Detection of ECG characteristic points using wavelet transforms

Delineation of 12-Lead ECG Representative Beats Using Convolutional Encoder-Decoders with Residual and Recurrent Connections

The aim of this study is to address the challenge of 12-lead ECG delineation by different encoder-decoder architectures of deep neural networks (DNNs). This study compares four concepts for encoder-decoders based on a fully convolutional architecture (CED-Net) and its modifications with a recurrent layer (CED-LSTM-Net), residual connections between symmetrical encoder and decoder feature maps (CED-U-Net), and sequential residual blocks (CED-Res-Net). All DNNs transform 12-lead representative beats to three diagnostic ECG intervals (P-wave, QRS-complex, QT-interval) used for the global delineation of the representative beat (P-onset, P-offset, QRS-onset, QRS-offset, T-offset). All DNNs were trained and optimized using the large PhysioNet ECG database (PTB-XL) under identical conditions, applying an advanced approach for machine-based supervised learning with a reference algorithm for ECG delineation (ETM, Schiller AG, Baar, Switzerland). The test results indicate that all DNN architectures are equally capable of reproducing the reference delineation algorithm's measurements in the diagnostic PTB database with an average P-wave detection accuracy (96.6%) and time and duration errors: mean values (-2.6 to 2.4 ms) and standard deviations (2.9 to 11.4 ms). The validation according to the standard-based evaluation practices of diagnostic electrocardiographs with the CSE database outlines a CED-Net model, which measures P-duration (2.6 ± 11.0 ms), PQ-interval (0.9 ± 5.8 ms), QRS-duration (-2.4 ± 5.4 ms), and QT-interval (-0.7 ± 10.3 ms), which meet all standard tolerances. Noise tests with high-frequency, low-frequency, and power-line frequency noise (50/60 Hz) confirm that CED-Net, CED-Res-Net, and CED-LSTM-Net are robust to all types of noise, mostly presenting a mean duration error < 2.5 ms when compared to measurements without noise. Reduced noise immunity is observed for the U-net architecture. Comparative analysis with other published studies scores this research within the lower range of time errors, highlighting its competitive performance.

Advanced integration of 2DCNN-GRU model for accurate identification of shockable life-threatening cardiac arrhythmias: a deep learning approach

Cardiovascular diseases remain one of the main threats to human health, significantly affecting the quality and life expectancy. Effective and prompt recognition of these diseases is crucial. This research aims to develop an effective novel hybrid method for automatically detecting dangerous arrhythmias based on cardiac patients' short electrocardiogram (ECG) fragments. This study suggests using a continuous wavelet transform (CWT) to convert ECG signals into images (scalograms) and examining the task of categorizing short 2-s segments of ECG signals into four groups of dangerous arrhythmias that are shockable, including ventricular flutter (C1), ventricular fibrillation (C2), ventricular tachycardia torsade de pointes (C3), and high-rate ventricular tachycardia (C4). We propose developing a novel hybrid neural network with a deep learning architecture to classify dangerous arrhythmias. This work utilizes actual electrocardiogram (ECG) data obtained from the PhysioNet database, alongside artificially generated ECG data produced by the Synthetic Minority Over-sampling Technique (SMOTE) approach, to address the issue of imbalanced class distribution for obtaining an accuracy-trained model. Experimental results demonstrate that the proposed approach achieves high accuracy, sensitivity, specificity, precision, and an F1-score of 97.75%, 97.75%, 99.25%, 97.75%, and 97.75%, respectively, in classifying all the four shockable classes of arrhythmias and are superior to traditional methods. Our work possesses significant clinical value in real-life scenarios since it has the potential to significantly enhance the diagnosis and treatment of life-threatening arrhythmias in individuals with cardiac disease. Furthermore, our model also has demonstrated adaptability and generality for two other datasets.

Deep learning based ECG segmentation for delineation of diverse arrhythmias

Accurate delineation of key waveforms in an ECG is a critical step in extracting relevant features to support the diagnosis and treatment of heart conditions. Although deep learning based methods using segmentation models to locate P, QRS, and T waves have shown promising results, their ability to handle arrhythmias has not been studied in any detail. In this paper we investigate the effect of arrhythmias on delineation quality and develop strategies to improve performance in such cases. We introduce a U-Net-like segmentation model for ECG delineation with a particular focus on diverse arrhythmias. This is followed by a post-processing algorithm which removes noise and automatically determines the boundaries of P, QRS, and T waves. Our model has been trained on a diverse dataset and evaluated against the LUDB and QTDB datasets to show strong performance, with F1-scores exceeding 99% for QRS and T waves, and over 97% for P waves in the LUDB dataset. Furthermore, we assess various models across a wide array of arrhythmias and observe that models with a strong performance on standard benchmarks may still perform poorly on arrhythmias that are underrepresented in these benchmarks, such as tachycardias. We propose solutions to address this discrepancy.

A comprehensive review on efficient artificial intelligence models for classification of abnormal cardiac rhythms using electrocardiograms

Deep learning has made many advances in data classification using electrocardiogram (ECG) waveforms. Over the past decade, data science research has focused on developing artificial intelligence (AI) based models that can analyze ECG waveforms to identify and classify abnormal cardiac rhythms accurately. However, the primary drawback of the current AI models is that most of these models are heavy, computationally intensive, and inefficient in terms of cost for real-time implementation. In this review, we first discuss the current state-of-the-art AI models utilized for ECG-based cardiac rhythm classification. Next, we present some of the upcoming modeling methodologies which have the potential to perform real-time implementation of AI-based heart rhythm diagnosis. These models hold significant promise in being lightweight and computationally efficient without compromising the accuracy. Contemporary models predominantly utilize 12-lead ECG for cardiac rhythm classification and cardiovascular status prediction, increasing the computational burden and making real-time implementation challenging. We also summarize research studies evaluating the potential of efficient data setups to reduce the number of ECG leads without affecting classification accuracy. Lastly, we present future perspectives on AI's utility in precision medicine by providing opportunities for accurate prediction and diagnostics of cardiovascular status in patients.

A Window Into the Tired Brain: Neurophysiological Dynamics of Visuospatial Working Memory Under Fatigue

OBJECTIVE

We examine the spatiotemporal dynamics of neural activity and its correlates in heart rate and its variability (HR/HRV) during a fatiguing visuospatial working memory task.

BACKGROUND

The neural and physiological drivers of fatigue are complex, coupled, and poorly understood. Investigations that combine the fidelity of neural indices and the field-readiness of physiological measures can facilitate measurements of fatigue states in operational settings.

METHOD

Sixteen healthy adults, balanced by sex, completed a 60-minute fatiguing visuospatial working memory task. Changes in task performance, subjective measures of effort and fatigue, cerebral hemodynamics, and HR/HRV were analyzed. Peak brain activation, functional and effective connections within relevant brain networks were contrasted against spectral and temporal features of HR/HRV.

