Electrocardiogram Data Research Articles

Enhancing Security of Telemedicine Data: A Multi-Scroll Chaotic System for ECG Signal Encryption and RF Transmission.

Protecting sensitive patient data, such as electrocardiogram (ECG) signals, during RF wireless transmission is essential due to the increasing demand for secure telemedicine communications. This paper presents an innovative chaotic-based encryption system designed to enhance the security and integrity of telemedicine data transmission. The proposed system utilizes a multi-scroll chaotic system for ECG signal encryption based on master-slave synchronization. The ECG signal is encrypted by a master system and securely transmitted to a remote location, where it is decrypted by a slave system using an extended state observer. Synchronization between the master and slave is achieved through the Lyapunov criteria, which ensures system stability. The system also supports Orthogonal Frequency Division Multiplexing (OFDM) and adaptive n-quadrature amplitude modulation (n-QAM) schemes to optimize signal discretization. Experimental validations with a custom transceiver scheme confirmed the system's effectiveness in preventing channel overlap during 2.5 GHz transmissions. Additionally, a commercial RF Power Amplifier (RF-PA) for LTE applications and a development board were integrated to monitor transmission quality. The proposed encryption system ensures robust and efficient RF transmission of ECG data, addressing critical challenges in the wireless communication of sensitive medical information. This approach demonstrates the potential for broader applications in modern telemedicine environments, providing a reliable and efficient solution for the secure transmission of healthcare data.

Machine Learning Approaches for Automated Diagnosis of Cardiovascular Diseases: A Review of Electrocardiogram Data Applications.

Cardiovascular diseases (CVDs) have been identified as the leading cause of mortality worldwide. Electrocardiogram (ECG) is a fundamental diagnostic tool used for the diagnosis and detection of these diseases. The new technological tools can help enhance the effectiveness of ECGs. Machine learning (ML) is widely acknowledged as a highly effective approach in the realm of computer-aided diagnostics. This article presents a review of the effectiveness of ML algorithms and deep-learning algorithms in diagnosing, identifying, and classifying CVDs using ECG data. The review identified relevant studies published in the 5 major databases: PubMed, Web of Science (WoS), Scopus, Springer, and IEEE Xplore; between 2021 and 2023, a total of 30 were chosen for the comprehensive quantitative and qualitative. The study demonstrated that different datasets are available online with data related to CVDs. The various ML techniques are employed for the purpose of classification. Based on our investigation, it has been observed that deep learning-based neural network algorithms, such as convolutional neural networks and deep neural networks, have demonstrated superior performance in the detection of entire record data. Furthermore, deep learning showcases its efficacy even when confronted with a scarcity of data. ML approaches utilizing ECG data exhibit a notable proficiency in the realm of diagnosis, hence holding the potential to mitigate the occurrence of disease-related consequences at advanced stages.

Ecg signal watermarking using QR decomposition.

This study introduces a novel watermarking technique for electrocardiogram (ECG) signals. Watermarking embeds critical information within the ECG signal, enabling data origin authentication, ownership verification, and ensuring the integrity of research data in domains like telemedicine, medical databases, insurance, and legal proceedings. Drawing inspiration from image watermarking, the proposed method transforms the ECG signal into a two-dimensional format for QR decomposition. The watermark is then embedded within the first row of the resulting R matrix. Three implementation scenarios are proposed: one in the spatial domain and two in the transform domain utilizing discrete wavelet transform (DWT) for improved watermark imperceptibility. Evaluation on real ECG signals from MIT-BIH Arrhythmia database and comparison to existing methods demonstrate that the proposed method achieves: (1) higher Peak Signal-to-Noise Ratio (PSNR) indicating minimal alterations to the watermarked signal, (2) lower bit error rates (BER) in robustness tests against external modifications such as AWGN noise (additive white Gaussian noise), line noise and down-sampling, and (3) lower computational complexity. These findings emphasize the effectiveness of the proposed QR decomposition-based watermarking method, achieving a balance between robustness and imperceptibility. The proposed approach has the potential to improve the security and authenticity of ECG data in healthcare and legal contexts, while its lower computational complexity enhances its practical applicability.

