased with increasing CTL (p < .05). The heart-rate variability index can be used to objectively identify high CTL flight conditions.Practitioner summary: We used principal component analysis of electrocardiogram data to construct a composite index for identifying high cognitive task load in pilots during simulated flight. We validated the index in a separate group of pilots under similar conditions. The index can be used to improve cadet training and flight safety.Abbreviations: ANOVA: a one-way analysis of variance; AP: anti-gravity pedaling task; CTL: cognitive task load; ECG: electrocardiograms; HR: heart rate; HRV: heart-rate variability; HRVI: heart-rate variability index; PT: plane-tracking task; RMSSD: root-mean square of differences between consecutive R-R intervals; RT: reaction task; SDNN: standard deviation of R-R intervals; HF: high frequency power; HFnu: normalized HF; LF: low frequency power; LFnu: normalized LF; PCA: principal component analysis.

E-Tattoos: Toward Functional but Imperceptible Interfacing with Human Skin

The human body continuously emits physiological and psychological information from head to toe. Wearable electronics capable of noninvasively and accurately digitizing this information without compromising user comfort or mobility have the potential to revolutionize telemedicine, mobile health, and both human-machine or human-metaverse interactions. However, state-of-the-art wearable electronics face limitations regarding wearability and functionality due to the mechanical incompatibility between conventional rigid, planar electronics and soft, curvy human skin surfaces. E-Tattoos, a unique type of wearable electronics, are defined by their ultrathin and skin-soft characteristics, which enable noninvasive and comfortable lamination on human skin surfaces without causing obstruction or even mechanical perception. This review article offers an exhaustive exploration of e-tattoos, accounting for their materials, structures, manufacturing processes, properties, functionalities, applications, and remaining challenges. We begin by summarizing the properties of human skin and their effects on signal transmission across the e-tattoo-skin interface. Following this is a discussion of the materials, structural designs, manufacturing, and skin attachment processes of e-tattoos. We classify e-tattoo functionalities into electrical, mechanical, optical, thermal, and chemical sensing, as well as wound healing and other treatments. After discussing energy harvesting and storage capabilities, we outline strategies for the system integration of wireless e-tattoos. In the end, we offer personal perspectives on the remaining challenges and future opportunities in the field.

Enhancing ECG classification with continuous wavelet transform and multi-branch transformer

Background

Accurate classification of electrocardiogram (ECG) signals is crucial for automatic diagnosis of heart diseases. However, existing ECG classification methods often require complex preprocessing and denoising operations, and traditional convolutional neural network (CNN)-based methods struggle to capture complex relationships and high-level time-series features.

Method

In this study, we propose an ECG classification method based on continuous wavelet transform and multi-branch transformer. The method utilizes continuous wavelet transform (CWT) to convert the ECG signal into time-series feature map, eliminating the need for complicated preprocessing. Additionally, the multi-branch transformer is introduced to enhance feature extraction during model training and improve classification performance by removing redundant information while preserving important features.

Results

The proposed method was evaluated on the CPSC 2018 (6877 cases) and MIT-BIH (47 cases) ECG public datasets, achieving an accuracy of 98.53% and 99.38%, respectively, with F1 scores of 97.57% and 98.65%. These results outperformed most existing methods, demonstrating the excellent performance of the proposed method.

Conclusion

The proposed method accurately classifies the ECG time-series feature map, which holds promise for the diagnosis of cardiac arrhythmias. The findings of this study are valuable for advancing the field of automatic ECG diagnosis.

Operational disruption in healthcare associated with software functionality issue due to software security patching: a case report

Despite many benefits, the extensive deployment of Health Information Technology (HIT) systems by healthcare organizations has encountered many challenges, particularly in the field of telemetry concerning patient monitoring and its operational workflow. These challenges can add more layers of complexity when an unplanned software security patching is performed, affecting patient monitoring and causing disruption in daily clinical operations. This study is a reflection on what happened associated with software security patching and why it happened through the lens of an incident report to develop potential preventive and corrective strategies using qualitative analyses—inductive and deductive approaches. There is a need for such analyses to identify the underlying mechanism behind such issues since very limited research has been conducted on the study of software patching. The incident was classified as a “software functionality” issue, and the consequence was an “incident with a noticeable consequence but no patient harm”, and the contributing factor was a software update, i.e., software security patching. This report describes how insufficient planning of software patching, lack of training for healthcare professionals, contingency planning on unplanned system disruption, and HIT system configuration can compromise healthcare quality and cause risks to patient safety. We propose 15 preventive and corrective strategies grouped under four key areas based on the system approach and social-technical aspects of the patching process. The key areas are (i) preparing, developing, and deploying patches; (ii) training the frontline operators; (iii) ensuring contingency planning; and (iv) establishing configuration and communication between systems. These strategies are expected to minimize the risk of HIT-related incidents, enhance software security patch management in healthcare organizations, and improve patient safety. However, further discussion should be continued about general HIT problems connected to software security patching.

Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review

Electrocardiogram (ECG) are the physiological signals and a standard test to measure the heart's electrical activity that depicts the movement of cardiac muscles. A review study has been conducted on ECG signals analysis with the help of artificial intelligence (AI) methods over the last ten years i.e., 2012-22. Primarily, the method of ECG analysis by software systems was divided into classical signal processing (e.g. spectrograms or filters), machine learning (ML) and deep learning (DL), including recursive models, transformers and hybrid. Secondly, the data sources and benchmark datasets were depicted. Authors grouped resources by ECG acquisition methods into hospital-based portable machines and wearable devices. Authors also included new trends like advanced pre-processing, data augmentation, simulations and agent-based modeling. The study found improvement in ECG examination perfection made each year through ML, DL, hybrid models, and transformers. Convolutional neural networks and hybrid models were more targeted and proved efficient. The transformer model extended the accuracy from 90% to 98%. The Physio-Net library helps acquire ECG signals, including the popular benchmark databases such as MIT-BIH, PTB, and challenging datasets. Similarly, wearable devices have been established as a appropriate option for monitoring patient health without the time and place limitations and are also helpful for AI model calibration with so far accuracy of 82%-83% on Samsung smartwatch. In the pre-processing signals, spectrogram generation through Fourier and wavelet transformations are erected leading approaches promoting on average accuracy of 90%-95%. Likewise, data enhancement using geometrical techniques is well-considered; however, extraction and concatenation-based methods need attention. As the what-if analysis in healthcare or cardiac issues can be performed using a complex simulation, the study reviews agent-based modeling and simulation approaches for cardiovascular risk event assessment.

