Prediction of heart failure patients with distinct left ventricular ejection fraction levels using circadian ECG features and machine learning.

Heart failure (HF) encompasses a diverse clinical spectrum, including instances of transient HF or HF with recovered ejection fraction, alongside persistent cases. This dynamic condition exhibits a growing prevalence and entails substantial healthcare expenditures, with anticipated escalation in the future. It is essential to classify HF patients into three groups based on their ejection fraction: reduced (HFrEF), mid-range (HFmEF), and preserved (HFpEF), such as for diagnosis, risk assessment, treatment choice, and the ongoing monitoring of heart failure. Nevertheless, obtaining a definitive prediction poses challenges, requiring the reliance on echocardiography. On the contrary, an electrocardiogram (ECG) provides a straightforward, quick, continuous assessment of the patient's cardiac rhythm, serving as a cost-effective adjunct to echocardiography. In this research, we evaluate several machine learning (ML)-based classification models, such as K-nearest neighbors (KNN), neural networks (NN), support vector machines (SVM), and decision trees (TREE), to classify left ventricular ejection fraction (LVEF) for three categories of HF patients at hourly intervals, using 24-hour ECG recordings. Information from heterogeneous group of 303 heart failure patients, encompassing HFpEF, HFmEF, or HFrEF classes, was acquired from a multicenter dataset involving both American and Greek populations. Features extracted from ECG data were employed to train the aforementioned ML classification models, with the training occurring in one-hour intervals. To optimize the classification of LVEF levels in coronary artery disease (CAD) patients, a nested cross-validation approach was employed for hyperparameter tuning. HF patients were best classified using TREE and KNN models, with an overall accuracy of 91.2% and 90.9%, and average area under the curve of the receiver operating characteristics (AUROC) of 0.98, and 0.99, respectively. Furthermore, according to the experimental findings, the time periods of midnight-1 am, 8-9 am, and 10-11 pm were the ones that contributed to the highest classification accuracy. The results pave the way for creating an automated screening system tailored for patients with CAD, utilizing optimal measurement timings aligned with their circadian cycles.

Securing Internet-of-Medical-Things networks using cancellable ECG recognition.

Reinforcement of the Internet of Medical Things (IoMT) network security has become extremely significant as these networks enable both patients and healthcare providers to communicate with each other by exchanging medical signals, data, and vital reports in a safe way. To ensure the safe transmission of sensitive information, robust and secure access mechanisms are paramount. Vulnerabilities in these networks, particularly at the access points, could expose patients to significant risks. Among the possible security measures, biometric authentication is becoming a more feasible choice, with a focus on leveraging regularly-monitored biomedical signals like Electrocardiogram (ECG) signals due to their unique characteristics. A notable challenge within all biometric authentication systems is the risk of losing original biometric traits, if hackers successfully compromise the biometric template storage space. Current research endorses replacement of the original biometrics used in access control with cancellable templates. These are produced using encryption or non-invertible transformation, which improves security by enabling the biometric templates to be changed in case an unwanted access is detected. This study presents a comprehensive framework for ECG-based recognition with cancellable templates. This framework may be used for accessing IoMT networks. An innovative methodology is introduced through non-invertible modification of ECG signals using blind signal separation and lightweight encryption. The basic idea here depends on the assumption that if the ECG signal and an auxiliary audio signal for the same person are subjected to a separation algorithm, the algorithm will yield two uncorrelated components through the minimization of a correlation cost function. Hence, the obtained outputs from the separation algorithm will be distorted versions of the ECG as well as the audio signals. The distorted versions of the ECG signals can be treated with a lightweight encryption stage and used as cancellable templates. Security enhancement is achieved through the utilization of the lightweight encryption stage based on a user-specific pattern and XOR operation, thereby reducing the processing burden associated with conventional encryption methods. The proposed framework efficacy is demonstrated through its application on the ECG-ID and MIT-BIH datasets, yielding promising results. The experimental evaluation reveals an Equal Error Rate (EER) of 0.134 on the ECG-ID dataset and 0.4 on the MIT-BIH dataset, alongside an exceptionally large Area under the Receiver Operating Characteristic curve (AROC) of 99.96% for both datasets. These results underscore the framework potential in securing IoMT networks through cancellable biometrics, offering a hybrid security model that combines the strengths of non-invertible transformations and lightweight encryption.