Cardiac automaticity is modulated by IKACh in sinoatrial node during pregnancy.

Pregnant women have a significantly elevated resting heart rate (HR), which makes cardiac arrhythmias more likely to occur. Although electrical remodeling of the sinoatrial node (SAN) has been documented, the underlying mechanism is not fully understood. The acetylcholine-activated potassium current (IKACh), one of the major repolarizing currents in the SAN, plays a critical role in HR control by hyperpolarizing the maximal diastolic potential (MDP) of the SAN action potential (AP), thereby reducing SAN automaticity and HR. Thus, considering its essential role in cardiac automaticity, this study aims to determine whether changes in IKACh are potentially involved in the increased HR associated with pregnancy. Experiments were conducted on non-pregnant (NP, 2-3 months old) and pregnant (P, 17-18 gestation days) female CD-1 mice. IKACh was recorded on spontaneously beating SAN cells using the muscarinic agonist carbachol (CCh). Voltage-clamp data showed a reduction in IKACh density during pregnancy, which returned to control values shortly after delivery. The reduction in IKACh was explained by a decrease in protein expression of Kir3.1 channel subunit and the muscarinic type 2 receptor. In agreement with these findings, current-clamp data shows that the MDP of SAN cells from P mice were less hyperpolarized following CCh administration. Surface electrocardiograms (ECGs) recorded on anesthetized mice revealed that the cholinergic antagonist atropine and the selective KACh channel blocker tertiapin-Q increased HR in NP mice and had only a minimal effect on P mice. AP and ECG data also showed that pregnancy is associated with a decrease in beating and heart rate variability, respectively. IKACh function and expression are decreased in the mouse SAN during pregnancy, strongly suggesting that, in addition to other electrical remodeling of the SAN, reduced IKACh also plays an important role in the pregnancy-induced increased HR.

Non-invasive acquisition of vital data in anesthetized rats using laser and radar application.

The aim of this study was to verify the possibility of obtaining vital sign information using a laser and radar sensor in a manner that is non-invasive and painless for test animals. A dataset was obtained from respiratory movement of anaesthetized male F344 rats, signals of laser and radar sensors were recorded simultaneously with vital data acquired with an integrated multiple-channel intraoperative monitor. In addition, respiratory movements were also video recorded, and used as reference data of respiration rate (RR; ref-RR). Reference data for heart rate (HR; ref-HR) were obtained from the R wave of electrocardiogram data for each epoch. Signals recorded from the radar sensor (I- and Q-signals) were input to a computer, and HR (radar-HR) and RR (radar-RR) were estimated using the frequency analysis method. Among the six positions where respiratory movements were measured by the laser sensor, the number of peak counts matched the visual counts of respiratory movements in the video records. The respiratory movements were significantly the greatest over the most caudal rib in the dorsal (p < 0.001). The average radar-RR and ref-RR values showed correspondence (ref-RR, 69 ± 6.2 breaths/min; radar-RR, 68 ± 5.7 breaths/min (p = 0.04-1.00); equivalence ratio, 86%). The radar-HR data showed slight variability; however, there was 80% homology compared with the ref-HR values (ref-HR, 336 ± 19.6 beats/min; radar-HR, 348 ± 34.1 (p = 0.10-0.95)). Although comparison of the data under noradrenaline administration failed to track drug-induced changes in some cases, the HR and RR data of anesthetized rats measured from the radar sensor system showed comparable accuracy to other conventional methods.

Effects of Heart Rate Variability (HRV) Biofeedback in Pulmonary Indicators and HRV Indices Among Patients with Chronic Obstructive Pulmonary Disease.

