Electrocardiogram (ECG) is a low-cost, simple, fast, and non-invasive test. It can reflect the heart's electrical activity and provide valuable diagnostic clues about the health of the entire body. Therefore, ECG has been widely used in various biomedical applications such as arrhythmia detection, disease-specific detection, mortality prediction, and biometric recognition. In recent years, ECG-related studies have been carried out using a variety of publicly available datasets, with many differences in the datasets used, data preprocessing methods, targeted challenges, and modeling and analysis techniques. Here we systematically summarize and analyze the ECG-based automatic analysis methods and applications. Specifically, we first reviewed 22 commonly used ECG public datasets and provided an overview of data preprocessing processes. Then we described some of the most widely used applications of ECG signals and analyzed the advanced methods involved in these applications. Finally, we elucidated some of the challenges in ECG analysis and provided suggestions for further research.
Humans ; Arrhythmias, Cardiac/diagnosis* ; Electrocardiography/methods* ; Algorithms

OBJECTIVE: To use the low-cost anesthesia monitor for realizing anesthesia depth monitoring, effectively assist anesthesiologists in diagnosis and reduce the cost of anesthesia operation. METHODS: Propose a monitoring method of anesthesia depth based on artificial intelligence. The monitoring method is designed based on convolutional neural network (CNN) and long and short-term memory (LSTM) network. The input data of the model include electrocardiogram (ECG) and pulse wave photoplethysmography (PPG) recorded in the anesthesia monitor, as well as heart rate variability (HRV) calculated from ECG, The output of the model is in three states of anesthesia induction, anesthesia maintenance and anesthesia awakening. RESULTS: The accuracy of anesthesia depth monitoring model under transfer learning is 94.1%, which is better than all comparison methods. CONCLUSIONS The accuracy of this study meets the needs of perioperative anesthesia depth monitoring and the study reduces the operation cost.
Artificial Intelligence ; Neural Networks, Computer ; Heart Rate ; Electrocardiography ; Photoplethysmography/methods* ; Anesthesia

Wearable monitoring, which has the advantages of continuous monitoring for a long time with low physiological and psychological load, represents a future development direction of monitoring technology. Based on wearable physiological monitoring technology, combined with Internet of Things (IoT) and artificial intelligence technology, this paper has developed an intelligent monitoring system, including wearable hardware, ward Internet of Things platform, continuous physiological data analysis algorithm and software. We explored the clinical value of continuous physiological data using this system through a lot of clinical practices. And four value points were given, namely, real-time monitoring, disease assessment, prediction and early warning, and rehabilitation training. Depending on the real clinical environment, we explored the mode of applying wearable technology in general ward monitoring, cardiopulmonary rehabilitation, and integrated monitoring inside and outside the hospital. The research results show that this monitoring system can be effectively used for monitoring of patients in hospital, evaluation and training of patients' cardiopulmonary function, and management of patients outside hospital.
Humans ; Artificial Intelligence ; Internet of Things ; Wearable Electronic Devices ; Monitoring, Physiologic/methods* ; Electrocardiography ; Internet