Diagnostic accuracy of digital technologies compared with 12-lead ECG in the diagnosis of atrial fibrillation in adults: A protocol for a systematic review.

BACKGROUND: Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia in the world. AF increases the risk of stroke 5-fold, though the risk can be reduced with appropriate treatment. Therefore, early diagnosis is imperative but remains a global challenge. In low-and middle-income countries (LMICs), a lack of diagnostic equipment and under-resourced healthcare systems generate further barriers. The rapid development of digital technologies that are capable of diagnosing AF remotely and cost-effectively could prove beneficial for LMICs. However, evidence is lacking on what digital technologies exist and how they compare in regards to diagnostic accuracy. We aim to systematically review the diagnostic accuracy of all digital technologies capable of AF diagnosis. METHODS: MEDLINE, Embase and Web of Science will be searched for eligible studies. Free text terms will be combined with corresponding index terms where available and searches will not be limited by language nor time of publication. Cohort or cross-sectional studies comprising adult (≥18 years) participants will be included. Only studies that use a 12-lead ECG as the reference test (comparator) and report outcomes of sensitivity, specificity, the diagnostic odds ratio (DOR) or the positive and negative predictive value (PPV and NPV) will be included (or if they provide sufficient data to calculate these outcomes). Two reviewers will independently assess articles for inclusion, extract data using a piloted tool and assess risk of bias using the QUADAS-2 tool. The feasibility of a meta-analysis will be determined by assessing heterogeneity across the studies, grouped by index device, diagnostic threshold and setting. If a meta-analysis is feasible for any index device, pooled sensitivity and specificity will be calculated using a random effect model and presented in forest plots. DISCUSSION: The findings of our review will provide a comprehensive synthesis of the diagnostic accuracy of available digital technologies capable for diagnosing AF. Thus, this review will aid in the identification of which devices could be further trialed and implemented, particularly in a LMIC setting, to improve the early diagnosis of AF. TRIAL REGISTRATION: Systematic review registration: PROSPERO registration number is CRD42021290542. https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021290542.

Early predictors of severe left main and/or three-vessel disease in patients with non-ST-segment elevation myocardial infarction: A dual-center retrospective study.

BACKGROUND: Early detection of patients concomitant with left main and/or three-vessel disease (LM/3VD) and high SYNTAX score (SS) is crucial for determining the most effective revascularization options regarding the use of antiplatelet medications and prognosis risk stratification. However, there is a lack of study for predictors of LM/3VD with SS in patients with non-ST-segment elevation myocardial infarction (NSTEMI). We aimed to identify potential factors that could predict LM/3VD with high SS (SS > 22) in patients with NSTEMI. METHODS: This dual-center retrospective study included a total of 481 patients diagnosed with NSTEMI who performed coronary angiography procedures. Clinical factors on admission were collected. The patients were divided into non-LM/3VD, Nonsevere LM/3VD (SS ≤ 22), and Severe LM/3VD (SS > 22) groups. To identify independent predictors, Univariate and logistic regression analyses were conducted on the clinical parameters. RESULTS: A total of 481 patients were included, with an average age of 60.9 years and 75.9% being male. Among these patients, 108 individuals had severe LM/3VD. Based on the findings of a multivariate logistic regression analysis, the extent of ST-segment elevation observed in lead aVR (OR: 7.431, 95% CI: 3.862-14.301, p < .001) and age (OR: 1.050, 95% CI: 1.029-1.071, p < .001) were identified as independent predictors of severe LM/3VD. CONCLUSION: This study indicated that the age of patients and the extent of ST-segment elevation observed in lead aVR on initial electrocardiogram were the independent predictive factors of LM/3VD with high SS in patients with NSTEMI.