Patients with chronic obstructive pulmonary disease (COPD) exhibit reduced cardiac autonomic activity, linked to poor prognosis and exercise intolerance. While heart rate variability biofeedback (HRVB) can enhance cardiac autonomic activity in various diseases, its use in patients with COPD is limited. This study explored the impact of the HRVB on cardiac autonomic activity and pulmonary indicators in patients with COPD. Fifty-three patients with COPD were assigned to either the HRVB (n = 26) or the control group (n = 27), with both groups receiving standard medical care. The HRVB group also underwent one-hour HRVB sessions weekly for six weeks. All participants had pre- and post-test measurements, including the Six-Minute Walking Test (6MWT), lead II electrocardiogram (ECG) recording, Modified Medical Research Council Dyspnea Scale (mMRC), body mass index, airflow obstruction, dyspnea, and exercise capacity (BODE) index. ECG data were analyzed for heart rate variability (HRV) as an index of cardiac autonomic activity. A two-way mixed analysis of variances demonstrated significant interaction effects of Group × Time in pulmonary indicators and HRV indices. The HRVB group exhibited significant post-test improvements, with decreased mMRC and BODE scores and increased 6MWT distance and HRV indices, compared to pre-test results. The 6MWT distance significantly increased and mMRC significantly decreased at post-test in the HRVB group compared with the control group. This study confirmed the efficacy of HRVB as an adjunct therapy in patients with COPD, showing improvements in exercise capacity, breathing difficulties, and cardiac autonomic activity.

An Evaluation of the Autonomic Nervous Activity and Psychomotor Vigilance Level for Smells in the Work Booth

In this study, we investigated the effects of the smell environment in the work booth on autonomic nervous activity (ANS) and psychomotor vigilance levels (PVLs) using linalool (LNL) and trans-2-nonenal (T2N). The subjects were six healthy males (31 ± 6 years old) and six healthy females (24 ± 5 years old). They sat in the work booth filled with the smells of LNL and T2N for 10 min, and their electrocardiograms (ECGs), skin conductance levels, pulse wave variabilities, skin temperatures, and seat pressure distributions were measured. In addition, the orthostatic load test (OLT) and psychomotor vigilance test (PVT) were performed before and after entering the work booth, and a subjective evaluation of the smell was also performed after the experiment. This paper focused on ECG and PVT data and analyzed changes in heart rate variability indices and PVT scores. Males felt slightly comfortable with the LNL smell and showed promoted sympathetic nerve activity in the OLT after the smell presentation. Females felt slightly uncomfortable with the T2N smell and showed promoted sympathetic nerve activity and a decrease in PVT scores in the OLT after the smell presentation. Gender differences were observed in ANS and PVLs, and it is possible that the comfort of LNL increased sympathetic nervous activity in males, while the uncomfortableness of T2N may have reduced work performance in females.

3DECG-Net: ECG fusion network for multi-label cardiac arrhythmia detection

Cardiovascular diseases represent the leading global cause of death, typically diagnosed and addressed through electrocardiograms (ECG), which record the heart's electrical activity. In recent years, there has been a notable surge in ECG recordings, driven by the widespread use of wearable devices. However, the limited availability of medical experts to analyze these recordings underscores the necessity for automated ECG analysis using computer-aided methods. In this study, we introduced 3DECG-Net, a deep learning model designed to detect and classify seven distinct heart states through the analysis of data fusion from 12-lead ECG in a multi-label framework. Our model leverages a residual architecture with a multi-head attention mechanism, undergoing training within a five-fold cross-validation scheme. By transforming 12-lead ECG signals into 3D data with the help of Recurrent Plot technique, 3DECG-Net achieves a noteworthy micro F1-score of 80.3 %, surpassing the performance of other state-of-the-art deep learning models developed for this specific task. Also, we present an ECG preprocessing framework to generate compact, high-quality ECG signals for potential application in future studies within this domain. We conduct an explainable AI experiment using Local Interpretable Model-agnostic Explanations (LIME) to elucidate the significance of each lead in accurately diagnosing specific arrhythmias, ensuring the logical processing of ECG data by 3DECG-Net. The findings of this study suggest that the proposed model is trustworthy and has the potential to be used as an effective diagnostic toolset for identifying heart arrhythmias. Its effectiveness can improve the diagnostic process, facilitate early treatment, and enhance overall efficiency in medical settings.