Objective: To observe the association between clinical phenotypes of hypertrophic cardiomyopathy (HCM) patients and a rare calcium channel and regulatory gene variation (Ca²⁺ gene variation) and to compare clinical phenotypes of HCM patients with Ca²⁺ gene variation, a single sarcomere gene variation and without gene variation and to explore the influence of rare Ca²⁺ gene variation on the clinical phenotypes of HCM. Methods: Eight hundred forty-two non-related adult HCM patients diagnosed for the first time in Xijing Hospital from 2013 to 2019 were enrolled in this study. All patients underwent exon analyses of 96 hereditary cardiac disease-related genes. Patients with diabetes mellitus, coronary artery disease, post alcohol septal ablation or septal myectomy, and patients who carried sarcomere gene variation of uncertain significance or carried>1 sarcomere gene variation or carried>1 Ca²⁺ gene variation, with HCM pseudophenotype or carrier of ion channel gene variations other than Ca²⁺ based on the genetic test results were excluded. Patients were divided into gene negative group (no sarcomere or Ca²⁺ gene variants), sarcomere gene variation group (only 1 sarcomere gene variant) and Ca²⁺ gene variant group (only 1 Ca²⁺ gene variant). Baseline data, echocardiography and electrocardiogram data were collected for analysis. Results: A total of 346 patients were enrolled, including 170 patients without gene variation (gene negative group), 154 patients with a single sarcomere gene variation (sarcomere gene variation group) and 22 patients with a single rare Ca²⁺ gene variation (Ca²⁺ gene variation group). Compared with gene negative group, patients in Ca²⁺ gene variation group had higher blood pressure and higher percentage of family history of HCM and sudden cardiac death (P<0.05); echocardiographic results showed that patients in Ca²⁺ gene variation group had thicker ventricular septum ((23.5±5.8) mm vs. (22.3±5.7) mm, P<0.05); electrocardiographic results showed that patients in Ca²⁺ gene variation group had prolonged QT interval ((416.6±23.1) ms vs. (400.6±47.2) ms, P<0.05) and higher RV5+SV1 ((4.51±2.26) mv vs. (3.50±1.65) mv, P<0.05). Compared with sarcomere gene variation group, patients in Ca²⁺ gene variation group had later onset age and higher blood pressure (P<0.05); echocardiographic results showed that there was no significant difference in ventricular septal thickness between two groups; patients in Ca²⁺ gene variation group had lower percentage of left ventricular outflow tract pressure gradient>30 mmHg (1 mmHg=0.133 kPa, 22.8% vs. 48.1%, P<0.05) and the lower early diastolic peak velocity of the mitral valve inflow/early diastolic peak velocity of the mitral valve annulus (E/e') ratio ((13.0±2.5) vs. (15.9±4.2), P<0.05); patients in Ca²⁺ gene variation group had prolonged QT interval ((416.6±23.1) ms vs. (399.0±43.0) ms, P<0.05) and lower percentage of ST segment depression (9.1% vs. 40.3%, P<0.05). Conclusion: Compared with gene negative group, the clinical phenotype of HCM is more severe in patients with rare Ca²⁺ gene variation; compared with patients with sarcomere gene variation, the clinical phenotype of HCM is milder in patients with rare Ca²⁺ gene variation.
Humans ; Cardiac Surgical Procedures/methods* ; Cardiomyopathy, Hypertrophic/genetics* ; Echocardiography ; Electrocardiography ; Phenotype ; Sarcomeres/genetics* ; Adult

Anti-motion artifact is one of the most important properties of ambulatory ECG monitoring equipment. At present, there is a lack of standardized means to test the performance of anti-motion artifact. ECG simulator and special conductive leather are used to build the simulator, it is used to simulate human skin, to generate ECG signal input for the ECG monitoring equipment attached to it. The mechanical arm and fixed support are used to build a motion simulation system to fix the conductive leather. The mechanical arm is programmed to simulate various motion states of the human body, so that the ECG monitoring equipment can produce corresponding motion artifacts. The collected ECG signals are read wirelessly, observed, analyzed and compared, and the anti-motion artifact performance of ECG monitoring equipment is evaluated. The test results show that by artificially creating the small difference between the two groups of ambulatory ECG monitoring equipment, the system can accurately test the interference signals introduced under the conditions of controlled movement such as tension and torsion, and compare the advantages and disadvantages. The research shows that the test system can provide convenient and accurate verification means for the research of optimizing anti-motion interference.
Humans ; Artifacts ; Signal Processing, Computer-Assisted ; Electrocardiography, Ambulatory/methods* ; Electrocardiography ; Motion

Objective: We aimed to determine the epidemiological characteristics of asymptomatic AF in elder community population (≥65 years old) to analyze the detection rate of different screening methods. Methods: The study was a prospective cohort study. The elder (≥65 years old) residents who voluntarily participated in free physical examination in Dalian community were selected. The participants were randomly divided into screening group (including intensive screening group and single screening group) and control group. The control group received interrogation, medical history collection and routine 12-lead electrocardiogram (ECG) examination. Screening group received an additional single-lead ambulatory ECG equipment worn for 5-7 days. Intensive screening group received two equal-length wearings in 2020 and 2021 respectively, while one screening group only wore once in 2020. Results: Finally 3 340 residents ((70.7±5.0) years old) which consisted of 1 488 males (44.55%) were enrolled. There were 1 945 residents in screening group, including 859 in intensive screening group and 1 086 in one-time screening group. The control group included 1 395 people. Detection rate of asymptomatic AF was significantly higher in screening group than control group (79(4.06%) vs. 24(1.72%), P<0.001). Higher detection rate was found in screening group than control group in AF risk factors (1 or 2-3) subgroups and CHA₂DS₂-VASc score (2-3 or≥4) subgroups (P<0.05). Additionally, no difference was found between intensive screening group and single screening group (42(4.89%) vs. 37(3.41%), P=0.100). Intensive screening increased detection rate (7(6.93%) vs. 1(0.58%), P=0.009) only in residents those with low thrombosis risk (CHA₂DS₂-VaSc<2). Conclusions: Screening in elderly (≥65 years old) can significantly improve the detection rate of asymptomatic AF by wearing single lead dynamic ECG device. The rate increased significantly with the increase of risk factors associated with AF by single screening. In addition, repeat screening of the same method may only improve detection rates in the group with low risk thrombotic scores and non-combination of AF risk factors.Screening methods that are appropriate for different populations may require further exploration.
Male ; Humans ; Aged ; Atrial Fibrillation/epidemiology* ; Prospective Studies ; Electrocardiography ; Risk Factors ; Stroke ; Risk Assessment ; Mass Screening/methods*