RESULTS

Task performance elicited increased neural activation in regions responsible for maintaining working memory capacity. With the onset of time-on-task effects, resource utilization was seen to increase beyond task-relevant networks. Over time, functional connections in the prefrontal cortex were seen to weaken, with changes in the causal relationships between key regions known to drive working memory. HR/HRV indices were seen to closely follow activity in the prefrontal cortex.

CONCLUSION

This investigation provided a window into the neurophysiological underpinnings of working memory under the time-on-task effect. HR/HRV was largely shown to mirror changes in cortical networks responsible for working memory, therefore supporting the possibility of unobtrusive state recognition under ecologically valid conditions.

APPLICATIONS

Findings here can inform the development of a fieldable index for cognitive fatigue.

Remote Multi-Person Heart Rate Monitoring with Smart Speakers: Overcoming Separation Constraint

Heart rate is a key vital sign that can be used to understand an individual's health condition. Recently, remote sensing techniques, especially acoustic-based sensing, have received increasing attention for their ability to non-invasively detect heart rate via commercial mobile devices such as smartphones and smart speakers. However, due to signal interference, existing methods have primarily focused on monitoring a single user and required a large separation between them when monitoring multiple people. These limitations hinder many common use cases such as couples sharing the same bed or two or more people located in close proximity. In this paper, we present an approach that can minimize interference and thereby enable simultaneous heart rate monitoring of multiple individuals in close proximity using a commonly available smart speaker prototype. Our user study, conducted under various real-life scenarios, demonstrates the system's accuracy in sensing two users' heart rates when they are seated next to each other with a median error of 0.66 beats per minute (bpm). Moreover, the system can successfully monitor up to four people in close proximity.

Template subtraction based methods for non-invasive fetal electrocardiography extraction

Assessment of fetal heart rate (fHR) through non-invasive fetal electrocardiogram (fECG) is challenging task. This study compares the performance of five template subtraction (TS) methods on Labor (12 5-min recordings) and Pregnancy datasets (10 20-min recordings). The methods include TS without adaptation, TS using singular value decomposition (TS[Formula: see text]), TS using linear prediction (TS[Formula: see text]), TS using scaling factor (TS[Formula: see text]), and sequential analysis (SA). The influence of the chosen maternal wavelet for the continuous wavelet transform (CWT) detector is also compared. The F1 score was used to measure performance. Each recording in both datasets consisted of four signals, resulting in a total comparison of 88 signals for the TS-based methods. The study reported the following results: F1 = 95.71% with TS, F1 = 95.93% with TS[Formula: see text], F1 = 95.30% with TS[Formula: see text], F1 = 95.82% with TS[Formula: see text], and F1 = 95.99% with SA. The study identified gaus3 as the suitable maternal wavelet for fetal R-peak detection using the CWT detector. Furthermore, the study classified signals from the tested datasets into categories of high, medium, and low quality, providing valuable insights for subsequent fECG signal extraction. This research contributes to advancing the understanding of non-invasive fECG signal processing and lays the groundwork for improving fetal monitoring in clinical settings.

SEResUTer: a deep learning approach for accurate ECG signal delineation and atrial fibrillation detection

Objective.Accurate detection of electrocardiogram (ECG) waveforms is crucial for computer-aided diagnosis of cardiac abnormalities. This study introduces SEResUTer, an enhanced deep learning model designed for ECG delineation and atrial fibrillation (AF) detection.Approach. Built upon a U-Net architecture, SEResUTer incorporates ResNet modules and Transformer encoders to replace convolution blocks, resulting in improved optimization and encoding capabilities. A novel masking strategy is proposed to handle incomplete expert annotations. The model is trained on the QT database (QTDB) and evaluated on the Lobachevsky University Electrocardiography Database (LUDB) to assess its generalization performance. Additionally, the model's scope is extended to AF detection using the the China Physiological Signal Challenge 2021 (CPSC2021) and the China Physiological Signal Challenge 2018 (CPSC2018) datasets.Main results.The proposed model surpasses existing traditional and deep learning approaches in ECG waveform delineation on the QTDB. It achieves remarkable average F1 scores of 99.14%, 98.48%, and 98.46% for P wave, QRS wave, and T wave delineation, respectively. Moreover, the model demonstrates exceptional generalization ability on the LUDB, achieving average SE, positive prediction rate, and F1 scores of 99.05%, 94.59%, and 94.62%, respectively. By analyzing RR interval differences and the existence of P waves, our method achieves AF identification with 99.20% accuracy on the CPSC2021 test set and demonstrates strong generalization on CPSC2018 dataset.Significance.The proposed approach enables highly accurate ECG waveform delineation and AF detection, facilitating automated analysis of large-scale ECG recordings and improving the diagnosis of cardiac abnormalities.

Wet-Adaptive Electronic Skin

Skin electronics provides remarkable opportunities for non-invasive and long-term monitoring of a wide variety of biophysical and physiological signals that are closely related to health, medicine, and human-machine interactions. Nevertheless, conventional skin electronics fabricated on elastic thin films are difficult to adapt to the wet microenvironments of the skin: Elastic thin films are non-permeable, which block the skin perspiration; Elastic thin films are difficult to adhere to wet skin; Most skin electronics are difficult to work underwater. Here, a Wet-Adaptive Electronic Skin (WADE-skin) is reported, which consists of a next-to-skin wet-adhesive fibrous layer, a next-to-air waterproof fibrous layer, and a stretchable and permeable liquid metal electrode layer. While the electronic functionality is determined by the electrode design, this WADE-skin simultaneously offers superb stretchability, wet adhesion, permeability, biocompatibility, and waterproof property. The WADE-skin can rapidly adhere to human skin after contact for a few seconds and stably maintain the adhesion over weeks even under wet conditions, without showing any negative effect to the skin health. The use of WADE-skin is demonstrated for the stable recording of electrocardiogram during intensive sweating as well as underwater activities, and as the strain sensor for the underwater operation of virtual reality-mediated human-machine interactions.

Implementation of Wavelet-Transform-Based Algorithms in an FPGA for Heart Rate and RT Interval Automatic Measurements in Real Time: Application in a Long-Term Ambulatory Electrocardiogram Monitor

Cardiovascular diseases are currently the leading cause of death worldwide. Thus, there is a need for non-invasive ambulatory (Holter) ECG monitors with automatic measurements of ECG intervals to evaluate electrocardiographic abnormalities of patients with cardiac diseases. This work presents the implementation of algorithms in an FPGA for beat-to-beat heart rate and RT interval measurements based on the continuous wavelet transform (CWT) with splines for a prototype of an ambulatory ECG monitor of three leads. The prototype's main elements are an analog-digital converter ADS1294, an FPGA of Xilinx XC7A35T-ICPG236C of the Artix-7 family of low consumption, immersed in a low-scale Cmod-A7 development card integration, an LCD display and a micro-SD memory of 16 Gb. A main state machine initializes and manages the simultaneous acquisition of three leads from the ADS1294 and filters the signals using a FIR filter. The algorithm based on the CWT with splines detects the QRS complex (R or S wave) and then the T-wave end using a search window. Finally, the heart rate (60/RR interval) and the RT interval (from R peak to T-wave end) are calculated for analysis of its dynamics. The micro-SD memory stores the three leads and the RR and RT intervals, and an LCD screen displays the beat-to-beat values of heart rate, RT interval and the electrode connection. The algorithm implemented on the FPGA achieved satisfactory results in detecting different morphologies of QRS complexes and T wave in real time for the analysis of heart rate and RT interval dynamics.