Wearable Technology for Monitoring Electrocardiograms (ECGs) in Adults: A Scoping Review

In the rapidly evolving landscape of continuous electrocardiogram (ECG) monitoring systems, there is a heightened demand for non-invasive sensors capable of measuring ECGs and detecting heart rate variability (HRV) in diverse populations, ranging from cardiovascular patients to sports enthusiasts. Challenges like device accuracy, patient privacy, signal noise, and long-term safety impede the use of wearable devices in clinical practice. This scoping review aims to assess the performance and safety of novel multi-channel, sensor-based biopotential wearable devices in adults. A comprehensive search strategy was employed on four databases, resulting in 143 records and the inclusion of 12 relevant studies. Most studies focused on healthy adult subjects (n = 6), with some examining controlled groups with atrial fibrillation (AF) (n = 3), long QT syndrome (n = 1), and sleep apnea (n = 1). The investigated bio-sensor devices included chest-worn belts (n = 2), wrist bands (n = 2), adhesive chest strips (n = 2), and wearable textile smart clothes (n = 4). The primary objective of the included studies was to evaluate device performance in terms of accuracy, signal quality, comparability, and visual assessment of ECGs. Safety findings, reported in five articles, indicated no major side effects for long-term/continuous monitoring, with only minor instances of skin irritation. Looking forward, there are ample opportunities to enhance and test these technologies across various physical activity intensities and clinical conditions.

Self-supervised multi-modal training from uncurated images and reports enables monitoring AI in radiology

The escalating demand for artificial intelligence (AI) systems that can monitor and supervise human errors and abnormalities in healthcare presents unique challenges. Recent advances in vision-language models reveal the challenges of monitoring AI by understanding both visual and textual concepts and their semantic correspondences. However, there has been limited success in the application of vision-language models in the medical domain. Current vision-language models and learning strategies for photographic images and captions call for a web-scale data corpus of image and text pairs which is not often feasible in the medical domain. To address this, we present a model named medical cross-attention vision-language model (Medical X-VL), which leverages key components to be tailored for the medical domain. The model is based on the following components: self-supervised unimodal models in medical domain and a fusion encoder to bridge them, momentum distillation, sentencewise contrastive learning for medical reports, and sentence similarity-adjusted hard negative mining. We experimentally demonstrated that our model enables various zero-shot tasks for monitoring AI, ranging from the zero-shot classification to zero-shot error correction. Our model outperformed current state-of-the-art models in two medical image datasets, suggesting a novel clinical application of our monitoring AI model to alleviate human errors. Our method demonstrates a more specialized capacity for fine-grained understanding, which presents a distinct advantage particularly applicable to the medical domain.

Survey of Transfer Learning Approaches in the Machine Learning of Digital Health Sensing Data

Machine learning and digital health sensing data have led to numerous research achievements aimed at improving digital health technology. However, using machine learning in digital health poses challenges related to data availability, such as incomplete, unstructured, and fragmented data, as well as issues related to data privacy, security, and data format standardization. Furthermore, there is a risk of bias and discrimination in machine learning models. Thus, developing an accurate prediction model from scratch can be an expensive and complicated task that often requires extensive experiments and complex computations. Transfer learning methods have emerged as a feasible solution to address these issues by transferring knowledge from a previously trained task to develop high-performance prediction models for a new task. This survey paper provides a comprehensive study of the effectiveness of transfer learning for digital health applications to enhance the accuracy and efficiency of diagnoses and prognoses, as well as to improve healthcare services. The first part of this survey paper presents and discusses the most common digital health sensing technologies as valuable data resources for machine learning applications, including transfer learning. The second part discusses the meaning of transfer learning, clarifying the categories and types of knowledge transfer. It also explains transfer learning methods and strategies, and their role in addressing the challenges in developing accurate machine learning models, specifically on digital health sensing data. These methods include feature extraction, fine-tuning, domain adaptation, multitask learning, federated learning, and few-/single-/zero-shot learning. This survey paper highlights the key features of each transfer learning method and strategy, and discusses the limitations and challenges of using transfer learning for digital health applications. Overall, this paper is a comprehensive survey of transfer learning methods on digital health sensing data which aims to inspire researchers to gain knowledge of transfer learning approaches and their applications in digital health, enhance the current transfer learning approaches in digital health, develop new transfer learning strategies to overcome the current limitations, and apply them to a variety of digital health technologies.

Reviving Hope: A Comprehensive Review of Post-resuscitation Care in Pediatric ICUs After Cardiac Arrest

This comprehensive review thoroughly examines post-resuscitation care in pediatric ICUs (PICUs) following cardiac arrest. The analysis encompasses adherence to resuscitation guidelines, advances in therapeutic interventions, and the nuanced management of neurological, cardiovascular, and respiratory considerations during the immediate post-resuscitation phase. Delving into the complexities of long-term outcomes, cognitive and developmental considerations, and rehabilitation strategies, the review emphasizes the importance of family-centered care for pediatric survivors. A call to action is presented, urging continuous education, research initiatives, and quality improvement efforts alongside strengthened multidisciplinary collaboration and advocacy for public awareness. Through implementing these principles, healthcare providers and systems can collectively contribute to ongoing advancements in pediatric post-resuscitation care, ultimately improving outcomes and fostering a culture of excellence in pediatric critical care.

Stretchable Gold Nanomembrane Electrode with Ionic Hydrogel Skin-Adhesive Properties

Skin has a dynamic surface and offers essential information through biological signals originating from internal organs, blood vessels, and muscles. Soft and stretchable bioelectronics can be used in wearable machines for long-term stability and to continuously obtain distinct bio-signals in conjunction with repeated expansion and contraction with physical activities. While monitoring bio-signals, the electrode and skin must be firmly attached for high signal quality. Furthermore, the signal-to-noise ratio (SNR) should be high enough, and accordingly, the ionic conductivity of an adhesive hydrogel needs to be improved. Here, we used a chitosan-alginate-chitosan (CAC) triple hydrogel layer as an interface between the electrodes and the skin to enhance ionic conductivity and skin adhesiveness and to minimize the mechanical mismatch. For development, thermoplastic elastomer Styrene-Ethylene-Butylene-Styrene (SEBS) dissolved in toluene was used as a substrate, and gold nanomembranes were thermally evaporated on SEBS. Subsequently, CAC triple layers were drop-casted onto the gold surface one by one and dried successively. Lastly, to demonstrate the performance of our electrodes, a human electrocardiogram signal was monitored. The electrodes coupled with our CAC triple hydrogel layer showed high SNR with clear PQRST peaks.

Flexible electronics for cardiovascular healthcare monitoring

Cardiovascular diseases (CVDs) are one of the most urgent threats to humans worldwide, which are responsible for almost one-third of global mortality. Over the last decade, research on flexible electronics for monitoring and treatment of CVDs has attracted tremendous attention. In contrast to conventional medical instruments in hospitals that are usually bulky, hard to move, monofunctional, and time-consuming, flexible electronics are capable of continuous, noninvasive, real-time, and portable monitoring. Notable progress has been made in this emerging field, and thus a number of significant achievements and concomitant research prospects deserve attention for practical implementation. Here, we comprehensively review the latest progress of flexible electronics for CVDs, focusing on new functions provided by flexible electronics. First, the characteristics of CVDs and flexible electronics and the foundation of their combination are briefly reviewed. Then, four representative applications of flexible electronics for CVDs are elaborated: blood pressure (BP) monitoring, electrocardiogram (ECG) monitoring, echocardiogram monitoring, and direct epicardium monitoring. Their operational principles, progress, merits and demerits, and future efforts are discussed. Finally, the remaining challenges and opportunities for flexible electronics for cardiovascular healthcare are outlined.