Objective: We aimed to determine the epidemiological characteristics of asymptomatic AF in elder community population (≥65 years old) to analyze the detection rate of different screening methods. Methods: The study was a prospective cohort study. The elder (≥65 years old) residents who voluntarily participated in free physical examination in Dalian community were selected. The participants were randomly divided into screening group (including intensive screening group and single screening group) and control group. The control group received interrogation, medical history collection and routine 12-lead electrocardiogram (ECG) examination. Screening group received an additional single-lead ambulatory ECG equipment worn for 5-7 days. Intensive screening group received two equal-length wearings in 2020 and 2021 respectively, while one screening group only wore once in 2020. Results: Finally 3 340 residents ((70.7±5.0) years old) which consisted of 1 488 males (44.55%) were enrolled. There were 1 945 residents in screening group, including 859 in intensive screening group and 1 086 in one-time screening group. The control group included 1 395 people. Detection rate of asymptomatic AF was significantly higher in screening group than control group (79(4.06%) vs. 24(1.72%), P<0.001). Higher detection rate was found in screening group than control group in AF risk factors (1 or 2-3) subgroups and CHA₂DS₂-VASc score (2-3 or≥4) subgroups (P<0.05). Additionally, no difference was found between intensive screening group and single screening group (42(4.89%) vs. 37(3.41%), P=0.100). Intensive screening increased detection rate (7(6.93%) vs. 1(0.58%), P=0.009) only in residents those with low thrombosis risk (CHA₂DS₂-VaSc<2). Conclusions: Screening in elderly (≥65 years old) can significantly improve the detection rate of asymptomatic AF by wearing single lead dynamic ECG device. The rate increased significantly with the increase of risk factors associated with AF by single screening. In addition, repeat screening of the same method may only improve detection rates in the group with low risk thrombotic scores and non-combination of AF risk factors.Screening methods that are appropriate for different populations may require further exploration.
Male ; Humans ; Aged ; Atrial Fibrillation/epidemiology* ; Prospective Studies ; Electrocardiography ; Risk Factors ; Stroke ; Risk Assessment ; Mass Screening/methods*

Objective: To explore the feasibility, safety and effectiveness of left bundle branch area pacing (LBBAP) in children aged ≤3 years. Methods: A total of 10 children aged ≤3 years who were diagnosed with brady arrhythmia in the First Hospital of Tsinghua University from September 2020 to September 2021 were retrospectively analyzed. All the children met the indication of permanent pacemaker implantation and underwent LBBAP successfully. The intraoperative data (pacing parameters, electrocardiogram and radiographic imaging), cardiac ultrasound data and clinical data during regular postoperative follow-up were recorded. The preoperative and postoperative data were compared using matched samples t test. Results: Ten children (aged (1.6±0.7) years with weight of (10.3±2.5) kg) underwent LBBAP successfully. The QRS wave duration on the postoperative electrocardiogram was (100±9) ms, and the percentage of ventricular pacing was (97±7)%. The postoperative follow-up period was 6 (6, 12) months. At 1 week after operation, the left ventricular end-diastolic diameter Z scores in these children reduced significantly compared with those before operation (1.3±0.6 vs. 3.6±1.1, t=9.37, P<0.001). During the follow-up period, cardiac function was normal and the last left ventricular ejection fraction was (66±4)% in all children. At the last follow-up, the pacing threshold of the 10 children was smaller than 1.0 V and was acceptable. Compared with the intraoperative baseline values, the pacing threshold was slightly higher ((0.8±0.1) vs. (0.5±0.1) V, t=-5.27, P=0.001). However, no significant difference was found regarding sensing threshold ((16±5) vs. (14±4) mV, t=-0.83, P=0.426) and impedance ((584±88) vs. (652±86) Ω, t=2.26, P=0.050). During follow-up, no electrode related complications were recorded. Conclusions: LBBAP is safe and effective for infants and toddlers. Narrow QRS pacing with stable pacing parameters and normal cardiac function could be achieved postoperatively.
Bundle of His ; Bundle-Branch Block ; Cardiac Pacing, Artificial/methods* ; Child, Preschool ; Electrocardiography/methods* ; Humans ; Retrospective Studies ; Stroke Volume ; Treatment Outcome ; Ventricular Function, Left