Novel phonocardiography system for heartbeat detection from various locations

The paper presents evaluation of the proposed phonocardiography (PCG) measurement system designed primarily for heartbeat detection to estimate heart rate (HR). Typically, HR estimation is performed using electrocardiography (ECG) or pulse wave as one of the fundamental diagnostic methodologies for assessing cardiac function. The system includes novel both sensory part and data processing procedure, which is based on signal preprocessing using Wavelet Transform (WT) and Shannon energy computation and heart sounds classification using K-means. Due to the lack of standardization in the placement of PCG sensors, the study focuses on evaluating the signal quality obtained from 7 different sensor locations on the subject's chest and investigates which locations are most suitable for recording heart sounds. The suitability of sensor localization was examined in 27 subjects by detecting the first two heart sounds (S1, S2). The HR detection sensitivity related to reference ECG from all sensor positions reached values over 88.9 and 77.4% in detection of S1 and S2, respectively. The placement in the middle of sternum showed the higher signal quality with median of the proper S1 and S2 detection sensitivity of 98.5 and 97.5%, respectively.

Stiffness pulsation of the human brain detected by non-invasive time-harmonic elastography

Introduction: Cerebral pulsation is a vital aspect of cerebral hemodynamics. Changes in arterial pressure in response to cardiac pulsation cause cerebral pulsation, which is related to cerebrovascular compliance and cerebral blood perfusion. Cerebrovascular compliance and blood perfusion influence the mechanical properties of the brain, causing pulsation-induced changes in cerebral stiffness. However, there is currently no imaging technique available that can directly quantify the pulsation of brain stiffness in real time. Methods: Therefore, we developed non-invasive ultrasound time-harmonic elastography (THE) technique for the real-time detection of brain stiffness pulsation. We used state-of-the-art plane-wave imaging for interleaved acquisitions of shear waves at a frequency of 60 Hz to measure stiffness and color flow imaging to measure cerebral blood flow within the middle cerebral artery. In the second experiment, we used cost-effective lineby-line B-mode imaging to measure the same mechanical parameters without flow imaging to facilitate future translation to the clinic. Results: In 10 healthy volunteers, stiffness increased during the passage of the arterial pulse wave from 4.8% ± 1.8% in the temporal parenchyma to 11% ± 5% in the basal cisterns and 13% ± 9% in the brain stem. Brain stiffness peaked in synchrony with cerebral blood flow at approximately 180 ± 30 ms after the cardiac R-wave. Line-by-line THE provided the same stiffness values with similar time resolution as high-end plane-wave THE, demonstrating the robustness of brain stiffness pulsation as an imaging marker. Discussion: Overall, this study sets the background and provides reference values for time-resolved THE in the human brain as a cost-efficient and easy-touse mechanical biomarker associated with cerebrovascular compliance.

Speckle-based structured light shift-keying for non-line-of-sight optical communication

We report an experimental proof of concept for speckle-based one-to-three non-line-of-sight (NLOS) free space optical (FSO) communication channels employing structured light shift-keying. A 3-bit gray image of resolution 100×100 pixels is encoded in Laguerre-Gaussian or Hermite-Gaussian beams and decoded using their respective intensity speckle patterns via trained 1D convolutional neural network. We have achieved an average classification accuracy of 96% and 93% using L G ml and H G pq beams, respectively, among all three channels. It demonstrates the directional independence and broadcasting capability of speckle-based decoding (SBD) in FSO communication using structured light. Further, we have extended the study from 2D to 1D SBD in one-to-three NLOS FSO communication channels to decrease the computational cost and to emphasize the importance of the 1D SBD approach.

Textile-based Wearable to Monitor Heart Activity in Paediatric Population: A Pilot Study

Background

Cardiac monitoring for children with heart disease still employs common clinical techniques that require visits to hospital either in an ambulatory or inpatient setting. Frequent cardiac monitoring, such as heart rate monitoring, can limit children's physical activity and quality of life. The main objective of this study is to evaluate the performance of a textile-based device (SKIIN) in measuring heart rate (HR) in different tasks: lying down, sitting, standing, exercising, and cooling down.

Methods

Twenty participants including healthy children and children with heart disease were included in this study. The difference between the HRs recorded by the SKIIN was compared with a reference electrocardiogram collection by normalized root mean squared error. Participants completed a questionnaire on their experience wearing the textile device with additional parental feedback on the textile device collected.

Results

Participants had the median age of 14 years (range: 10-17 years), with body mass index 23.1 ± 3.8 kg/m2 and body surface area 1.70 ± 0.25 m2. The HR recorded by SKIIN and reference system significantly changes between tasks (P < 0.001), while not significantly different from each other (P > 0.05). The normalized root mean squared error was 3.8% ± 3.0% and 3.6% ± 3.7% for healthy and the heart disease groups, respectively. All participants found the textile device non-irritating and easy to wear.

Conclusions

This study provides proof of concept that HR can be robustly and conveniently monitored by smart textiles, with similar accuracy to standard-of-care devices.

Beat-wise segmentation of electrocardiogram using adaptive windowing and deep neural network

Timely detection of anomalies and automatic interpretation of an electrocardiogram (ECG) play a crucial role in many healthcare applications, such as patient monitoring and post treatments. Beat-wise segmentation is one of the essential steps in ensuring the confidence and fidelity of many automatic ECG classification methods. In this sense, we present a reliable ECG beat segmentation technique using a CNN model with an adaptive windowing algorithm. The proposed adaptive windowing algorithm can recognise cardiac cycle events and perform segmentation, including regular and irregular beats from an ECG signal with satisfactorily accurate boundaries.The proposed algorithm was evaluated quantitatively and qualitatively based on the annotations provided with the datasets and beat-wise manual inspection. The algorithm performed satisfactorily well for the MIT-BIH dataset with a 99.08% accuracy and a 99.08% of F1-score in detecting heartbeats along with a 99.25% of accuracy in determining correct boundaries. The proposed method successfully detected heartbeats from the European S-T database with a 98.3% accuracy and 97.4% precision. The algorithm showed 99.4% of accuracy and precision for Fantasia database. In summary, the algorithm's overall performance on these three datasets suggests a high possibility of applying this algorithm in various applications in ECG analysis, including clinical applications with greater confidence.