Self-Attention LSTM-FCN model for arrhythmia classification and uncertainty assessment

This paper presents ArrhyMon, a self-attention-based LSTM-FCN model for arrhythmia classification from ECG signal inputs. ArrhyMon targets to detect and classify six different types of arrhythmia apart from normal ECG patterns. To the best of our knowledge, ArrhyMon is the first end-to-end classification model that successfully targets the classification of six detailed arrhythmia types and compared to previous work does not require additional preprocessing and/or feature extraction operations separate from the classification model. ArrhyMon's deep learning model is designed to capture and exploit both global and local features embedded in ECG sequences by integrating fully convolutional network (FCN) layers and a self-attention-based long and short-term memory (LSTM) architecture. Moreover, to enhance its practicality, ArrhyMon incorporates a deep ensemble-based uncertainty model that generates a confidence-level measure for each classification result. We evaluate ArrhyMon's effectiveness using three publicly available arrhythmia datasets (i.e., MIT-BIH, Physionet Cardiology Challenge 2017 and 2020/2021) to show that ArrhyMon achieves state-of-the-art classification performance (average accuracy 99.63%), and that confidence measures show close correlation with subjective diagnosis made from practitioners.

Electrocardiogram Devices for Home Use: Technological and Clinical Scoping Review

BACKGROUND

Electrocardiograms (ECGs) are used by physicians to record, monitor, and diagnose the electrical activity of the heart. Recent technological advances have allowed ECG devices to move out of the clinic and into the home environment. There is a great variety of mobile ECG devices with the capabilities to be used in home environments.

OBJECTIVE

This scoping review aimed to provide a comprehensive overview of the current landscape of mobile ECG devices, including the technology used, intended clinical use, and available clinical evidence.

METHODS

We conducted a scoping review to identify studies concerning mobile ECG devices in the electronic database PubMed. Secondarily, an internet search was performed to identify other ECG devices available in the market. We summarized the devices' technical information and usability characteristics based on manufacturer data such as datasheets and user manuals. For each device, we searched for clinical evidence on the capabilities to record heart disorders by performing individual searches in PubMed and ClinicalTrials.gov, as well as the Food and Drug Administration (FDA) 510(k) Premarket Notification and De Novo databases.

RESULTS

From the PubMed database and internet search, we identified 58 ECG devices with available manufacturer information. Technical characteristics such as shape, number of electrodes, and signal processing influence the capabilities of the devices to record cardiac disorders. Of the 58 devices, only 26 (45%) had clinical evidence available regarding their ability to detect heart disorders such as rhythm disorders, more specifically atrial fibrillation.

CONCLUSIONS

ECG devices available in the market are mainly intended to be used for the detection of arrhythmias. No devices are intended to be used for the detection of other cardiac disorders. Technical and design characteristics influence the intended use of the devices and use environments. For mobile ECG devices to be intended to detect other cardiac disorders, challenges regarding signal processing and sensor characteristics should be solved to increase their detection capabilities. Devices recently released include the use of other sensors on ECG devices to increase their detection capabilities.

CoAt-Mixer: Self-attention deep learning framework for left ventricular hypertrophy using electrocardiography

Left ventricular hypertrophy is a significant independent risk factor for all-cause mortality and morbidity, and an accurate diagnosis at an early stage of heart change is clinically significant. Electrocardiography is the most convenient, economical, and non-invasive method for screening in primary care. However, the coincidence rate of the actual left ventricular hypertrophy and diagnostic findings was low, consequently increasing the interest in algorithms using big data and deep learning. We attempted to diagnose left ventricular hypertrophy using big data and deep learning algorithms, and aimed to confirm its diagnostic power according to the differences between males and females. This retrospective study used electrocardiographs obtained at Yonsei University Wonju Severance Christian Hospital, Wonju, Korea, from October 2010 to February 2020. Binary classification was performed for primary screening for left ventricular hypertrophy. Three datasets were used for the experiment: the male, female, and entire dataset. A cutoff for binary classification was defined as the meaningful as a screening test (<132 g/m2 vs. ≥132 g/m2, <109 g/m2 vs. ≥109 g/m2). Six types of input were used for the classification tasks. We attempted to determine whether electrocardiography had predictive power for left ventricular hypertrophy diagnosis. For the entire dataset, the model achieved an area under the receiver operating characteristic (AUROC) curve of 0.836 (95% CI, 0.833-838) with a sensitivity of 78.37% (95% CI, 76.79-79.95). For the male dataset, the AUROC was 0.826 (95% CI, 0.822-830) with a sensitivity of 76.73% (95% CI, 75.14-78.33). For the female dataset, the AUROC was 0.772 (95% CI, 0.769-775) with a sensitivity of 72.90% (95% CI, 70.33-75.46). Our model confirmed that left ventricular hypertrophy can be classified to some extent using electrocardiography, demographics, and electrocardiography features. In particular, a learning environment that considered gender differences was constructed. Consequently, the difference in diagnostic power between men and women was confirmed. Our model will help patients with suspected left ventricular hypertrophy to undergo screening tests at a low cost. In addition, our research and attempts will show the expected effect that gender-consideration approaches can help with various currently proposed diagnostic methods.

Tablet-Based Wearable Patch Sensor Design for Continuous Cardiovascular System Monitoring in Postoperative Settings

Meticulous monitoring for cardiovascular systems is important for postoperative patients in postanesthesia or the intensive care unit. The continuous auscultation of heart and lung sounds can provide a valuable information for patient safety. Although numerous research projects have proposed the design of continuous cardiopulmonary monitoring devices, they primarily focused on the auscultation of heart and lung sounds and mostly served as screening tools. However, there is a lack of devices that could continuously display and monitor the derived cardiopulmonary parameters. This study presents a novel approach to address this need by proposing a bedside monitoring system that utilizes a lightweight and wearable patch sensor for continuous cardiovascular system monitoring. The heart and lung sounds were collected using a chest stethoscope and microphones, and a developed adaptive noise cancellation algorithm was implemented to remove the background noise corrupted with those sounds. Additionally, a short-distance ECG signal was acquired using electrodes and a high precision analog front end. A high-speed processing microcontroller was used to allow real-time data acquisition, processing, and display. A dedicated tablet-based software was developed to display the acquired signal waveforms and the processed cardiovascular parameters. A significant contribution of this work is the seamless integration of continuous auscultation and ECG signal acquisition, thereby enabling the real-time monitoring of cardiovascular parameters. The wearability and lightweight design of the system were achieved through the use of rigid-flex PCBs, which ensured patient comfort and ease of use. The system provides a high-quality signal acquisition and real-time monitoring of the cardiovascular parameters, thus proving its potential as a health monitoring tool.