Ten quick tips for electrocardiogram (ECG) signal processing.

The electrocardiogram (ECG) is a powerful tool to measure the electrical activity of the heart, and the analysis of its data can be useful to assess the patient's health. In particular, the computational analysis of electrocardiogram data, also called ECG signal processing, can reveal specific patterns or heart cycle trends which otherwise would be unnoticeable by medical experts. When performing ECG signal processing, however, it is easy to make mistakes and generate inflated, overoptimistic, or misleading results, which can lead to wrong diagnoses or prognoses and, in turn, could even contribute to bad medical decisions, damaging the health of the patient. Therefore, to avoid common mistakes and bad practices, we present here ten easy guidelines to follow when analyzing electrocardiogram data computationally. Our ten recommendations, written in a simple way, can be useful to anyone performing a computational study based on ECG data and eventually lead to better, more robust medical results.

Study On AI-Assisted Health Detection Mechanism Based On ECG Data For Public Health

Health care is being revolutionized by Artificial Intelligence (AI) technologies that provide more precise diagnosis, customized therapies, streamlined administrative procedures and better patient care. A health detection mechanism assesses electrocardiogram (ECG) data to detect cardiac anomalies, offering precise and immediate atrial fibrillation diagnosis. We propose artificial intelligence (AI) assisted public health monitoring using ECG data. This study introduces the dynamic Ant Colony Optimized Intelligent Gaussian Naïve Bayes (DACO-IGNB) method to identify the atrial fibrillation detection mechanism. The Atrial Fibrillation (AF) ECG data were collected and Baseline Wander was to facilitate pre-processing. The Principal Component Analysis (PCA) method was used to extract the feature. Compared to other traditional methods, it demonstrated superior performance across accuracy (90.9%), F1-Score (0.87), recall (0.89) and precision (0.88) metrics. These findings underscore its efficiency in DACO-IGNB assisting health detection and diagnostics, significantly improving the accuracy and reliability of public health monitoring systems.

Temporal attention network for CNNE model of variable-length ECG signals in early arrhythmia detection

&lt;p&gt;Cardiac arrhythmia identification and categorization are crucial for prompt treatment and better patient outcomes. Arrhythmia identification is the main focus of this study's temporal attention network (TAN)-based multiclass categorization of varied-length electrocardiogram (ECG) data. The suggested TAN is designed to handle variable-duration ECG signals, making it ideal for real-time monitoring. The TAN uses a dynamic snippet extraction approach to choose meaningful ECG segments to ensure the model captures essential properties despite the constraints of processing such heterogeneous data. Training and assessment use a large dataset of atrial fibrillation, ventricular, and supraventricular arrhythmias. The TAN outperforms current approaches in multiclass early arrhythmia classification and is very accurate. Concatenating EfficientNet with CNN layer helped overcome different data and variable-length signals. High accuracy: 98% of normal, 97.1% of atrial fibrillation (AF), 98% of other, and 98% of noisy using the proposed CEEC model. Early arrhythmia diagnosis has improved due to the TAN's ability to effectively identify varied-length ECG data and give interpretability. It enables quicker interventions, personalised treatment plans, and improved arrhythmia control, which can greatly benefit patient care.&lt;/p&gt;

Frequency-Enhanced Geometric-Constrained Reconstruction for Localizing Myocardial Infarction in 12-Lead Electrocardiograms.