Systolic Time Interval Extraction in Hypertensive and Hypotensive Pig Models Using Wearable Near-Field Radio-Frequency Sensors

Screening and monitoring for cardiovascular diseases (CVDs) can be enabled by analyzing systolic time intervals (STIs). As CVDs have a strong causal correlation with hypertension, it is important to validate STI sensor accuracy in hypertensive hearts to ensure consistent performance in this prevalent cardiac disease state. This work presents STI extraction using a non-invasive near-field radio-frequency (RF) sensor during normotension, hypertension, and hypotension in a pig model. Waveform features of semilunar and atrioventricular valve dynamics during systole were extracted to derive isovolumic contraction time (ICT) and left ventricular ejection time (LVET), benchmarked by a phonocardiogram and aortic catheterization. Study-wide mean relative ICT and LVET errors were -4.4ms and -3.6ms, respectively, demonstrating high accuracy during both normal and abnormal systemic pressures.Clinical relevance- This work demonstrates accurate STI extraction with relative error less than 5 ms from a non-invasive near-field RF sensor during normotensive, hypotensive, and hypertensive systemic pressures, validating the sensor's accuracy as a screening tool during this disease state.

AI-Assisted QT Measurements for Highly Automated Drug Safety Studies

Rate-corrected QT interval (QTc) prolongation has been suggested as a biomarker for the risk of drug-induced torsades de pointes, and is therefore monitored during clinical trials for the assessment of drug safety. Manual QT measurements by expert ECG analysts are expensive, laborious and prone to errors. Wavelet-based delineators and other automatic methods do not generalize well to different T wave morphologies and may require laborious tuning. Our study investigates the robustness of convolutional neural networks (CNNs) for QT measurement. We trained 3 CNN-based deep learning models on a private ECG database with human expert-annotated QT intervals. Among these models, we propose a U-Net model, which is widely used for segmentation tasks, to build a novel clinically useful QT estimator that includes QT delineation for better interpretability. We tested the 3 models on four external databases, amongst which a clinical trial investigating four drugs. Our results show that the deep learning models are in stronger agreement with the experts than the state-of-the-art wavelet-based algorithm. Indeed, the deep learning models yielded up to 71% of accurate QT measurements (absolute difference between manual and automatic QT below 15 ms) whereas the wavelet-based algorithm only allowed 52% of QT accuracy. For the 2 studies of drugs with small to no QT prolonging effect, a mean absolute difference of 6 ms (std = 5 ms) was obtained between the manual and deep learning methods. For the other 2 drugs with more significant effect on the volunteers, a mean difference of up to 17 ms (std = 17 ms) was obtained. The proposed models are therefore promising for automated QT measurements during clinical trials. They can analyze various ECG morphologies from a diversity of individuals although some QT-prolonged ECGs can be challenging. The U-Net model is particularly interesting for our application as it facilitates expert review of automatic QT intervals, which is still required by regulatory bodies, by providing QRS onset and T offset positions that are consistent with the estimated QT intervals.

The Power of ECG in Semi-Automated Seizure Detection in Addition to Two-Channel behind-the-Ear EEG

Long-term home monitoring of people living with epilepsy cannot be achieved using the standard full-scalp electroencephalography (EEG) coupled with video. Wearable seizure detection devices, such as behind-the-ear EEG (bte-EEG), offer an unobtrusive method for ambulatory follow-up of this population. Combining bte-EEG with electrocardiography (ECG) can enhance automated seizure detection performance. However, such frameworks produce high false alarm rates, making visual review necessary. This study aimed to evaluate a semi-automated multimodal wearable seizure detection framework using bte-EEG and ECG. Using the SeizeIT1 dataset of 42 patients with focal epilepsy, an automated multimodal seizure detection algorithm was used to produce seizure alarms. Two reviewers evaluated the algorithm's detections twice: (1) using only bte-EEG data and (2) using bte-EEG, ECG, and heart rate signals. The readers achieved a mean sensitivity of 59.1% in the bte-EEG visual experiment, with a false detection rate of 6.5 false detections per day. Adding ECG resulted in a higher mean sensitivity (62.2%) and a largely reduced false detection rate (mean of 2.4 false detections per day), as well as an increased inter-rater agreement. The multimodal framework allows for efficient review time, making it beneficial for both clinicians and patients.

An intelligent health monitoring and diagnosis system based on the internet of things and fuzzy logic for cardiac arrhythmia COVID-19 patients

BACKGROUND

During the COVID-19 pandemic, there is a global demand for intelligent health surveillance and diagnosis systems for patients with critical conditions, particularly those with severe heart diseases. Sophisticated measurement tools are used in hospitals worldwide to identify serious heart conditions. However, these tools need the face-to-face involvement of healthcare experts to identify cardiac problems.

OBJECTIVE

To design and implement an intelligent health monitoring and diagnosis system for critical cardiac arrhythmia COVID-19 patients.

METHODOLOGY

We use artificial intelligence tools divided into two parts: (i) IoT-based health monitoring; and (ii) fuzzy logic-based medical diagnosis. The intelligent diagnosis of heart conditions and IoT-based health surveillance by doctors is offered to critical COVID-19 patients or isolated in remote locations. Sensors, cloud storage, as well as a global system for mobile texts and emails for communication with doctors in case of emergency are employed in our proposal.

RESULTS

Our implemented system favors remote areas and isolated critical patients. This system utilizes an intelligent algorithm that employs an ECG signal pre-processed by moving through six digital filters. Then, based on the processed results, features are computed and assessed. The intelligent fuzzy system can make an autonomous diagnosis and has enough information to avoid human intervention. The algorithm is trained using ECG data from the MIT-BIH database and achieves high accuracy. In real-time validation, the fuzzy algorithm obtained almost 100% accuracy for all experiments.

CONCLUSION

Our intelligent system can be helpful in many situations, but it is particularly beneficial for isolated COVID-19 patients who have critical heart arrhythmia and must receive intensive care.

A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision

Providing reliable detection of QRS complexes is key in automated analyses of electrocardiograms (ECG). Accurate and timely R-peak detections provide a basis for ECG-based diagnoses and to synchronize radiologic, electrophysiologic, or other medical devices. Compared with classical algorithms, deep learning (DL) architectures have demonstrated superior accuracy and high generalization capacity. Furthermore, they can be embedded on edge devices for real-time inference. 3D vectorcardiograms (VCG) provide a unifying framework for detecting R-peaks regardless of the acquisition strategy or number of ECG leads. In this article, a DL architecture was demonstrated to provide enhanced precision when trained and applied on 3D VCG, with no pre-processing nor post-processing steps. Experiments were conducted on four different public databases. Using the proposed approach, high F1-scores of 99.80% and 99.64% were achieved in leave-one-out cross-validation and cross-database validation protocols, respectively. False detections, measured by a precision of 99.88% or more, were significantly reduced compared with recent state-of-the-art methods tested on the same databases, without penalty in the number of missed peaks, measured by a recall of 99.39% or more. This approach can provide new applications for devices where precision, or positive predictive value, is essential, for instance cardiac magnetic resonance imaging.