Temporal Relationship-Aware Treadmill Exercise Test Analysis Network for Coronary Artery Disease Diagnosis.

The treadmill exercise test (TET) serves as a non-invasive method for the diagnosis of coronary artery disease (CAD). Despite its widespread use, TET reports are susceptible to external influences, heightening the risk of misdiagnosis and underdiagnosis. In this paper, we propose a novel automatic CAD diagnosis approach. The proposed approach introduces a customized preprocessing method to obtain clear electrocardiograms (ECGs) from individual TET reports. Additionally, it presents TETDiaNet, a novel neural network designed to explore the temporal relationships within TET ECGs. Central to TETDiaNet is the TETDia block, which mimics clinicians' diagnostic processes to extract essential diagnostic information. This block encompasses an intra-state contextual learning module and an inter-state contextual learning module, modeling the temporal relationships within a single state and between states, respectively. These two modules help the TETDia block to capture effective diagnosis information by exploring the temporal relationships within TET ECGs. Furthermore, we establish a new TET dataset named TET4CAD for CAD diagnosis. It contains simplified TET reports for 192 CAD patients and 224 non-CAD patients, and each patient undergoes coronary angiography for labeling. Experimental results on TET4CAD underscore the superior performance of the proposed approach, highlighting the discriminative value of the temporal relationships within TET ECGs for CAD diagnosis.

A Multimodal Feature Fusion Brain Fatigue Recognition System Based on Bayes-gcForest.

Modern society increasingly recognizes brain fatigue as a critical factor affecting human health and productivity. This study introduces a novel, portable, cost-effective, and user-friendly system for real-time collection, monitoring, and analysis of physiological signals aimed at enhancing the precision and efficiency of brain fatigue recognition and broadening its application scope. Utilizing raw physiological data, this study constructed a compact dataset that incorporated EEG and ECG data from 20 subjects to index fatigue characteristics. By employing a Bayesian-optimized multi-granularity cascade forest (Bayes-gcForest) for fatigue state recognition, this study achieved recognition rates of 95.71% and 96.13% on the DROZY public dataset and constructed dataset, respectively. These results highlight the effectiveness of the multi-modal feature fusion model in brain fatigue recognition, providing a viable solution for cost-effective and efficient fatigue monitoring. Furthermore, this approach offers theoretical support for designing rest systems for researchers.

Enhancing Fetal Electrocardiogram Signal Extraction Accuracy through a CycleGAN Utilizing Combined CNN-BiLSTM Architecture.

The fetal electrocardiogram (FECG) records changes in the graph of fetal cardiac action potential during conduction, reflecting the developmental status of the fetus in utero and its physiological cardiac activity. Morphological alterations in the FECG can indicate intrauterine hypoxia, fetal distress, and neonatal asphyxia early on, enhancing maternal and fetal safety through prompt clinical intervention, thereby reducing neonatal morbidity and mortality. To reconstruct FECG signals with clear morphological information, this paper proposes a novel deep learning model, CBLS-CycleGAN. The model's generator combines spatial features extracted by the CNN with temporal features extracted by the BiLSTM network, thus ensuring that the reconstructed signals possess combined features with spatial and temporal dependencies. The model's discriminator utilizes PatchGAN, employing small segments of the signal as discriminative inputs to concentrate the training process on capturing signal details. Evaluating the model using two real FECG signal databases, namely "Abdominal and Direct Fetal ECG Database" and "Fetal Electrocardiograms, Direct and Abdominal with Reference Heartbeat Annotations", resulted in a mean MSE and MAE of 0.019 and 0.006, respectively. It detects the FQRS compound wave with a sensitivity, positive predictive value, and F1 of 99.51%, 99.57%, and 99.54%, respectively. This paper's model effectively preserves the morphological information of FECG signals, capturing not only the FQRS compound wave but also the fetal P-wave, T-wave, P-R interval, and ST segment information, providing clinicians with crucial diagnostic insights and a scientific foundation for developing rational treatment protocols.