Determining the location of myocardial infarction is crucial for clinical management and therapeutic stratagem. However, existing diagnostic tools either sacrifice ease of use or are limited by their spatial resolution. Addressing this, we aim to refine myocardial infarction localization via surface potential reconstruction of the ventricles in 12-lead electrocardiograms (ECG). A notable obstacle is the ill-posed nature of such reconstructions. To overcome this, we introduce the frequency-enhanced geometric-constrained iterative network (FGIN). FGIN begins by mining the latent features from ECG data across both time and frequency domains. Subsequently, it increases the data dimensionality of ECG and captures intricate features using convolutional layers. Finally, FGIN incorporates ventricular geometry as a constraint on surface potential distribution. It allocates variable weights to distinct edges. Experimental validation of FGIN confirms its efficacy over synthetic and clinical datasets. On the synthetic dataset, FGIN outperforms seven existing reconstruction methods, attaining the highest Pearson Correlation Coefficient of 0.8624, the lowest Root Mean Square Error of 0.1548, and the highest Structural Similarity Index Measure of 0.7988. On the clinical public dataset (2007 PhysioNet/Computers in Cardiology Challenge), FGIN achieves better localization results than other approaches, according to the clinical standard 17-segment model, achieving an average Segment Overlap of 87.2%. Clinical trials on 50 patients demonstrate FGIN's effectiveness, showing an average accuracy of 91.6% and an average Segment Overlap of 88.2%.

Association between instantaneous heart rate sequence during the awake period and cardiovascular events: a study based on Sleep Heart Health Study.

Heart rate variability (HRV) has been reported to be associated with cardiovascular diseases (CVD), while few studies focused on the instantaneous heart rate (IHR). This study aimed to establish models to predict the occurrence of cardiovascular events based on the IHR sequence. A total of 2977 participants with useful electrocardiogram (ECG) data and free of CVD events at baseline from the Sleep Heart Health Study (SHHS) database were included in this retrospective cohort study. All IHR indicators were measured during the awake period before sleep. The logistic regression, random forest, and XGBoost methods were used to develop the predictive models. The model performance was quantified by calculating the area under the curve (AUC). Of theses 2977 participants, 1460 (49.04%) participants had CVD events during the 15-year follow-up. Higher standard deviation of IHR (SDHR) (OR=0.906; 95% CI, 0.832-0.986), coefficient of variation of IHR (CVHR) (OR=0.910; 95% CI, 0.835-0.990), power in low frequency (LF) (OR=0.896; 95% CI, 0.822-0.975), power in high frequency (HF) (OR=0.872; 95% CI, 0.796-0.955), and total power (TP) (OR=0.887; 95% CI, 0.813-0.967) were associated with the lower risk of CVD events, while ratio of semi-minor axis and semi-major axis in Poincare plot (SDratio) (OR=1.105; 95% CI, 1.012-1.206) was related to the higher risk of CVD events. The AUCs of the logistic regression, random forest, and the XGBoost models were 0.734 (95% CI, 0.701-0.767), 0.794 (95% CI, 0.764-0.823) and 0.828 (95% CI, 0.801-0.855) in the testing set, respectively. IHR sequences were important predictors of cardiovascular events. The IHR indicators should be paid more attention to in future clinical researches on CVD.

Intra- and Inter-Rater Reliability of Linear and Nonlinear Measures of Short-Term Heart Rate Variability Following Combat-Related Traumatic Injury.

Heart rate variability (HRV) is a marker of autonomic function. However, the reliability of short-term HRV measurement in individuals with combat-related traumatic injury (CRTI) remains undetermined. An intra- and inter-rater reliability study was conducted using a subsample (n = 35) of British servicemen with CRTI enrolled in the ongoing ADVANCE study. A five-minute epoch of single-lead electrocardiogram data collected during spontaneous breathing was used to measure HRV. HRV analyses were independently performed by two examiners using Kubios. Intraclass correlation coefficient (ICC), standard error of measurement (SEM), minimum detectable change (MDC), and coefficient of variance were calculated for linear [root mean square of successive difference (RMSSD), standard deviation of NN interval, low-frequency, high-frequency, total power] and nonlinear (SD1-2, acceleration and deceleration capacities, sample entropy) measures. Bland-Altman %plots were used to assess bias in intra- and inter-rater HRV data. The mean age of participants was 39.3 ± 6.3 years. An excellent ICC score of 0.9998 (95% CI 0.9997, 0.9999) was observed for intra-rater analyses of RMSSD, and similar excellent ICC scores were seen for all other HRV measures. The inter-rater reliability analyses produced an excellent ICC score (range 0.97-1.00). Comparatively, frequency-domain measures produced higher MDC% and SEM% scores than time-domain and nonlinear measures in both inter- and intra-rater analyses. The Bland-Altman plots revealed relatively higher bias for frequency-domain and nonlinear measures than time-domain measures. ECG-related short-term HRV measures were reliable in injured servicemen under spontaneous breathing. However, the reliability appeared better with the time-domain measure than frequency-domain and nonlinear measures in this sample.