GAN-based patient information hiding for an ECG authentication system

Various biometrics such as the face, irises, and fingerprints, which can be obtained in a relatively simple way in modern society, are used in personal authentication systems to identify individuals. These biometric data are extracted from an individual's physiological data and yield high performance in identifying an individual using unique data patterns. Biometric identification is also used in portable devices such as mobile devices because it is more secure than cryptographic token-based authentication methods. However, physiological data could include personal health information such as arrhythmia related patterns in electrocardiogram (ECG) signals. To protect sensitive health information from hackers, the biomarkers of certain diseases or disorders that exist in ECG signals need to be hidden. Additionally, to implement the inference models for both arrhythmia detection and personal authentication in a mobile device, a lightweight model such as a multi-task deep learning model should be considered. This study demonstrates a multi-task neural network model that simultaneously identifies an individual's ECG and arrhythmia patterns using a small network. Finally, the computational efficiency and model size of the single-task and multi-task models were compared based on the number of parameters. Although the multi-task model has 20,000 fewer parameters than the single-task model, they yielded similar performance, which demonstrates the efficient structure of the multi-task model.

Deep Learning Algorithms for Estimation of Demographic and Anthropometric Features from Electrocardiograms

The electrocardiogram (ECG) has been known to be affected by demographic and anthropometric factors. This study aimed to develop deep learning models to predict the subject's age, sex, ABO blood type, and body mass index (BMI) based on ECGs. This retrospective study included individuals aged 18 years or older who visited a tertiary referral center with ECGs acquired from October 2010 to February 2020. Using convolutional neural networks (CNNs) with three convolutional layers, five kernel sizes, and two pooling sizes, we developed both classification and regression models. We verified a classification model to be applicable for age (<40 years vs. ≥40 years), sex (male vs. female), BMI (<25 kg/m² vs. ≥25 kg/m²), and ABO blood type. A regression model was also developed and validated for age and BMI estimation. A total of 124,415 ECGs (1 ECG per subject) were included. The dataset was constructed by dividing the entire set of ECGs at a ratio of 4:3:3. In the classification task, the area under the receiver operating characteristic (AUROC), which represents a quantitative indicator of the judgment threshold, was used as the primary outcome. The mean absolute error (MAE), which represents the difference between the observed and estimated values, was used in the regression task. For age estimation, the CNN achieved an AUROC of 0.923 with an accuracy of 82.97%, and a MAE of 8.410. For sex estimation, the AUROC was 0.947 with an accuracy of 86.82%. For BMI estimation, the AUROC was 0.765 with an accuracy of 69.89%, and a MAE of 2.332. For ABO blood type estimation, the CNN showed an inferior performance, with a top-1 accuracy of 31.98%. For the ABO blood type estimation, the CNN showed an inferior performance, with a top-1 accuracy of 31.98% (95% CI, 31.98-31.98%). Our model could be adapted to estimate individuals' demographic and anthropometric features from their ECGs; this would enable the development of physiologic biomarkers that can better reflect their health status than chronological age.

Morphological Autoencoders for Beat-by-Beat Atrial Fibrillation Detection Using Single-Lead ECG

Engineered feature extraction can compromise the ability of Atrial Fibrillation (AFib) detection algorithms to deliver near real-time results. Autoencoders (AEs) can be used as an automatic feature extraction tool, tailoring the resulting features to a specific classification task. By coupling an encoder to a classifier, it is possible to reduce the dimension of the Electrocardiogram (ECG) heartbeat waveforms and classify them. In this work we show that morphological features extracted using a Sparse AE are sufficient to distinguish AFib from Normal Sinus Rhythm (NSR) beats. In addition to the morphological features, rhythm information was included in the model using a proposed short-term feature called Local Change of Successive Differences (LCSD). Using single-lead ECG recordings from two referenced public databases, and with features from the AE, the model was able to achieve an F1-score of 88.8%. These results show that morphological features appear to be a distinct and sufficient factor for detecting AFib in ECG recordings, especially when designed for patient-specific applications. This is an advantage over state-of-the-art algorithms that need longer acquisition times to extract engineered rhythm features, which also requires careful preprocessing steps. To the best of our knowledge, this is the first work that presents a near real-time morphological approach for AFib detection under naturalistic ECG acquisition with a mobile device.

Phase angle, muscle tissue, and resistance training

The biophysical response of the human body to electric current is widely appreciated as a barometer of fluid distribution and cell function. From distinct raw bioelectrical impedance (BIA) variables assessed in the field of body composition, phase angle (PhA) has been repeatedly indicated as a functional marker of the cell's health and mass. Although resistance training (RT) programs have demonstrated to be effective to improve PhA, with varying degrees of change depending on other raw BIA variables, there is still limited research explaining the biological mechanisms behind these changes. Here, we aim to provide the rationale for the responsiveness of PhA determinants to RT, as well as to summarize all available evidence addressing the effect of varied RT programs on PhA of different age groups. Available data led us to conclude that RT modulates the cell volume by increasing the levels of intracellular glycogen and water, thus triggering structural and functional changes in different cell organelles. These alterations lead, respectively, to shifts in the resistive path of the electric current (resistance, R) and capacitive properties of the human body (reactance, Xc), which ultimately impact PhA, considering that it is the angular transformation of the ratio between Xc and R. Evidence drawn from experimental research suggests that RT is highly effective for enhancing PhA, especially when adopting high-intensity, volume, and duration RT programs combining other types of exercise. Still, additional research exploring the effects of RT on whole-body and regional BIA variables of alternative population groups is recommended for further knowledge development.

Wearable Heart Rate Monitoring Device Communicating in 5G ISM Band for IoHT

Advances in wearable device technology pave the way for wireless health monitoring for medical and non-medical applications. In this work, we present a wearable heart rate monitoring platform communicating in the sub-6GHz 5G ISM band. The proposed device is composed of an Aluminium Nitride (AlN) piezoelectric sensor, a patch antenna, and a custom printed circuit board (PCB) for data acquisition and transmission. The experimental results show that the presented system can acquire heart rate together with diastolic and systolic duration, which are related to heart relaxation and contraction, respectively, from the posterior tibial artery. The overall system dimension is 20 mm by 40 mm, and the total weight is 20 g, making this device suitable for daily utilization. Furthermore, the system allows the simultaneous monitoring of multiple subjects, or a single patient from multiple body locations by using only one reader. The promising results demonstrate that the proposed system is applicable to the Internet of Healthcare Things (IoHT), and particularly Integrated Clinical Environment (ICE) applications.

A Denoising and Fourier Transformation-Based Spectrograms in ECG Classification Using Convolutional Neural Network

The non-invasive electrocardiogram (ECG) signals are useful in heart condition assessment and are found helpful in diagnosing cardiac diseases. However, traditional ways, i.e., a medical consultation required effort, knowledge, and time to interpret the ECG signals due to the large amount of data and complexity. Neural networks have been shown to be efficient recently in interpreting the biomedical signals including ECG and EEG. The novelty of the proposed work is using spectrograms instead of raw signals. Spectrograms could be easily reduced by eliminating frequencies with no ECG information. Moreover, spectrogram calculation is time-efficient through short-time Fourier transformation (STFT) which allowed to present reduced data with well-distinguishable form to convolutional neural network (CNN). The data reduction was performed through frequency filtration by taking a specific cutoff value. These steps makes architecture of the CNN model simple which showed high accuracy. The proposed approach reduced memory usage and computational power through not using complex CNN models. A large publicly available PTB-XL dataset was utilized, and two datasets were prepared, i.e., spectrograms and raw signals for binary classification. The highest accuracy of 99.06% was achieved by the proposed approach, which reflects spectrograms are better than the raw signals for ECG classification. Further, up- and down-sampling of the signals were also performed at various sampling rates and accuracies were attained.