Improving Adversarial Robustness of ECG Classification Based on Lipschitz Constraints and Channel Activation Suppression.

Deep neural networks (DNNs) are increasingly important in the medical diagnosis of electrocardiogram (ECG) signals. However, research has shown that DNNs are highly vulnerable to adversarial examples, which can be created by carefully crafted perturbations. This vulnerability can lead to potential medical accidents. This poses new challenges for the application of DNNs in the medical diagnosis of ECG signals. This paper proposes a novel network Channel Activation Suppression with Lipschitz Constraints Net (CASLCNet), which employs the Channel-wise Activation Suppressing (CAS) strategy to dynamically adjust the contribution of different channels to the class prediction and uses the 1-Lipschitz's ℓ∞ distance network as a robust classifier to reduce the impact of adversarial perturbations on the model itself in order to increase the adversarial robustness of the model. The experimental results demonstrate that CASLCNet achieves ACCrobust scores of 91.03% and 83.01% when subjected to PGD attacks on the MIT-BIH and CPSC2018 datasets, respectively, which proves that the proposed method in this paper enhances the model's adversarial robustness while maintaining a high accuracy rate.

MA-MIL: Sampling point-level abnormal ECG location method via weakly supervised learning.

BACKGROUND AND OBJECTIVE: Current automatic electrocardiogram (ECG) diagnostic systems could provide classification outcomes but often lack explanations for these results. This limitation hampers their application in clinical diagnoses. Previous supervised learning could not highlight abnormal segmentation output accurately enough for clinical application without manual labeling of large ECG datasets. METHOD: In this study, we present a multi-instance learning framework called MA-MIL, which has designed a multi-layer and multi-instance structure that is aggregated step by step at different scales. We evaluated our method using the public MIT-BIH dataset and our private dataset. RESULTS: The results show that our model performed well in both ECG classification output and heartbeat level, sub-heartbeat level abnormal segment detection, with accuracy and F1 scores of 0.987 and 0.986 for ECG classification and 0.968 and 0.949 for heartbeat level abnormal detection, respectively. Compared to visualization methods, the IoU values of MA-MIL improved by at least 17 % and at most 31 % across all categories. CONCLUSIONS: MA-MIL could accurately locate the abnormal ECG segment, offering more trustworthy results for clinical application.

Prediction of adverse cardiovascular events in children using artificial intelligence-based electrocardiogram.

BACKGROUND: Convolutional neural networks (CNNs) have emerged as a novel method for evaluating heart failure (HF) in adult electrocardiograms (ECGs). However, such CNNs are not applicable to pediatric HF, where abnormal anatomy of congenital heart defects plays an important role. ECG-based CNNs reflecting neurohormonal activation (NHA) may be a useful marker of pediatric HF. This study aimed to develop and validate an ECG-derived marker of pediatric HF that reflects the risk of future cardiovascular events. METHODS: Based on 21,378 ECGs from 8324 children, a CNN was trained using B-type natriuretic peptide (BNP) and the occurrence of major adverse cardiovascular events (MACEs). The output of the model, or the electrical heart failure indicator (EHFI), was compared with the BNP regarding its ability to predict MACEs in 813 ECGs from 295 children. RESULTS: EHFI achieved a better area under the curve than BNP in predicting MACEs within 180 days (0.826 versus 0.691, p = 0.03). On Cox univariable analyses, both EHFI and BNP were significantly associated with MACE (log10 EHFI: hazard ratio [HR] = 16.5, p < 0.005 and log10 BNP: HR = 4.4, p < 0.005). The time-dependent average precisions of EHFI in predicting MACEs were 32.4%-67.9% and 1.6-7.5-fold higher than those of BNP in the early period. Additionally, the MACE rate increased monotonically with EHFI, whereas the rate peaked at approximately 100 pg/mL of BNP and decreased in the higher range. CONCLUSIONS: ECG-derived CNN is a novel marker of HF with different prognostic potential from BNP. CNN-based ECG analysis may provide a new guide for assessing pediatric HF.