Algorithm for Mobile Platform-Based Real-Time QRS Detection

Recent advancements in smart, wearable technologies have allowed the detection of various medical conditions. In particular, continuous collection and real-time analysis of electrocardiogram data have enabled the early identification of pathologic cardiac rhythms. Various algorithms to assess cardiac rhythms have been developed, but these utilize excessive computational power. Therefore, adoption to mobile platforms requires more computationally efficient algorithms that do not sacrifice correctness. This study presents a modified QRS detection algorithm, the AccYouRate Modified Pan-Tompkins (AMPT), which is a simplified version of the well-established Pan-Tompkins algorithm. Using archived ECG data from a variety of publicly available datasets, relative to the Pan-Tompkins, the AMPT algorithm demonstrated improved computational efficiency by 5-20×, while also universally enhancing correctness, both of which favor translation to a mobile platform for continuous, real-time QRS detection.

An improved adaptive periodical segment matrix algorithm for ECG denoising based on singular value decomposition

BACKGROUND

Wearable devices that monitor heart health of cardiac disease patients in real time are in great demand.

OBJECTIVE

We propose an algorithm of improved segment periodical matrix construction for irregular electrocardiogram (ECG) signal denoising.

METHOD

While splitting the heartbeat based on each RR interval for periodical segments matrix construction, the as-filtered ECG signal is reconstructed by the maximum singular value after a singular value decomposition.

RESULTS

The results demonstrate a higher noise reduction effect with lower signal distortions of our methods compared to several singular value decomposition counterpart approaches.

CONCLUSION

Our method has great potential to enhance wearable devices diagnosis accuracy by denoising the complex noises such as electromyography artifacts in real-time ECG sensing.

Atrial Fibrillation Detection with Low Signal-to-Noise Ratio Data Using Artificial Features and Abstract Features

Detecting atrial fibrillation (AF) of short single-lead electrocardiogram (ECG) with low signal-to-noise ratio (SNR) is a key of the wearable heart monitoring system. This study proposed an AF detection method based on feature fusion to identify AF rhythm (A) from other three categories of ECG recordings, that is, normal rhythm (N), other rhythm (O), and noisy (∼) ECG recordings. So, the four categories, that is, N, A, O, and ∼ were identified from the database provided by PhysioNet/CinC Challenge 2017. The proposed method first unified the 9 to 60 seconds unbalanced ECG recordings into 30 s segments by copying, cutting, and symmetry. Then, 24 artificial features including waveform features, interval features, frequency-domain features, and nonlinear feature were extracted relying on prior knowledge. Meanwhile, a 13-layer one-dimensional convolutional neural network (1-D CNN) was constructed to yield 38 abstract features. Finally, 24 artificial features and 38 abstract features were fused to yield the feature matrix. Random forest was employed to classify the ECG recordings. In this study, the mean accuracy (Acc) of the four categories reached 0.857. The F ₁ of N, A, and O reached 0.837. The results exhibited the proposed method had relatively satisfactory performance for identifying AF from short single-lead ECG recordings with low SNR.

A novel proposed CNN-SVM architecture for ECG scalograms classification

Nowadays, the number of sudden deaths due to heart disease is increasing with the coronavirus pandemic. Therefore, automatic classification of electrocardiogram (ECG) signals is crucial for diagnosis and treatment. Thanks to deep learning algorithms, classification can be performed without manual feature extraction. In this study, we propose a novel convolutional neural networks (CNN) architecture to detect ECG types. In addition, the proposed CNN can automatically extract features from images. Here, we classify a real ECG dataset using our proposed CNN which includes 34 layers. While this dataset is one-dimensional signals, these are transformed into images (scalograms) using continuous wavelet transform (CWT). In addition, the proposed CNN is compared to known architectures: AlexNet and SqueezeNet for classifying ECG images, and we find it more effective than others. This study, which not only performed CWT but also implemented short-time Fourier transform, examines the success in recognizing ECG types for the proposed CNN. Besides, different split methods: training and testing, and cross-validation are applied in this study. Eventually, CWT and cross-validation are the best pre-processing and split methods for the proposed CNN, respectively. Although the results are quite good, we benefit from support vector machines (SVM) to obtain the best algorithm and for detecting ECG types. Essentially, the main aim of the study increases classification results. In this way, the proposed CNN is utilized as deep feature extractor and combined with SVM. As a conclusion of this study, we achieve the highest accuracy of 99.21% from the proposed CNN-SVM when using CWT. Therefore, we can express that this framework can be used as an aid to clinicians for ECG-type identification.

Independent Detection of T-Waves in Single Lead ECG Signal Using Continuous Wavelet Transform

INTRODUCTION

In the ECG signals, T-waves play a very important role in the detection of cardiac arrest. During myocardial ischemia, the first significant change occurs on the T-wave. These waves are generated due to the repolarization of the heart ventricle. The independent detection of T-waves is a bit challenging due to its variable nature, therefore, most of the algorithms available in the literature for T-wave detection use the detection of the QRS complex as the starting point. But accurate detection of Twave is very much required, as clinically, the first indication of a shortage of blood supply to the heart muscle (myocardial ischemia) shows up as changes in T-wave followed by other changes in the morphology of the ECG signal.

MATERIALS AND METHODS

In this paper, an efficient and novel algorithm based on Continuous Wavelet Transform (CWT) is presented to detect the Twave independently. In CWT, for better matching, a new mother wavelet is designed using the pattern and shape of the Twave. This algorithm is validated on all the signals of the QT database.

CONCLUSION

The algorithm attains an average sensitivity of 99.88% and positive predictivity of 99.81% for the signals annotated by the cardiologists in the database.

QRS complex detection using stationary wavelet transform and adaptive thresholding

Purpose- Electrocardiogram (ECG) signal is a record of the electrical activity of the heart and contains important clinical data about cardiovascular-related misfunctioning. The goal of the present work is to develop an improved QRS detection algorithm for the detection of heart abnormalities. Methods- In this present work stationary wavelet transforms (SWT) based method has been proposed for precise detection of QRS complex with 'sym2' mother wavelet. The stationary wavelet transform is a systematic mathematical tool to decompose the signal without downsampling using scale analysis and provides high detection of QRS complex and accurate localization of signal components. In the proposed method four level of decomposition is applied and the initial thresholding value is computed by the maximum amplitude of scale one at level four in SWT coefficients without the zero-crossing amplitude detection method. The multi-layered dynamic thresholding method has been applied to detect the true R-peak values and locate the QRS complex in the ECG signal. Results- For evaluation of results, the presented methodology is assessed on MIT-BIH, QTDB, and Noise stress test databases. In MIT-BIH, the sensitivity = 99.88%, positive predictivity = 99.93%, accuracy = 99.80% and detection error rate = 0.18% is achieved. In NSTD database, sensitivity = 97.46%, positive predictivity = 94.20%, accuracy = 91.95% and detection error rate = 8.47% and in QTDB, sensitivity = 99.95%, positive predictivity = 99.90%, accuracy = 99.71% and detection error rate = 0.16% is executed. Conclusion- In the presented proposed methodology, the computation complexity is low and exhibits a simple technique rather than an empirical approach. The proposed technique corroborates the performance for the detection of QRS complex with improved accuracy.