Internet of Things-Based ECG and Vitals Healthcare Monitoring System

Health monitoring and its associated technologies have gained enormous importance over the past few years. The electrocardiogram (ECG) has long been a popular tool for assessing and diagnosing cardiovascular diseases (CVDs). Since the literature on ECG monitoring devices is growing at an exponential rate, it is becoming difficult for researchers and healthcare professionals to select, compare, and assess the systems that meet their demands while also meeting the monitoring standards. This emphasizes the necessity for a reliable reference to guide the design, categorization, and analysis of ECG monitoring systems, which will benefit both academics and practitioners. We present a complete ECG monitoring system in this work, describing the design stages and implementation of an end-to-end solution for capturing and displaying the patient's heart signals, heart rate, blood oxygen levels, and body temperature. The data will be presented on an OLED display, a developed Android application as well as in MATLAB via serial communication. The Internet of Things (IoT) approaches have a clear advantage in tackling the problem of heart disease patient care as they can transform the service mode into a widespread one and alert the healthcare services based on the patient's physical condition. Keeping this in mind, there is also the addition of a web server for monitoring the patient's status via WiFi. The prototype, which is compliant with the electrical safety regulations and medical equipment design, was further benchmarked against a commercially available off-the-shelf device, and showed an excellent accuracy of 99.56%.

Ubiquitous and smart healthcare monitoring frameworks based on machine learning: A comprehensive review

During the COVID-19 pandemic, the patient care delivery paradigm rapidly shifted to remote technological solutions. Rising rates of life expectancy of older people, and deaths due to chronic diseases (CDs) such as cancer, diabetes and respiratory disease pose many challenges to healthcare. While the feasibility of Remote Patient Monitoring (RPM) with a Smart Healthcare Monitoring (SHM) framework was somewhat questionable before the COVID-19 pandemic, it is now a proven commodity and is on its way to becoming ubiquitous. More health organizations are adopting RPM to enable CD management in the absence of individual monitoring. The current studies on SHM have reviewed the applications of IoT and/or Machine Learning (ML) in the domain, their architecture, security, privacy and other network related issues. However, no study has analyzed the AI and ubiquitous computing advances in SHM frameworks. The objective of this research is to identify and map key technical concepts in the SHM framework. In this context an interesting and meaningful classification of the research articles surveyed for this work is presented. The comprehensive and systematic review is based on the "Preferred Reporting Items for Systematic Review and Meta-Analysis" (PRISMA) approach. A total of 2540 papers were screened from leading research archives from 2016 to March 2021, and finally, 50 articles were selected for review. The major advantages, developments, distinctive architectural structure, components, technical challenges and possibilities in SHM are briefly discussed. A review of various recent cloud and fog computing based architectures, major ML implementation challenges, prospects and future trends is also presented. The survey primarily encourages the data driven predictive analytics aspects of healthcare and the development of ML models for health empowerment.

Design and Validation of a Multimodal Wearable Device for Simultaneous Collection of Electrocardiogram, Electromyogram, and Electrodermal Activity

Bio-signals are being increasingly used for the assessment of pathophysiological conditions including pain, stress, fatigue, and anxiety. For some approaches, a single signal is not sufficient to provide a comprehensive diagnosis; however, there is a growing consensus that multimodal approaches allow higher sensitivity and specificity. For instance, in visceral pain subjects, the autonomic activation can be inferred using electrodermal activity (EDA) and heart rate variability derived from the electrocardiogram (ECG), but including the muscle activation detected from the surface electromyogram (sEMG) can better differentiate the disease that causes the pain. There is no wearable device commercially capable of collecting these three signals simultaneously. This paper presents the validation of a novel multimodal low profile wearable data acquisition device for the simultaneous collection of EDA, ECG, and sEMG signals. The device was validated by comparing its performance to laboratory-scale reference devices. N = 20 healthy subjects were recruited to participate in a four-stage study that exposed them to an array of cognitive, orthostatic, and muscular stimuli, ensuring the device is sensitive to a range of stressors. Time and frequency domain analyses for all three signals showed significant similarities between our device and the reference devices. Correlation of sEMG metrics ranged from 0.81 to 0.95 and EDA/ECG metrics showed few instances of significant difference in trends between our device and the references. With only minor observed differences, we demonstrated the ability of our device to collect EDA, sEMG, and ECG signals. This device will enable future practical and impactful advances in the field of chronic pain and stress measurement and can confidently be implemented in related studies.

Dependence of Skin-Electrode Contact Impedance on Material and Skin Hydration

Dry electrodes offer an accessible continuous acquisition of biopotential signals as part of current in-home monitoring systems but often face challenges of high-contact impedance that results in poor signal quality. The performance of dry electrodes could be affected by electrode material and skin hydration. Herein, we investigate these dependencies using a circuit skin-electrode interface model, varying material and hydration in controlled benchtop experiments on a biomimetic skin phantom simulating dry and hydrated skin. Results of the model demonstrate the contribution of the individual components in the circuit to total impedance and assist in understanding the role of electrode material in the mechanistic principle of dry electrodes. Validation was performed by conducting in vivo skin-electrode contact impedance measurements across ten normative human subjects. Further, the impact of the electrode on biopotential signal quality was evaluated by demonstrating an ability to capture clinically relevant electrocardiogram signals by using dry electrodes integrated into a toilet seat cardiovascular monitoring system. Titanium electrodes resulted in better signal quality than stainless steel electrodes. Results suggest that relative permittivity of native oxide of electrode material come into contact with the skin contributes to the interface impedance, and can lead to enhancement in the capacitive coupling of biopotential signals, especially in dry skin individuals.

How is the usability of commercial activity monitors perceived by older adults and by researchers? A cross-sectional evaluation of community-living individuals

OBJECTIVES

Using commercial activity monitors may advance research with older adults. However, usability for the older population is not sufficiently established. This study aims at evaluating the usability of three wrist-worn monitors for older adults. In addition, we report on usability (including data management) for research.

DESIGN

Data were collected cross-sectionally. Between-person of three activity monitor type (Apple Watch 3, Fitbit Charge 4, Polar A370) were made.

SETTING

The activity monitors were worn in normal daily life in an urban community in Germany. The period of wear was 2 weeks.

PARTICIPANTS

Using convenience sampling, we recruited N=27 healthy older adults (≥60 years old) who were not already habitual users of activity monitors.

OUTCOMES

To evaluate usability from the participant perspective, we used the System Usability Scale (SUS) as well as a study-specific qualitative checklist. Assessment further comprised age, highest academic degree, computer proficiency and affinity for technology interaction. Usability from the researchers' perspective was assessed using quantitative data management markers and a study-specific qualitative check-list.

RESULTS

There was no significant difference between monitors in the SUS. Female gender was associated with higher SUS usability ratings. Qualitative participant-usability reports revealed distinctive shortcomings, for example, in terms of battery life and display readability. Usability for researchers came with problems in data management, such as completeness of the data download.