The role of beat-by-beat cardiac features in machine learning classification of ischemic heart disease (IHD) in magnetocardiogram (MCG).

Cardiac electrical changes associated with ischemic heart disease (IHD) are subtle and could be detected even in rest condition in magnetocardiography (MCG) which measures weak cardiac magnetic fields. Cardiac features that are derived from MCG recorded from multiple locations on the chest of subjects and some conventional time domain indices are widely used in Machine learning (ML) classifiers to objectively distinguish IHD and control subjects. Most of the earlier studies have employed features that are derived from signal-averaged cardiac beats and have ignored inter-beat information. The present study demonstrates the utility of beat-by-beat features to be useful in classifying IHD subjects (n = 23) and healthy controls (n = 75) in 37-channel MCG data taken under rest condition of subjects. The study reveals the importance of three features (out of eight measured features) namely, the field map angle (FMA) computed from magnetic field map, beat-by-beat variations of alpha angle in the ST-T region and T wave magnitude variations in yielding a better classification accuracy (92.7 %) against that achieved by conventional features (81 %). Further, beat-by-beat features are also found to augment the accuracy in classifying myocardial infarction (MI) Versus control subjects in two public ECG databases (92 % from 88 % and 94 % from 77 %). These demonstrations summarily suggest the importance of beat-by-beat features in clinical diagnosis of ischemia.

Comparison of electrographic changes, clinical features and outcomes in different variants of Takotsubo syndrome.

BACKGROUND: Dysfunction of the left ventricular (LV) apex (apical variant) is the most common form in Takotsubo syndrome (TS). Several less common non-apical variants have been described - mid-ventricular, basal and focal. We hypothesised that the clinical presentation, and electrocardiographic (ECG) findings may vary between apical and non-apical TS. METHODS: We prospectively identified 194 consecutive patients with TS presenting to Middlemore Hospital, Auckland and obtained clinical, echocardiography, coronary angiography, and long-term follow-up data. ECGs at admission and Day 1 were compared. RESULTS: Of 194 patients with TS, 168 (86.6%) had apical TS, and 26 (13.4%) non-apical TS (11 mid-ventricular TS, 5 basal TS, 10 focal TS). Apical TS patients had more significant LV systolic impairment (p = 0.001) and longer length of stay (p = 0.001). The extent of T-wave inversion (TWI) was similar for both groups on admission (p = 0.88). By Day 1 the extent of TWI was greater in apical TS group (median number of leads 5 vs. 1, p = 0.02). The change in QTc interval between admission and Day 1 was greater in apical TS group (29.7 ms vs. 2.77 ms, p < 0.001). Composite in-hospital complication rate was similar for both groups (13.7% vs. 15.4%, p = 0.77). CONCLUSIONS: Compared with non-apical variants, apical TS patients develop more extensive TWI and greater QT prolongation on ECG, and more significant LV systolic impairment, but in-hospital complications were similar. Clinicians should be aware that there is a sub-group of TS patients who have non-apical regional wall motion abnormalities and who don't develop ECG changes typical of the more common apical variant.

Real-world validation of smartphone-based photoplethysmography for rate and rhythm monitoring in atrial fibrillation.