An Intelligent Multimodal Biometric Authentication Model for Personalised Healthcare Services

With the advent of modern technologies, the healthcare industry is moving towards a more personalised smart care model. The enablers of such care models are the Internet of Things (IoT) and Artificial Intelligence (AI). These technologies collect and analyse data from persons in care to alert relevant parties if any anomaly is detected in a patient’s regular pattern. However, such reliance on IoT devices to capture continuous data extends the attack surfaces and demands high-security measures. Both patients and devices need to be authenticated to mitigate a large number of attack vectors. The biometric authentication method has been seen as a promising technique in these scenarios. To this end, this paper proposes an AI-based multimodal biometric authentication model for single and group-based users’ device-level authentication that increases protection against the traditional single modal approach. To test the efficacy of the proposed model, a series of AI models are trained and tested using physiological biometric features such as ECG (Electrocardiogram) and PPG (Photoplethysmography) signals from five public datasets available in Physionet and Mendeley data repositories. The multimodal fusion authentication model shows promising results with 99.8% accuracy and an Equal Error Rate (EER) of 0.16.

A Machine Learning Approach for the Detection of QRS Complexes in Electrocardiogram (ECG) Using Discrete Wavelet Transform (DWT) Algorithm

This study describes a modified approach for the detection of cardiac abnormalities and QRS complexes using machine learning and support vector machine (SVM) classifiers. The suggested technique overtakes prevailing approaches in terms of both sensitivity and specificity, with 0.45 percent detection error rate for cardiac irregularities. Moreover, the vector machine classifiers validated the proposed method's superiority by accurately categorising four ECG beat types: normal, LBBBs, RBBBs, and Paced beat. The technique had 96.67 percent accuracy in MLP-BP and 98.39 percent accuracy in support of vector machine classifiers. The results imply that the SVM classifier can play an important role in the analysis of cardiac abnormalities. Furthermore, the SVM classifier also categorises ECG beats using DWT characteristics collected from ECG signals.

Beat-Level Interpretation of Intra-Patient Paradigm Based on Object Detection

Electrocardiogram (ECG), as a product that can most directly reflect the electrical activity of the heart, has become the most common clinical technique used for the analysis of cardiac abnormalities. However, it is a heavy and tedious burden for doctors to analyze a large amount of ECG data from the long-term monitoring system. The realization of automatic ECG analysis is of great significance. This work proposes a beat-level interpretation method based on the automatic annotation algorithm and object detector, which abandons the previous mode of separate R peak detection and heartbeat classification. The ground truth of the QRS complex is automatically annotated and also regarded as the object the model can learn like category information. The object detector unifies the localization and classification tasks, achieving an end-to-end optimization as well as decoupling the high dependence on the R peak. Compared with most advanced methods, this work shows superior performance. For the interpretation of 12 heartbeat types in the MIT-BIH dataset, the average accuracy is 99.60%, the average sensitivity is 97.56%, and the average specificity is 99.78%. This method can be used as a clinical auxiliary tool to help doctors diagnose arrhythmia after receiving large-scale database training.

Electrocardiogram Signal Classification in the Diagnosis of Heart Disease Based on RBF Neural Network

Heart disease is a common disease affecting human health. Electrocardiogram (ECG) classification is the most effective and direct method to detect heart disease, which is helpful to the diagnosis of most heart disease symptoms. At present, most ECG diagnosis depends on the personal judgment of medical staff, which leads to heavy burden and low efficiency of medical staff. Automatic ECG analysis technology will help the work of relevant medical staff. In this paper, we use the MIT-BIH ECG database to extract the QRS features of ECG signals by using the Pan-Tompkins algorithm. After extraction of the samples, $K$ -means clustering is used to screen the samples, and then, RBF neural network is used to analyze the ECG information. The classifier trains the electrical signal features, and the classification accuracy of the final classification model can reach 98.9%. Our experiments show that this method can effectively detect the abnormality of ECG signal and implement it for the diagnosis of heart disease.

Evolution of single-lead ECG for STEMI detection using a deep learning approach

BACKGROUND

While ST-Elevation Myocardial Infarction (STEMI) door-to-balloon times are often below 90 min, symptom to door times remain long at 2.5-h, due at least in part to a delay in diagnosis.

OBJECTIVES

To develop and validate a machine learning-guided algorithm which uses a single‑lead electrocardiogram (ECG) for STEMI detection to speed diagnosis.

METHODS

Data was extracted from the Latin America Telemedicine Infarct Network (LATIN), a population-based Acute Myocardial Infarction (AMI) program that provides care to patients in Brazil, Colombia, Mexico, and Argentina through telemedicine.

SAMPLE

the first dataset was comprised of 8511 ECGs that were used for various machine learning experiments to test our Deep Learning approach for STEMI diagnosis. The second dataset of 2542 confirmed STEMI diagnosis EKG records, including specific ischemic heart wall information (anterior, inferior, and lateral), was derived from the previous dataset to test the STEMI localization model. Preprocessing: Detection of QRS complexes by wavelet system, segmentation of each EKG record into individual heartbeats with fixed window of 0.4 s to the left and 0.9 s to the right of main. Training & Testing: 90% and 10% of the total dataset, respectively, were used for both models.

CLASSIFICATION

two 1-D convolutional neural networks were implemented, two classes were considered for first models (STEMI/Not-STEMI) and three classes for the second model (Anterior/Inferior/Lateral) each corresponding to the heart wall affected. These individual probabilities were aggregated to generate the final label for each model.

RESULTS

The single‑lead ECG strategy was able to provide an accuracy of 90.5% for STEMI detection with Lead V2, which also yielded the best results overall among individual leads. STEMI Localization model provided promising results for anterior and inferior wall STEMIs but remained suboptimal for Lateral STEMI.

CONCLUSIONS

An Artificial Intelligence-enhanced single‑lead ECG is a promising screening tool. This technology provides an autonomous and accurate STEMI diagnostic alternative that can be incorporated into wearable devices, potentially providing patients reliable means to seek treatment early and offers the potential to thereby improve STEMI outcomes in the long run.