Natriuretic Peptide Concentrations and Echocardiography Findings in Patients with Micro-atrial Fibrillation.

Atrial fibrillation (AF) is a rhythm disorder characterized by very rapid and disorganized atrial-derived electrical activations with uncoordinated atrial contractions. Very short periods of AF-like activity (micro-AF) may be precursors of undetected, silent episodes of atrial fibrillation. Here, we examined the relationship between natriuretic peptide concentrations and echocardiography findings in patients with micro-AF. The electrocardiograms (ECGs) of patients complaining of palpitations were recorded with a 24‑hour Holter monitor, and the patients were consecutively included in the study. Micro-AF was defined as sudden, irregular atrial tachycardia lasting less than 30 sec with episodes of ≥5 consecutive supraventricular depolarizations with the absolute absence of p-waves. After a G-power test, patients were consecutively included in the study: 45 patients in the micro-AF group and 45 patients in the control group. Laboratory parameters, ECG and echocardiographic findings of the two groups were compared. N-terminal pro B-type natriuretic peptide (Pro-BNP) and serum troponin T concentrations were higher in the micro-AF group, (375.5±63.6 pg / ml vs. 63.1±56.8 pg / ml, p&lt;0.001; 13±11.4 ng / dl vs. 4.4±2.4 ng / dl, p&lt;0.001 respectively.) Each 1 pg / ml increase in serum Pro-BNP increased the risk of micro-AF by 1.8 %. In the ROC analysis, the cut-off value of Pro-BNP for the diagnosis of micro-AF was 63.4 pg / ml, with a sensitivity of 91.1 % and a specificity of 73.3 %. Atrial electro-mechanical delay durations were significantly higher in the micro-AF group. To predict micro-AF, the inter-annulus plane electromechanical delay time (inter-annulus plane AEMD) had a cut-off value of 18.5 sec, with a sensitivity of 93.3 % and a specificity of 91.1 %. Left intra-annulus plane electro-mechanical delay time (intra-annulus AEMD LEFT) had a cut-off value of 11.5 sec with a 95.6 % sensitivity and 75.6 % specificity. In the ECG evaluation, maximum P wave duration (Pmax) (113±10.2 ms vs. 98±10.4 ms; p&lt;0.001), minimum P wave duration (Pmin) (73.8±5.5 ms vs.70±6.3 ms; p&lt;0.001) and P wave dispersion (PWD) (39.1±7.9 ms vs.28±7.6 ms; p&lt;0.001) were longer in the micro-AF group. Micro-AF in patients may be predicted by evaluating ECG, echocardiographic, and serum natriuretic peptide data.

Pilot study to assess the early cardiac safety of carbon ion radiotherapy for intra- and para-cardiac tumours.