CONCLUSION

The usability of the monitors compared in this work differed qualitatively. Yet, the overall usability ratings by participants were comparable. Conversely, from the researchers' perspective, there were crucial differences in data management and usability that should be considered when making monitor choices for future studies.

A Review of Digital Health and Biotelemetry: Modern Approaches towards Personalized Medicine and Remote Health Assessment

With the prevalence of digitalization in all aspects of modern society, health assessment is becoming digital too. Taking advantage of the most recent technological advances and approaching medicine from an interdisciplinary perspective has allowed for important progress in healthcare services. Digital health technologies and biotelemetry devices have been more extensively employed for preventing, detecting, diagnosing, monitoring, and predicting the evolution of various diseases, without requiring wires, invasive procedures, or face-to-face interaction with medical personnel. This paper aims to review the concepts correlated to digital health, classify and describe biotelemetry devices, and present the potential of digitalization for remote health assessment, the transition to personalized medicine, and the streamlining of clinical trials.

The Relationship between Body Composition and ECG Ventricular Activity in Young Adults

This study aimed to determine the correlation between body composition (measured as weight, body mass index, and body fat percentage (BFP)) and electrocardiographic ventricular parameters (the QT and TQ intervals and the ratios between the electrical diastole and electrical systole (TQ/QT) and between the cardiac cycle and electrical diastole (RR/TQ), both for uncorrected and corrected intervals) in a sample of 50 healthy subjects (age interval 19-23 years, mean age 21.27 ± 1.41 years, 33 women and 17 men). Subjects' measurements were performed with a bioimpedancemetry body composition analyzer and a portable ECG monitor with six leads. Starting from the correlations obtained between the investigated continuous variables, we performed a standard linear regression analysis between the body composition parameters and the ECG ones. Our results revealed that some of our regression models are statistically significant (p < 0.001). Thus, a specific part of the variability of the dependent variables (ECG ventricular activity parameters for corrected QT intervals) is explained by the independent variable BFP. Therefore, body composition influences ventricular electrical activity in young adults, which implies a differentiated interpretation of the electrocardiogram in these situations.

Cardiovascular Response of Aged Outpatients With Systemic Diseases During Tooth Extraction: A Single-Center Retrospective Observational Study

Background

Aged people are maintaining many natural teeth due to improved oral health. However, compromised general health and poor oral hygiene habits at earlier ages resulted in poor status of preserved teeth. Therefore, tooth extraction is required in many aged people. More knowledge is needed because there are many risk factors during the surgery in frail aged adults. The aim of this study was to evaluate the cardiovascular response of such a population during tooth extraction and analyze risk factors to provide clinical guidance.

Methods

A retrospective study was performed on aged patients with systemic diseases who underwent tooth extraction. Data regarding demographic profiles and cardiovascular parameters of heart rate and blood pressure were collected preoperative, when local anesthesia was administered, at the beginning of tooth extraction, 5 min after tooth extraction, and postoperative. The effects of risk factors, including age, sex, and systemic diseases on these parameters were analyzed with a multilevel model.

Results

Heart rate (HR), systolic blood pressure (SBP), and diastolic blood pressure (DBP) of aged patients increased significantly when performing local anesthesia and tooth extraction. During the operation, the older patients (β = 2.011, P = 0.005) and the diabetics (β = 3.902, P < 0.0001) were associated with higher SBP, while those with more tooth extractions exhibited higher HR (β = 0.893, P = 0.007). Women patients showed both significantly elevated HR (β = 1.687, P < 0.0001) and SBP (β = 2.268, P < 0.0001). However, for coronary artery disease patients, HR (β = −2.747, P < 0.0001) and blood pressure [SBP (β = −4.094, P < 0.0001) and DBP (β = −0.87, P = 0.016)] were markedly lower than those of patients without a diagnosis of coronary artery disease.

Conclusion

Cardiovascular response of aged outpatients with systemic diseases during tooth extraction is quite significant. Age, sex, systemic diseases, and the number of tooth extraction could be risk factors closely associated with cardiovascular response. The findings might provide safety guidance for dentists on tooth extraction in this population.

A systematic review and Meta-data analysis on the applications of Deep Learning in Electrocardiogram

The success of deep learning over the traditional machine learning techniques in handling artificial intelligence application tasks such as image processing, computer vision, object detection, speech recognition, medical imaging and so on, has made deep learning the buzz word that dominates Artificial Intelligence applications. From the last decade, the applications of deep learning in physiological signals such as electrocardiogram (ECG) have attracted a good number of research. However, previous surveys have not been able to provide a systematic comprehensive review including biometric ECG based systems of the applications of deep learning in ECG with respect to domain of applications. To address this gap, we conducted a systematic literature review on the applications of deep learning in ECG including biometric ECG based systems. The study analyzed systematically, 150 primary studies with evidence of the application of deep learning in ECG. The study shows that the applications of deep learning in ECG have been applied in different domains. We presented a new taxonomy of the domains of application of the deep learning in ECG. The paper also presented discussions on biometric ECG based systems and meta-data analysis of the studies based on the domain, area, task, deep learning models, dataset sources and preprocessing methods. Challenges and potential research opportunities were highlighted to enable novel research. We believe that this study will be useful to both new researchers and expert researchers who are seeking to add knowledge to the already existing body of knowledge in ECG signal processing using deep learning algorithm.

Supplementary information

The online version contains supplementary material available at 10.1007/s12652-022-03868-z.

Detection of Atrial Fibrillation in Compressively Sensed Electrocardiogram for Remote Monitoring

The objective of this paper is to develop an optimized system to detect Atrial Fibrillation (AF) in compressively sensed electrocardiogram (ECG) for long-term remote patient monitoring. A three-stage system was developed to 1) reject ECG of poor signal quality, 2) detect AF in compressively sensed ECG, and 3) detect AF in selectively reconstructed ECG. The Long-Term AF Database (LTAFDB), sampled at 128 Hz using a 12-bit ADC with a range of 20 mV, was used to validate the system. The LTAFDB had 83,315 normal and 82,435 AF rhythm 30 s ECG segments. Clean ECG from the LTAFDB was artificially contaminated with motion artifact to achieve −12 to 12 dB Signal-to-Noise Ratio (SNR) in steps of 3 dB. The contaminated ECG was compressively sensed at 50% and 75% compression ratio (CR). The system was evaluated using average precision (AP), the area under the curve (AUC) of the receiver operator characteristic curve, and the F1 score. The system was optimized to maximize the AP and minimize ECG rejection and reconstruction ratios. The optimized system for 50% CR had 0.72 AP, 0.63 AUC, and 0.58 F1 score, 0.38 rejection ratio, and 0.38 reconstruction ratio. The optimized system for 75% CR had 0.72 AP, 0.63 AUC, and 0.59 F1 score, 0.40 rejection ratio, and 0.35 reconstruction ratio. Challenges for long-term AF monitoring are the short battery life of monitors and the high false alarm rate due to artifacts. The proposed system improves the short battery life through compressive sensing while reducing false alarms (high AP) and ECG reconstruction (low reconstruction ratio).