AIMS: Photoplethysmography- (PPG) based smartphone applications facilitate heart rate and rhythm monitoring in patients with paroxysmal and persistent atrial fibrillation (AF). Despite an endorsement from the European Heart Rhythm Association, validation studies in this setting are lacking. Therefore, we evaluated the accuracy of PPG-derived heart rate and rhythm classification in subjects with an established diagnosis of AF in unsupervised real-world conditions. METHODS AND RESULTS: Fifty consecutive patients were enrolled, 4 weeks before undergoing AF ablation. Patients used a handheld single-lead electrocardiography (ECG) device and a fingertip PPG smartphone application to record 3907 heart rhythm measurements twice daily during 8 weeks. The ECG was performed immediately before and after each PPG recording and was given a diagnosis by the majority of three blinded cardiologists. A consistent ECG diagnosis was exhibited along with PPG data of sufficient quality in 3407 measurements. A single measurement exhibited good quality more often with ECG (93.2%) compared to PPG (89.5%; P < 0.001). However, PPG signal quality improved to 96.6% with repeated measurements. Photoplethysmography-based detection of AF demonstrated excellent sensitivity [98.3%; confidence interval (CI): 96.7-99.9%], specificity (99.9%; CI: 99.8-100.0%), positive predictive value (99.6%; CI: 99.1-100.0%), and negative predictive value (99.6%; CI: 99.0-100.0%). Photoplethysmography underestimated the heart rate in AF with 6.6 b.p.m. (95% CI: 5.8 b.p.m. to 7.4 b.p.m.). Bland-Altman analysis revealed increased underestimation in high heart rates. The root mean square error was 11.8 b.p.m. CONCLUSION: Smartphone applications using PPG can be used to monitor patients with AF in unsupervised real-world conditions. The accuracy of AF detection algorithms in this setting is excellent, but PPG-derived heart rate may tend to underestimate higher heart rates.

ECG signal quality in intermittent long-term dry electrode recordings with controlled motion artifacts.

Wearable long-term monitoring applications are becoming more and more popular in both the consumer and the medical market. In wearable ECG monitoring, the data quality depends on the properties of the electrodes and on how they interface with the skin. Dry electrodes do not require any action from the user. They usually do not irritate the skin, and they provide sufficiently high-quality data for ECG monitoring purposes during low-intensity user activity. We investigated prospective motion artifact-resistant dry electrode materials for wearable ECG monitoring. The tested materials were (1) porous: conductive polymer, conductive silver fabric; and (2) solid: stainless steel, silver, and platinum. ECG was acquired from test subjects in a 10-min continuous settling test and in a 48-h intermittent long-term test. In the settling test, the electrodes were stationary, whereas both stationary and controlled motion artifact tests were included in the long-term test. The signal-to-noise ratio (SNR) was used as the figure of merit to quantify the results. Skin-electrode interface impedance was measured to quantify its effect on the ECG, as well as to leverage the dry electrode ECG amplifier design. The SNR of all electrode types increased during the settling test. In the long-term test, the SNR was generally elevated further. The introduction of electrode movement reduced the SNR markedly. Solid electrodes had a higher SNR and lower skin-electrode impedance than porous electrodes. In the stationary testing, stainless steel showed the highest SNR, followed by platinum, silver, conductive polymer, and conductive fabric. In the movement testing, the order was platinum, stainless steel, silver, conductive polymer, and conductive fabric.

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

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

Prototype Learning for Medical Time Series Classification via Human-Machine Collaboration.