Blood pressure and cardiac autonomic adaptations to isometric exercise training: A randomized sham-controlled study

Isometric exercise training (IET) is increasingly cited for its role in reducing resting blood pressure (BP). Despite this, few studies have investigated a potential sham effect attributing to the success of IET, thus dictating the aim of the present study. Thirty physically inactive males (n = 15) and females (n = 15) were randomly assigned into three groups. The IET group completed a wall squat intervention at 95% peak heart rate (HR) using a prescribed knee joint angle. The sham group performed a parallel intervention, but at an intensity (<75% peak HR) previously identified to be inefficacious over a 4-week training period. No-intervention controls maintained their normal daily activities. Pre- and post-measures were taken for resting and continuous blood pressure and cardiac autonomic modulation. Resting clinic and continuous beat-to-beat systolic (-15.2 ± 9.2 and -7.3 ± 5.6 mmHg), diastolic (-4.6 ± 5 and -4.5 ± 5.1), and mean (-7 ± 4.2 and -7.5 ± 5.3) BP, respectively, all significantly decreased in the IET group compared to sham and no-intervention control. The IET group observed a significant decrease in low-frequency normalized units of heart rate variability concurrent with a significant increase in high-frequency normalized units of heart rate variability compared to both the sham and no-intervention control groups. The findings of the present study reject a nonspecific effect and further support the role of IET as an effective antihypertensive intervention. Clinical Trials ID: NCT05025202.

Real-Time Patient-Specific ECG Classification by 1D Self-Operational Neural Networks

Despite the proliferation of numerous deep learning methods proposed for generic ECG classification and arrhythmia detection, compact systems with the real-time ability and high accuracy for classifying patient-specific ECG are still few. Particularly, the scarcity of patient-specific data poses an ultimate challenge to any classifier. Recently, compact 1D Convolutional Neural Networks (CNNs) have achieved the state-of-the-art performance level for the accurate classification of ventricular and supraventricular ectopic beats. However, several studies have demonstrated the fact that the learning performance of the conventional CNNs is limited because they are homogenous networks with a basic (linear) neuron model. In order to address this deficiency and further boost the patient-specific ECG classification performance, in this study, we propose 1D Self-organized Operational Neural Networks (1D Self-ONNs). Due to its self-organization capability, Self-ONNs have the utmost advantage and superiority over conventional ONNs where the prior operator search within the operator set library to find the best possible set of operators is entirely avoided. As the first study where 1D Self-ONNs are ever proposed for a classification task, our results over the MIT-BIH arrhythmia benchmark database demonstrate that 1D Self-ONNs can surpass 1D CNNs with a significant margin while having a similar computational complexity. Under AAMI recommendations and with minimal common training data used, over the entire MIT-BIH dataset 1D Self-ONNs have achieved 98% and 99.04% average accuracies, 76.6% and 93.7% average F1 scores on supra-ventricular and ventricular ectopic beat (VEB) classifications, respectively, which is the highest performance level ever reported.

Left ventricular mechanical, cardiac autonomic and metabolic responses to a single session of high intensity interval training

PURPOSE

High-intensity interval training (HIIT) produces significant health benefits. However, the acute physiological responses to HIIT are poorly understood. Therefore, we aimed to measure the acute cardiac autonomic, haemodynamic, metabolic and left ventricular mechanical responses to a single HIIT session.

METHODS

Fifty young, healthy participants completed a single HIIT session, comprising of three 30-s maximal exercise intervals on a cycle ergometer, interspersed with 2-min active recovery. Cardiac autonomics, haemodynamics and metabolic variables were measured pre-, during and post-HIIT. Conventional and speckle tracking echocardiography was used to record standard and tissue Doppler measures of left ventricular (LV) structure, function and mechanics pre- and post-HIIT.

RESULTS

Following a single HIIT session, there was significant post-exercise systolic hypotension (126 ± 13 to 111 ± 10 mmHg, p < 0.05), parallel to a significant reduction in total peripheral resistance (1640 ± 365 to 639 ± 177 dyne⋅s⋅cm⁵, p < 0.001) and significant increases in baroreceptor reflex sensitivity and baroreceptor effectiveness index (9.2 ± 11 to 24.8 ± 16.7 ms⋅mmHg^-1 and 41.8 ± 28 to 68.8 ± 16.2, respectively) during recovery compared to baseline. There was also a significant increase in the low- to high-frequency heart rate variability ratio in recovery (0.7 ± 0.48 to 1.7 ± 1, p < 0.001) and significant improvements in left ventricular global longitudinal strain (- 18.3 ± 1.2% to - 29.2 ± 2.3%, p < 0.001), and myocardial twist mechanics (1.27 ± 0.72 to 1.98 ± 0.72°·cm^-1, p = 0.028) post-HIIT compared to baseline.

CONCLUSION

A single HIIT session is associated with acute improvements in autonomic modulation, haemodynamic cardiovascular control and left ventricular function, structure and mechanics. The acute responses to HIIT provide crucial mechanistic information, which may have significant acute and chronic clinical implications.

Self-Supervised Learning with Electrocardiogram Delineation for Arrhythmia Detection

Electrocardiogram (ECG) signals convey immense information that, when properly processed, can be used to diagnose various health conditions including arrhythmia and heart failure. Deep learning algorithms have been successfully applied to medical diagnosis, but existing methods heavily rely on abundant high-quality annotations which are expensive. Self-supervised learning (SSL) circumvents this annotation cost by pre-training deep neural networks (DNNs) on auxiliary tasks that do not require manual annotation. Despite its imminent need, SSL applications to ECG classification remain under-explored. In this work, we propose an SSL algorithm based on ECG delineation and show its effectiveness for arrhythmia classification. Our experiments demonstrate not only how the proposed algorithm enhances the DNN's performance across various datasets and fractions of labeled data, but also how features learnt via pre-training on one dataset can be trans-ferred when fine-tuned on a different dataset.

Information fusion and multi-classifier system for miner fatigue recognition in plateau environments based on electrocardiography and electromyography signals

BACKGROUND AND OBJECTIVE

Human factors are important contributors to accidents, especially human error induced by fatigue. In this study, field tests and analyses were conducted on physiological indexes extracted from electrocardiography (ECG) and electromyography (EMG) signals in miners working under the extreme conditions of a plateau environment. To provide insights into models for fatigue classification and recognition based on machine learning, multi-modal feature information fusion and miner fatigue identification based on ECG and EMG signals as physiological indicators were studied.

METHODS

Fifty-five miners were randomly selected as field test subjects, and characteristic signals were extracted from 110 groups of ECG and EMG signals as the basic signals for fatigue analysis. We conducted principal component analysis (PCA) and grey relational analysis (GRA) on the measurement indicators. Support vector machine (SVM), random forest (RF) and extreme gradient boosting (XG-Boost) machine learning models were used for fatigue classification based on multi-modal information fusion. The area under the receiver operating characteristic (ROC) curve and the confusion matrix were used to evaluate the performance of the recognition models.

RESULTS

The ECG and EMG signals showed obvious changes with fatigue. The results of fatigue model identification showed that PCA feature fusion was superior to GRA feature fusion for all three machine learning approaches, and XG-Boost achieved the best performance, with a recognition accuracy of 89.47%, a sensitivity and specificity of 100%, and an AUC of 0.90. The SVM model also showed good recognition performance (89.47% accuracy, AUC=0.89). The worst performance was that of the RF model, with a recognition accuracy of only 78.95%.