Objective: To investigate the efficacy and safety of left bundle branch pacing(LBBP) in patients after transcatheter aortic valve implantation (TAVI). Methods: This is a retrospective study. A total of 35 patients underwent TAVI and received pacemaker implantation from January 2018 to December 2020 in Beijing Fuwai Hospital were enrolled. Patients were divided into LBBP group (n=12) and right ventricular apex pacing (RVAP) group (n=23) according to the pacing position. The success rate of operation in LBBP group was calculated, and the occurrence of complications were observed, and the parameters of pacemaker were measured on the 3rd day and 1, 3 and 6 months after operation. The N-terminal pro-B-type natriuretic peptide (NT-proBNP), echocardiographic and ECG indexes were compared between the two groups on the 3rd day and 1, 3, and 6 months after pacemaker implantation. Result: A total of 35 patients were included, The age was (76.4±7.7) years, including 19 males (54.3%). The procedure time ((86.58±17.10)min vs. (68.74±9.18)min, P<0.001) and fluoroscopy duration ((20.08±4.44)min vs. (17.00±2.26)min, P<0.001) were significantly longer in LBBP group compared with RVAP group. The operation success rate of LBBP group was 11/12. There was no serious operation related complications such as pneumothorax, hemothorax, electrode dislocation, infection, and lower limb bleeding. The patients were followed up for 7.43 (5.21, 9.84) months. The programmed parameters of pacemaker were in the ideal range and stable during follow-up. At 3 and 6 months after operation, the left ventricular ejection fraction in LBBP group was higher than that in RVAP Group (at 3 months: (60.75±2.89)% vs. (57.35±3.33)%, P=0.004; at 6 months: (63.17±3.33)% vs. (56.17±3.97)%, P<0.001), NT-proBNP values was lower in LBBP group than that in RVAP Group (at 3 months: 822 (607, 1 150)ng/L vs. 1 052 (902, 1 536)ng/L, P=0.006; at 6 months: 440 (330,679)ng/L vs. 783 (588, 1 023)ng/L, P=0.001). At 1, 3 and 6 months after operation, the QRS duration was shorter in LBBP group than that in RVAP group (1 month: 99 (97, 107)ms vs. 126(124, 130)ms, P<0.001; 3 months: 98(96, 105)ms vs. 129(128, 133)ms, P<0.001; 6 months: 96(94, 104)ms vs. 130(128, 132)ms, P<0.001). Conclusions: For patients with permanent pacemaker indications after TAVI, LBBP is feasible, safe and reliable. It could improve the cardiac function in the short term, the long-term effect of LBBP needs to be further observed.
Aged ; Aged, 80 and over ; Bundle of His ; Cardiac Pacing, Artificial/methods* ; Electrocardiography/methods* ; Fluoroscopy ; Humans ; Male ; Retrospective Studies ; Stroke Volume ; Transcatheter Aortic Valve Replacement/adverse effects* ; Treatment Outcome ; Ventricular Function, Left

The judgment of the type of arrhythmia is the key to the prevention and diagnosis of early cardiovascular disease. Therefore, electrocardiogram (ECG) analysis has been widely used as an important basis for doctors to diagnose. However, due to the large differences in ECG signal morphology among different patients and the unbalanced distribution of categories, the existing automatic detection algorithms for arrhythmias have certain difficulties in the identification process. This paper designs a variable scale fusion network model for automatic recognition of heart rhythm types. In this study, a variable-scale fusion network model was proposed for automatic identification of heart rhythm types. The improved ECG generation network (EGAN) module was used to solve the imbalance of ECG data, and the ECG signal was reproduced in two dimensions in the form of gray recurrence plot (GRP) and spectrogram. Combined with the branching structure of the model, the automatic classification of variable-length heart beats was realized. The results of the study were verified by the Massachusetts institute of technology and Beth Israel hospital (MIT-BIH) arrhythmia database, which distinguished eight heart rhythm types. The average accuracy rate reached 99.36%, and the sensitivity and specificity were 96.11% and 99.84%, respectively. In conclusion, it is expected that this method can be used for clinical auxiliary diagnosis and smart wearable devices in the future.
Algorithms ; Arrhythmias, Cardiac/diagnosis* ; Databases, Factual ; Electrocardiography/methods* ; Heart Rate ; Humans