Deep neural networks must address the dual challenge of delivering high-accuracy predictions and providing user-friendly explanations. While deep models are widely used in the field of time series modeling, deciphering the core principles that govern the models' outputs remains a significant challenge. This is crucial for fostering the development of trusted models and facilitating domain expert validation, thereby empowering users and domain experts to utilize them confidently in high-risk decision-making contexts (e.g., decision-support systems in healthcare). In this work, we put forward a deep prototype learning model that supports interpretable and manipulable modeling and classification of medical time series (i.e., ECG signal). Specifically, we first optimize the representation of single heartbeat data by employing a bidirectional long short-term memory and attention mechanism, and then construct prototypes during the training phase. The final classification outcomes (i.e., normal sinus rhythm, atrial fibrillation, and other rhythm) are determined by comparing the input with the obtained prototypes. Moreover, the proposed model presents a human-machine collaboration mechanism, allowing domain experts to refine the prototypes by integrating their expertise to further enhance the model's performance (contrary to the human-in-the-loop paradigm, where humans primarily act as supervisors or correctors, intervening when required, our approach focuses on a human-machine collaboration, wherein both parties engage as partners, enabling more fluid and integrated interactions). The experimental outcomes presented herein delineate that, within the realm of binary classification tasks-specifically distinguishing between normal sinus rhythm and atrial fibrillation-our proposed model, albeit registering marginally lower performance in comparison to certain established baseline models such as Convolutional Neural Networks (CNNs) and bidirectional long short-term memory with attention mechanisms (Bi-LSTMAttns), evidently surpasses other contemporary state-of-the-art prototype baseline models. Moreover, it demonstrates significantly enhanced performance relative to these prototype baseline models in the context of triple classification tasks, which encompass normal sinus rhythm, atrial fibrillation, and other rhythm classifications. The proposed model manifests a commendable prediction accuracy of 0.8414, coupled with macro precision, recall, and F1-score metrics of 0.8449, 0.8224, and 0.8235, respectively, achieving both high classification accuracy as well as good interpretability.

[New frontiers in pacing: from myocardial pacing to conduction system pacing]. / Nuove frontiere dell'elettrostimolazione: dal pacing del miocardio comune al pacing del sistema di conduzione.

For many years, cardiac pacing has been based on the stimulation of right ventricular common myocardium to correct diseases of the conduction system. The birth and the development of cardiac resynchronization have led to growing interest in the correction and prevention of pacing-induced dyssynchrony. Many observational studies and some randomized clinical trials have shown that conduction system pacing (CSP) can not only prevent pacing-induced dyssynchrony but can also correct proximal conduction system blocks, with reduction of QRS duration and with equal or greater effectiveness than biventricular pacing. Based on these results, many Italian electrophysiologists have changed the stimulation target from the right ventricular common myocardium to CSP. The two techniques with greater clinical impact are the His bundle stimulation and the left bundle branch pacing. The latter, in particular, because of its easier implantation technique and better electric parameters, is spreading like wildfire and is representing a real revolution in the cardiac pacing field. However, despite the growing amount of data, until now, the European Society of Cardiology guidelines give a very limited role to CSP.

Evaluation of the introduction of a single-lead ECG device and digital cardiologist consultation platform among general practitioners in the Netherlands.

AIM: To evaluate the use of a single-lead electrocardiography (1L-ECG) device and digital cardiologist consultation platform in diagnosing arrhythmias among general practitioners (GPs). BACKGROUND: Handheld 1L-ECG offers a user-friendly alternative to conventional 12-lead ECG in primary care. While GPs can safely rule out arrhythmias on 1L-ECG recordings, expert consultation is required to confirm suspected arrhythmias. Little is known about GPs' experiences with both a 1L-ECG device and digital consultation platform for daily practice. METHODS: We used two distinct methods in this study. First, in an observational study, we collected and described all cases shared by GPs within a digital cardiologist consultation platform initiated by a local GP cooperative. This GP cooperative distributed KardiaMobile 1L-ECG devices among all affiliated GPs (n = 203) and invited them to this consultation platform. In the second part, we used an online questionnaire to evaluate the experiences of these GPs using the KardiaMobile and consultation platform. FINDINGS: In total, 98 (48%) GPs participated in this project, of whom 48 (49%) shared 156 cases. The expert panel was able to provide a definitive rhythm interpretation in 130 (83.3%) shared cases and answered in a median of 4 min (IQR: 2-18). GPs responding to the questionnaire (n = 43; 44%) thought the KardiaMobile was of added value for rhythm diagnostics in primary care (n = 42; 98%) and easy to use (n = 41; 95%). Most GPs (n = 36; 84%) valued the feedback from the cardiologists in the consultation platform. GPs experienced this project to have a positive impact on both the quality of care and diagnostic efficiency for patients with (suspected) cardiac arrhythmias. Although we lack a comprehensive picture of experienced impediments by GPs, solving technical issues was mentioned to be helpful for further implementation. More research is needed to explore reasons of GPs not motivated using these tools and to assess real-life clinical impact.