Comfortable Body Surface Potential Mapping by Means of a Dry Electrode Belt

Body Surface Potential Mapping is the spatial high-resolution acquisition of cardiac electrical activity from the thorax surface. The method is used to record more comprehensive cardiac information than conventional ECG measurement approaches. Although Body Surface Potential Mapping is well-known and is technically feasible, it is rarely used in clinical environments. One reason for this is the cumbersome procedure of a measurement. The placement of many adhesive gel electrodes and the contacting with many cables are particularly problematic. These limit both patients and medical staff. Therefore, the goal of this work is to technically simplify Body Surface Potential Mapping so that it would be applicable under clinical conditions. For this purpose, we present a new measurement approach in which only a narrow elastic belt is placed around the thorax to measure the electrical activity of the heart. This belt is equipped with an array of reusable gold-plated dry electrodes. With these dry electrodes, the differential voltages are measured in the horizontal and vertical directions. Afterwards, an approximation of the geometrical potential distribution on the thorax is obtained from these measurements. The results are then visualized as videos or image series or used for further analysis. A subject measurement demonstrates the applicability of this novel approach. It is shown that the obtained Body Surface Potential Maps are very similar to those found in the literature, despite a reduced spatial measurement range. This approach is not only applicable for clinical applications but also suitable for monitoring during physiological training.

XBeats: A Real-Time Electrocardiogram Monitoring and Analysis System

This work presents XBeats, a novel platform for real-time electrocardiogram monitoring and analysis that uses edge computing and machine learning for early anomaly detection. The platform encompasses a data acquisition ECG patch with 12 leads to collect heart signals, perform on-chip processing, and transmit the data to healthcare providers in real-time for further analysis. The ECG patch provides a dynamically configurable selection of the active ECG leads that could be transmitted to the backend monitoring system. The selection ranges from a single ECG lead to a complete 12-lead ECG testing configuration. XBeats implements a lightweight binary classifier for early anomaly detection to reduce the time to action should abnormal heart conditions occur. This initial detection phase is performed on the edge (i.e., the device paired with the patch) and alerts can be configured to notify designated healthcare providers. Further deep analysis can be performed on the full fidelity 12-lead data sent to the backend. A fully functional prototype of the XBeats has been implemented to demonstrate the feasibly and usability of the proposed system. Performance evaluation shows that XBeats can achieve up to 95.30% detection accuracy for abnormal conditions, while maintaining a high data acquisition rate of up to 441 samples per second. Moreover, the analytical results of the energy consumption profile show that the ECG patch provides up to 37 h of continuous 12-lead ECG streaming.

Validation of Continuous Monitoring System for Epileptic Users in Outpatient Settings

Epilepsy is a chronic disease with a significant social impact, given that the patients and their families often live conditioned by the possibility of an epileptic seizure and its possible consequences, such as accidents, injuries, or even sudden unexplained death. In this context, ambulatory monitoring allows the collection of biomedical data about the patients’ health, thus gaining more knowledge about the physiological state and daily activities of each patient in a more personalized manner. For this reason, this article proposes a novel monitoring system composed of different sensors capable of synchronously recording electrocardiogram (ECG), photoplethysmogram (PPG), and ear electroencephalogram (EEG) signals and storing them for further processing and analysis in a microSD card. This system can be used in a static and/or ambulatory way, providing information about the health state through features extracted from the ear EEG signal and the calculation of the heart rate variability (HRV) and pulse travel time (PTT). The different applied processing techniques to improve the quality of these signals are described in this work. A novel algorithm used to compute HRV and PTT robustly and accurately in ambulatory settings is also described. The developed device has also been validated and compared with other commercial systems obtaining similar results. In this way, based on the quality of the obtained signals and the low variability of the computed parameters, even in ambulatory conditions, the developed device can potentially serve as a support tool for clinical decision-taking stages.

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.

Hybrid-Pattern Recognition Modeling with Arrhythmia Signal Processing for Ubiquitous Health Management

We established a web-based ubiquitous health management (UHM) system, "ECG4UHM", for processing ECG signals with AI-enabled models to recognize hybrid arrhythmia patterns, including atrial premature atrial complex (APC), atrial fibrillation (AFib), ventricular premature complex (VPC), and ventricular tachycardia (VT), versus normal sinus rhythm (NSR). The analytical model coupled machine learning methods, such as multiple layer perceptron (MLP), random forest (RF), support vector machine (SVM), and naive Bayes (NB), to process the hybrid patterns of four arrhythmia symptoms for AI computation. The data pre-processing used Hilbert-Huang transform (HHT) with empirical mode decomposition to calculate ECGs' intrinsic mode functions (IMFs). The area centroids of the IMFs' marginal Hilbert spectrum were suggested as the HHT-based features. We engaged the MATLAB^TM compiler and runtime server in the ECG4UHM to build the recognition modules for driving AI computation to identify the arrhythmia symptoms. The modeling extracted the crucial data sets from the MIT-BIH arrhythmia open database. The validated models, including the premature pattern (i.e., APC-VPC) and the fibril-rapid pattern (i.e., AFib-VT) against NSR, could reach the best area under the curve (AUC) of the receiver operating characteristic (ROC) of approximately 0.99. The models for all hybrid patterns, without VPC versus AFib and VT, achieved an average accuracy of approximately 90%. With the prediction test, the respective AUCs of the NSR and APC versus the AFib, VPC, and VT were 0.94 and 0.93 for the RF and SVM on average. The average accuracy and the AUC of the MLP, RF, and SVM models for APC-VT reached the value of 0.98. The self-developed system with AI computation modeling can be the backend of the intelligent social-health system that can recognize hybrid arrhythmia patterns in the UHM and home-isolated cares.

The relationship between demographic features, anthropometric parameters, sleep duration, and physical activity with ECG parameters in Fasa Persian cohort study

Backgrounds

Cardiovascular Diseases (CVDs) are the first leading cause of death worldwide. The present study aimed to investigate the relationship between demographics, anthropometrics, sleep duration, physical activity, and ECG parameters in the Fasa Persian cohort study.

Methods

In this cross-sectional study, the basic information of 10,000 participants aged 35–70 years in the Fasa cohort study was used. The data used in this study included demographic data, main Electrocardiogram (ECG) parameters, anthropometric data, sleep duration, and physical activity. Data analysis was performed using t-test, chi-square, and linear regression model.

Results

Based on multivariate linear regression analysis results, increased age was significantly associated with all study parameters. Nevertheless, gender and body mass index showed no significant relationship with SV3 and PR. Wrist circumference, hip circumference and waist circumference significantly increased the mean values of the ECG parameters. However, sleep duration was not significantly associated with the ECG parameters. In addition, hypertension was major comorbidity, which was shown to increase the mean values of the ECG parameters.

Conclusion

Several factors affected the ECG parameters. Thus, to interpret ECGs, in addition to age and gender, anthropometric indices, physical activity, and previous history of comorbidities, such as hypertension and ischemic heart disease, should be taken into consideration.