Modern photon radiotherapy effectively spares cardiac structures more than previous volumetric approaches. Still, it is related to non-negligible cardiac toxicity due to the low-dose bath of surrounding normal tissues. However, the dosimetric advantages of particle radiotherapy make it apromising treatment for para- and intra-cardiac tumours. In the current short report, we evaluate the cardiac safety profile of carbon ion radiotherapy (CIRT) for radioresistant intra- and para-cardiac malignancies in areal-world setting. We retrospectively analysed serum biomarkers (TnI, CRP and NT-proBNP), echocardiographic, and both 12-lead and 24-hour Holter electrocardiogram (ECG) data of consecutive patients with radioresistant intra- and para-cardiac tumours irradiated with CIRT between June 2019 and September 2022. In the CIRT planning optimization process, to minimize the delivered doses, we contoured and gave ahigh priority to the cardiac substructures. Weekly re-evaluative 4D computed tomography scans were carried out throughout the treatment. Atotal of 16patients with intra- and para-cardiac localizations of radioresistant tumours were treated up to atotal dose of 70.4 Gy relative biological effectiveness (RBE) and amean heart dose of 2.41 Gy(RBE). We did not record any significant variation of the analysed serum biomarkers after CIRT nor significant changes of echocardiographic features, biventricular strain, or 12-lead and 24-hour Holter ECG parameters during 6months of follow-up. Our pilot study suggests that carbon ion radiotherapy is apromising radiation technique capable of sparing off-target side effects at the cardiac level. Alarger cohort, long-term follow-up and further prospective studies are needed to confirm these findings.

Prevalence, Cardiac Phenotype, and Outcomes of Transthyretin Variants in the UK Biobank Population

The population prevalence of cardiac transthyretin amyloidosis (ATTR) caused by pathogenic variation in the TTR gene (vATTR) is unknown. To estimate the population prevalence of disease-causing TTR variants and evaluate associated phenotypes and outcomes. This population-based cohort study analyzed UK Biobank (UKB) participants with whole-exome sequencing, electrocardiogram, and cardiovascular magnetic resonance data. Participants were enrolled from 2006 to 2010, with a median follow-up of 12 (IQR, 11-13) years (cutoff date for the analysis, March 12, 2024). Sixty-two candidate TTR variants were extracted based on rarity (minor allele frequency ≤0.0001) and/or previously described associations with amyloidosis if more frequent. Carrier status for TTR variants. Associations of TTR carrier status with vATTR prevalence and cardiovascular imaging and electrocardiogram traits were explored using descriptive statistics. Associations between TTR carrier status and atrial fibrillation, conduction disease, heart failure, and all-cause mortality were evaluated using adjusted Cox proportional hazards models. Genotypic and diagnostic concordance was examined using International Statistical Classification of Diseases, Tenth Revision codes from the hospital record. The overall cohort included 469 789 UKB participants (mean [SD] age, 56.5 [8.1] years; 54.2% female and 45.8% male). A likely pathogenic/pathogenic (LP/P) TTR variant was detected in 473 (0.1%) participants, with Val142Ile being the most prevalent (367 [77.6%]); 91 individuals (0.02%) were carriers of a variant of unknown significance . The overall prevalence of LP/P variants was 0.02% (105 of 444 243) in participants with European ancestry and 4.3% (321 of 7533) in participants with African ancestry. The LP/P variants were associated with higher left ventricular mass indexed to body surface area (β = 4.66; 95% CI, 1.87-7.44), and Val142Ile was associated with a longer PR interval (β = 18.34; 95% CI, 5.41-31.27). The LP/P carrier status was associated with a higher risk of heart failure (hazard ratio [HR], 2.68; 95% CI, 1.75-4.12) and conduction disease (HR, 1.88; 95% CI, 1.25-2.83). Higher all-cause mortality risk was observed for non-Val142Ile LP/P variants (HR, 1.98; 95% CI, 1.06-3.67). Thirteen participants (2.8%) with LP/P variants had diagnostic codes compatible with cardiac or neurologic amyloidosis. Variants of unknown significance were not associated with outcomes. This study found that approximately 1 in 1000 UKB participants were LP/P TTR variant carriers, exceeding previously reported prevalence. The findings emphasize the need for clinical vigilance in identifying individuals at risk of developing vATTR and associated poor outcomes.