CONCLUSIONS

This study shows that the physiological indexes of ECG and EMG exhibit obvious, regular changes with fatigue and that it is feasible to use SVM, RF and XG-Boost models for miner fatigue identification. The PCA fusion technique can improve the identification accuracy more than the GRA method. XG-Boost classification yields the best accuracy and robustness. This study can serve as a reference for clinical research on the identification of human fatigue at high altitudes and for the clinical study of acute mountain sickness and human acclimatization to high altitudes.

Electrocardiogram Fiducial Point Detector Using a Bilateral Filter and Symmetrical Point-Filter Structure

The characteristics or aspects of important fiducial points (FPs) in the electrocardiogram (ECG) signal are complicated because of various factors, such as non-stationary effects and low signal-to-noise ratio. Due to the various noises caused by the ECG signal measurement environment and by typical ECG signal deformation due to heart diseases, detecting such FPs becomes a challenging task. In this study, we introduce a novel PQRST complex detector using a one-dimensional bilateral filter (1DBF) and the temporal characteristics of FPs. The 1DBF with noise suppression and edge preservation preserves the P- or T-wave whereas it suppresses the QRS-interval. The 1DBF acts as a background predictor for predicting the background corresponding to the P- and T-waves and the remaining flat interval excluding the QRS-interval. The R-peak and QRS-interval are founded by the difference of the original ECG signal and the predicted background signal. Then, the Q- and S-points and the FPs related to the P- and T-wave are sequentially detected using the determined searching range and detection order based on the detected R-peak. The detection performance of the proposed method is analyzed through the MIT-BIH database (MIT-DB) and the QT database (QT-DB).

Wavelet Analysis and Self-Similarity of Photoplethysmography Signals for HRV Estimation and Quality Assessment

Peak-to-peak intervals in Photoplethysmography (PPG) can be used for heart rate variability (HRV) estimation if the PPG is collected from a healthy person at rest. Many factors, such as a person's movements or hardware issues, can affect the signal quality and make some parts of the PPG signal unsuitable for reliable peak detection. Therefore, a robust HRV estimation algorithm should not only detect peaks, but also identify corrupted signal parts. We introduce such an algorithm in this paper. It uses continuous wavelet transform (CWT) for peak detection and a combination of features derived from CWT and metrics based on PPG signals' self-similarity to identify corrupted parts. We tested the algorithm on three different datasets: a newly introduced Welltory-PPG-dataset containing PPG signals collected with smartphones using the Welltory app, and two publicly available PPG datasets: TROIKAand PPG-DaLiA. The algorithm demonstrated good accuracy in peak-to-peak intervals detection and HRV metric estimation.

The Assessment of Autonomic Nervous System Activity Based on Photoplethysmography in Healthy Young Men

Noninvasive assessment of autonomic nervous system (ANS) activity is of great importance, but the accuracy of the method used, which is primarily based on electrocardiogram-derived heart rate variability (HRV), has long been suspected. We investigated the feasibility of photoplethysmography (PPG) in ANS evaluation. Data of 32 healthy young men under four different ANS activation patterns were recorded: baseline, slow deep breathing (parasympathetic activation), cold pressor test (peripheral sympathetic activation), and mental arithmetic test (cardiac sympathetic activation). We extracted 110 PPG-based features to construct classification models for the four ANS activation patterns. Using interpretable models based on random forest, the main PPG features related to ANS activation were obtained. Results showed that pulse rate variability (PRV) exhibited similar changes to HRV across the different experiments. The four ANS patterns could be better classified using more PPG-based features compared with using HRV or PRV features, for which the classification accuracies were 0.80, 0.56, and 0.57, respectively. Sensitive features of parasympathetic activation included features of nonlinear (sample entropy), frequency, and time domains of PRV. Sensitive features of sympathetic activation were features of the amplitude and frequency domain of PRV of the PPG derivatives. Subsequently, these sensitive PPG-based features were used to fit the improved HRV parameters. The fitting results were acceptable (p < 0.01), which might provide a better method of evaluating ANS activity using PPG.

Improving R Peak Detection in ECG Signal Using Dynamic Mode Selected Energy and Adaptive Window Sizing Algorithm with Decision Tree Algorithm

R peak detection is crucial in electrocardiogram (ECG) signal analysis to detect and diagnose cardiovascular diseases (CVDs). Herein, the dynamic mode selected energy (DMSE) and adaptive window sizing (AWS) algorithm are proposed for detecting R peaks with better efficiency. The DMSE algorithm adaptively separates the QRS components and all non-objective components from the ECG signal. Based on local peaks in QRS components, the AWS algorithm adaptively determines the Region of Interest (ROI). The Feature Extraction process computes the statistical properties of energy, frequency, and noise from each ROI. The Sequential Forward Selection (SFS) procedure is used to find the best subsets of features. Based on these characteristics, an ensemble of decision tree algorithms detects the R peaks. Finally, the R peak position on the initial ECG signal is adjusted using the R location correction (RLC) algorithm. The proposed method has an experimental accuracy of 99.94%, a sensitivity of 99.98%, positive predictability of 99.96%, and a detection error rate of 0.06%. Given the high efficiency in detection and fast processing speed, the proposed approach is ideal for intelligent medical and wearable devices in the diagnosis of CVDs.

Anodal tDCS augments and preserves working memory beyond time-on-task deficits

Transcranial direct current stimulation (tDCS) of the left dorsolateral prefrontal cortex (DLPFC) has been shown to promote working memory (WM), however, its efficacy against time-on-task-related performance decline and associated cognitive fatigue remains uncertain. This study examined the impact of anodal tDCS of the left DLPFC on performance during a fatiguing visuospatial WM test. We adopted a repeated measures design, where 32 healthy adults (16 female), underwent anodal, control and sham tDCS on separate days. They completed an hour long two-back test, with stimulation intensity, onset, and duration set at 1 mA, at the 20th minute for 10 minutes respectively. Task performance, subjective responses, and heart rate variability (HRV) were captured during the experiment. Anodal tDCS substantially improved WM relative to sham tDCS and control in both sexes. These benefits lasted beyond the stimulation interval, and were unique across performance measures. However, no perceptual changes in subjective effort or fatigue levels were noted between conditions, although participants reported greater discomfort during stimulation. While mood and sleepiness changed with time-on-task, reflecting fatigue, these were largely similar across conditions. HRV increased under anodal tDCS and control, and plateaued under sham tDCS. We found that short duration anodal tDCS at 1 mA was an effective countermeasure to time-on-task deficits during a visuospatial two-back task, with enhancement and preservation of WM capacity. However, these improvements were not available at a perceptual level. Therefore, wider investigations are necessary to determine “how” such solutions will be operationalized in the field, especially within human-centered systems.