The E-Textile for Biomedical Applications: A Systematic Review of Literature

The use of e-textile technologies spread out in the scientific research with several applications in both medical and nonmedical world. In particular, wearable technologies and miniature electronics devices were implemented and tested for medical research purposes. In this paper, a systematic review regarding the use of e-textile for clinical applications was conducted: the Scopus and Pubmed databases were investigate by considering research studies from 2010 to 2020. Overall, 262 papers were found, and 71 of them were included in the systematic review. Of the included studies, 63.4% focused on information and communication technology studies, while the other 36.6% focused on industrial bioengineering applications. Overall, 56.3% of the research was published as an article, while the remainder were conference papers. Papers included in the review were grouped by main aim into cardiological, muscular, physical medicine and orthopaedic, respiratory, and miscellaneous applications. The systematic review showed that there are several types of applications regarding e-textile in medicine and several devices were implemented as well; nevertheless, there is still a lack of validation studies on larger cohorts of subjects since the majority of the research only focuses on developing and testing the new device without considering a further extended validation.

Cardiac monitoring for patients with palpitations

Palpitations are one of the most common reasons for medical consultation. They tend to worry patients and can affect their quality of life. They are often a symptom associated with cardiac rhythm disorders, although there are other etiologies. For diagnosis, it is essential to be able to reliably correlate the symptoms with an electrocardiographic record allowing the identification or ruling out of a possible rhythm disorder. However, reaching a diagnosis is not always simple, given that they tend to be transitory symptoms and the patient is frequently asymptomatic at the time of assessment. In recent years, electrocardiographic monitoring systems have incorporated many technical improvements that solve several of the 24-h Holter monitor limitations. The objective of this review is to provide an update on the different monitoring methods currently available, remarking their indications and limitations, to help healthcare professionals to appropriately select and use them in the work-up of patients with palpitations.

Classification of Arrhythmia in Heartbeat Detection Using Deep Learning

The electrocardiogram (ECG) is one of the most widely used diagnostic instruments in medicine and healthcare. Deep learning methods have shown promise in healthcare prediction challenges involving ECG data. This paper aims to apply deep learning techniques on the publicly available dataset to classify arrhythmia. We have used two kinds of the dataset in our research paper. One dataset is the MIT-BIH arrhythmia database, with a sampling frequency of 125 Hz with 1,09,446 ECG beats. The classes included in this first dataset are N, S, V, F, and Q. The second database is PTB Diagnostic ECG Database. The second database has two classes. The techniques used in these two datasets are the CNN model, CNN + LSTM, and CNN + LSTM + Attention Model. 80% of the data is used for the training, and the remaining 20% is used for testing. The result achieved by using these three techniques shows the accuracy of 99.12% for the CNN model, 99.3% for CNN + LSTM, and 99.29% for CNN + LSTM + Attention Model.

A Machine Learning Framework for Balancing Training Sets of Sensor Sequential Data Streams

The recent explosive growth in the number of smart technologies relying on data collected from sensors and processed with machine learning classifiers made the training data imbalance problem more visible than ever before. Class-imbalanced sets used to train models of various events of interest are among the main reasons for a smart technology to work incorrectly or even to completely fail. This paper presents an attempt to resolve the imbalance problem in sensor sequential (time-series) data through training data augmentation. An Unrolled Generative Adversarial Networks (Unrolled GAN)-powered framework is developed and successfully used to balance the training data of smartphone accelerometer and gyroscope sensors in different contexts of road surface monitoring. Experiments with other sensor data from an open data collection are also conducted. It is demonstrated that the proposed approach allows for improving the classification performance in the case of heavily imbalanced data (the F1 score increased from 0.69 to 0.72, p<0.01, in the presented case study). However, the effect is negligible in the case of slightly imbalanced or inadequate training sets. The latter determines the limitations of this study that would be resolved in future work aimed at incorporating mechanisms for assessing the training data quality into the proposed framework and improving its computational efficiency.

Applications of Machine Learning in Ambulatory ECG

The ambulatory ECG (AECG) is an important diagnostic tool for many heart electrophysiology-related cases. AECG covers a wide spectrum of devices and applications. At the core of these devices and applications are the algorithms responsible for signal conditioning, ECG beat detection and classification, and event detections. Over the years, there has been huge progress for algorithm development and implementation thanks to great efforts by researchers, engineers, and physicians, alongside the rapid development of electronics and signal processing, especially machine learning (ML). The current efforts and progress in machine learning fields are unprecedented, and many of these ML algorithms have also been successfully applied to AECG applications. This review covers some key AECG applications of ML algorithms. However, instead of doing a general review of ML algorithms, we are focusing on the central tasks of AECG and discussing what ML can bring to solve the key challenges AECG is facing. The center tasks of AECG signal processing listed in the review include signal preprocessing, beat detection and classification, event detection, and event prediction. Each AECG device/system might have different portions and forms of those signal components depending on its application and the target, but these are the topics most relevant and of greatest concern to the people working in this area.

Anytime ECG Monitoring through the Use of a Low-Cost, User-Friendly, Wearable Device

Every year cardiovascular diseases kill the highest number of people worldwide. Among these, pathologies characterized by sporadic symptoms, such as atrial fibrillation, are difficult to be detected as state-of-the-art solutions, e.g., 12-leads electrocardiogram (ECG) or Holter devices, often fail to tackle these kinds of pathologies. Many portable devices have already been proposed, both in literature and in the market. Unfortunately, they all miss relevant features: they are either not wearable or wireless and their usage over a long-term period is often unsuitable. In addition, the quality of recordings is another key factor to perform reliable diagnosis. The ECG WATCH is a device designed for targeting all these issues. It is inexpensive, wearable (size of a watch), and can be used without the need for any medical expertise about positioning or usage. It is non-invasive, it records single-lead ECG in just 10 s, anytime, anywhere, without the need to physically travel to hospitals or cardiologists. It can acquire any of the three peripheral leads; results can be shared with physicians by simply tapping a smartphone app. The ECG WATCH quality has been tested on 30 people and has successfully compared with an electrocardiograph and an ECG simulator, both certified. The app embeds an algorithm for automatically detecting atrial fibrillation, which has been successfully tested with an official ECG simulator on different severity of atrial fibrillation. In this sense, the ECG WATCH is a promising device for anytime cardiac health monitoring.

Patient monitoring in the nonoperating room anesthesia (NORA) setting: current advances in technology

PURPOSE OF REVIEW

Nonoperating room anesthesia (NORA) procedures continue to increase in type and complexity as procedural medicine makes technical advances. Patients presenting for NORA procedures are also older and sicker than ever. Commensurate with the requirements of procedural medicine, anesthetic monitoring must meet the American Society of Anesthesiologists standards for basic monitoring.

RECENT FINDINGS

There have been improvements in the required monitors that are used for intraoperative patient care. Some of these changes have been with new technologies and others have occurred with software refinements. In addition, specialized monitoring devises have also been introduced into NORA locations (depth of hypnosis, respiratory monitoring, point-of care ultrasound). These additions to the monitoring tools available to the anesthesiologist working in the NORA-environment push the boundaries of procedures which may be accomplished in this setting.

SUMMARY

NORA procedures constitute a growing percentage of total administered anesthetics. There is no difference in the monitoring standard between that of an anesthetic administered in an operating room and a NORA location. Anesthesiologists in the NORA setting must have the same compendium of monitors available as do their colleagues working in the operating suite.