An open-access simultaneous electrocardiogram and phonocardiogram database.

Objective.The EPHNOGRAM project aimed to develop a low-cost, low-power device for simultaneous electrocardiogram (ECG) and phonocardiogram (PCG) recording, with additional channels for environmental audio to enhance PCG through active noise cancellation. The objective was to study multimodal electro-mechanical activities of the heart, offering insights into the differences and synergies between these modalities during various cardiac activity levels.Approach.We developed and tested several hardware prototypes of a simultaneous ECG-PCG acquisition device. Using this technology, we collected simultaneous ECG and PCG data from 24 healthy adults during different physical activities, including resting, walking, running, and stationary biking, in an indoor fitness center. The data were annotated using a robust software that we developed for detecting ECG R-peaks and PCG S1 and S2 components, and overseen by a human expert. We also developed machine learning models using ECG-based, PCG-based, and joint ECG-PCG features, like R-R and S1-S2 intervals, to classify physical activities and analyze electro-mechanical dynamics.Main results.The results show a significant coupling between ECG and PCG components, especially during high-intensity exercise. Notable micro-variations in S2-based heart rate show differences in the heart's electrical and mechanical functions. The Lomb-Scargle periodogram and approximate entropy analyses confirm the higher volatility of S2-based heart rate compared to ECG-based heart rate. Correlation analysis shows stronger coupling between R-R and R-S1 intervals during high-intensity activities. Hybrid ECG-PCG features, like the R-S2 interval, were identified as more informative for physical activity classification through mRMR feature selection and SHAP value analysis.Significance.The EPHNOGRAM database, is available on PhysioNet. The database enhances our understanding of cardiac function, enabling future studies on the heart's mechanical and electrical interrelationships. The results of this study can contribute to improved cardiac condition diagnoses. Additionally, the designed hardware has the potential for integration into wearable devices and the development of multimodal stress test technologies.

A Wavelet-Based Approach for Motion Artifact Reduction in Ambulatory Seismocardiography.

Wearable sensing has become a vital approach to cardiac health monitoring, and seismocardiography (SCG) is emerging as a promising technology in this field. However, the applicability of SCG is hindered by motion artifacts, including those encountered in practice of which the strongest source is walking. This holds back the translation of SCG to clinical settings. We therefore investigated techniques to enhance the quality of SCG signals in the presence of motion artifacts. To simulate ambulant recordings, we corrupted a clean SCG dataset with real-walking-vibrational noise. We decomposed the signal using several empirical-mode-decomposition methods and the maximum overlap discrete wavelet transform (MODWT). By combining MODWT, time-frequency masking, and nonnegative matrix factorization, we developed a novel algorithm which leveraged the vertical axis accelerometer to reduce walking vibrations in dorsoventral SCG. The accuracy and applicability of our method was verified using heart rate estimation. We used an interactive selection approach to improve estimation accuracy. The best decomposition method for reduction of motion artifact noise was the MODWT. Our algorithm improved heart rate estimation from 0.1 to 0.8 r-squared at -15 dB signal-to-noise ratio (SNR). Our method reduces motion artifacts in SCG signals up to a SNR of -19 dB without requiring any external assistance from electrocardiography (ECG). Such a standalone solution is directly applicable to the usage of SCG in daily life, as a content-rich replacement for other wearables in clinical settings, and other continuous monitoring scenarios. In applications with higher noise levels, ECG may be incorporated to further enhance SCG and extend its usable range. This work addresses the challenges posed by motion artifacts, enabling SCG to offer reliable cardiovascular insights in more difficult scenarios, and thereby facilitating wearable monitoring in daily life and the clinic.