AI-Driven IoT Healthcare System for Real-Time ECG Analysis and Comprehensive Patient Monitoring

This study explores the integration of deep learning and Internet of Things (IoT) technologies to enhance healthcare delivery, with a primary focus on improving electrocardiogram (ECG) analysis and real-time patient monitoring systems. The research presents the development of two innovative deep learning models based on the MIT-BIH dataset, enabling highly accurate ECG analysis. One model is trained for precise R-R peak detection, while the other performs effective classification of ECG signals into five distinct disease categories. The study also introduces an integrated healthcare system that seamlessly captures patients' real-time physiological data, including ECG, SpO2, and temperature, using an ESP32 microcontroller and Raspberry Pi. An IoT infrastructure with Node-RED IBM Platform and Message Queuing Telemetry Transport (MQTT) securely transmits the ECG data to the advanced analysis algorithms. The user interface displays patients' vital signs, including heart rate, oxygen saturation, and temperature, providing healthcare professionals with comprehensive real-time insights. By integrating the deep learning models, which achieve approximately 99% accuracy, alongside robust sensor technology and an IoT architecture, this system aims to transform healthcare by enabling highly precise ECG analysis and remote patient monitoring. The findings of this study underscore the potential of the synergistic convergence of deep learning, sensor technology, and IoT to advance healthcare delivery and improve patient outcomes.

Artificial Intelligence-Driven Prognosis of Respiratory Mechanics: Forecasting Tissue Hysteresivity Using Long Short-Term Memory and Continuous Sensor Data.

Tissue hysteresivity is an important marker for determining the onset and progression of respiratory diseases, calculated from forced oscillation lung function test data. This study aims to reduce the number and duration of required measurements by combining multivariate data from various sensing devices. We propose using the Forced Oscillation Technique (FOT) lung function test in both a low-frequency prototype and the commercial RESMON device, combined with continuous monitoring from the Equivital (EQV) LifeMonitor and processed by artificial intelligence (AI) algorithms. While AI and deep learning have been employed in various aspects of respiratory system analysis, such as predicting lung tissue displacement and respiratory failure, the prediction or forecasting of tissue hysteresivity remains largely unexplored in the literature. In this work, the Long Short-Term Memory (LSTM) model is used in two ways: (1) to estimate the hysteresivity coefficient η using heart rate (HR) data collected continuously by the EQV sensor, and (2) to forecast η values by first predicting the heart rate from electrocardiogram (ECG) data. Our methodology involves a rigorous two-hour measurement protocol, with synchronized data collection from the EQV, FOT, and RESMON devices. Our results demonstrate that LSTM networks can accurately estimate the tissue hysteresivity parameter η, achieving an R2 of 0.851 and a mean squared error (MSE) of 0.296 for estimation, and forecast η with an R2 of 0.883 and an MSE of 0.528, while significantly reducing the number of required measurements by a factor of three (i.e., from ten to three) for the patient. We conclude that our novel approach minimizes patient effort by reducing the measurement time and the overall ambulatory time and costs while highlighting the potential of artificial intelligence methods in respiratory monitoring.

Early classification and recognition algorithm for sudden cardiac arrest based on limited electrocardiogram data trained with a two-stages convolutional neural network

Sudden cardiac arrest (SCA) is a lethal cardiac arrhythmia that poses a serious threat to human life and health. However, clinical records of sudden cardiac death (SCD) electrocardiogram (ECG) data are extremely limited. This paper proposes an early prediction and classification algorithm for SCA based on deep transfer learning. With limited ECG data, it extracts heart rate variability features before the onset of SCA and utilizes a lightweight convolutional neural network model for pre-training and fine-tuning in two stages of deep transfer learning. This achieves early classification, recognition and prediction of high-risk ECG signals for SCA by neural network models. Based on 16 788 30-second heart rate feature segments from 20 SCA patients and 18 sinus rhythm patients in the international publicly available ECG database, the algorithm performance evaluation through ten-fold cross-validation shows that the average accuracy (Acc), sensitivity (Sen), and specificity (Spe) for predicting the onset of SCA in the 30 minutes prior to the event are 91.79%, 87.00%, and 96.63%, respectively. The average estimation accuracy for different patients reaches 96.58%. Compared to traditional machine learning algorithms reported in existing literatures, the method proposed in this paper helps address the requirement of large training datasets for deep learning models and enables early and accurate detection and identification of high-risk ECG signs before the onset of SCA.