Electrocardiogram (ECG) plays an important role in the diagnosis of cardiovascular diseases, but accurate ECG interpretation requires solid foundation of professional knowledge and rich clinical experience of physicians. Artificial intelligence (AI) has been one of hot research topics at present. Loads of research is devoted to developing AI models based on ECG, trying to elevate the reliability of ECG in diagnosing coronary artery diseases. This review introduces the important advances of AIenabled ECG in the detection of coronary artery lesions, and  discusses its clinical significance, development prospects and limitations.

Electrocardiogram (ECG) is an electrical signal of the heart recorded from the body surface by ECG recorder, which is an important tool for diagnosing cardiovascular diseases. As an important branch of artificial intelligence, machine learning can obtain information features from large ECG data sets to make accurate classification, diagnosis and interpretation of ECG,  and its diagnostic efficacy even reaches the level of medical experts.  Machine learning has been widely used in clinical practice. In recent years, it has been found that machine learning  also can effectively extract features in ECGs  that cannot be recognized by human eyes  to predict unidentified cardiovascular diseases such as left ventricular systolic dysfunction, asymptomatic atrial fibrillation and paroxysmal supraventricular tachycardia. As an important algorithm of machine learning, deep learning represented by convolutional neural network  also can make disease prediction more accurate. This review mainly summarizes the progress of ECGbased machine learning applied  in predicting cardiovascular diseases.

Objective  To discuss the feasibility of directly processing paper-based ECG by using deep learning method, and to propose a method for identifying atrial fibrillation (AF) from paper-based ECG rapidly and accurately. Methods  The 12-lead ECG signals of 1 040 AF and 1 344 non-AF patients were selected from CPSC 2018 Challenge data, and were plotted as  ECGs. These  ECGs were printed out on papers, and rescanned into images. The paper-based ECGs with white background were obtained by a series of preprocessing. These paper-based ECGs were used to construct AF recognition dataset; the artificial intelligence algorithm (AIA) was trained, validated and tested using the real labels provided by the Challenge as the gold standard. Results  The sensitivity, specificity and F1 score of the AIA based on paperbased ECGs are 0.957, 0.978 and 0.969, respectively, and the area under receiver operating characteristic curve  is 0.994. The Grad-CAM based feature visualization results show that in  paperbased ECGs, the position of P wave and F wave at the onset of AF provide main references for the algorithm to identify AF, which is consistent with the ECG diagnostic criteria of AF in clinical practice. Conclusion  The AF recognition algorithm based on paper-based ECGs shows good performance. The visualization results  verify the high efficiency and feasibility of directly analyzing paper-based ECGs by using AIA, which could provide guidance for clinical practice.

Atrial fibrillation(AF) is one of common arrhythmias in clinical practice. AF gives rise to a series of complications including stroke, thromboembolism and heart failure, which cause high disability rate and mortality, and increased family and social burdens. The treatment technology of AF is becoming more refined in modern medicine while traditional Chinese medicine has also achieved definite effect on AF. This paper reviews the research progress of diagnosing and treating AF with traditional Chinese medicine (TCM) from aspects of knowledge of disease name and pathogeny of AF in TCM, and typical TCM prescriptions, Chinese patent medicine and needle therapy of treating AF in TCM. This paper aims to provide new ideas for the diagnosis and treatment of AF.

The application of artificial intelligence (AI) and machine learning develops new pathways and new modalities for the diagnosis and treatment of hypertension. This paper reviews the progress of AI applied in aspects of hypertension prediction, assessment, and assistance for treatment decisionmaking. In terms of hypertension prediction, AI could build hypertension risk prediction models based on traditional hypertension risk factors combined with imaging, genomics and other factors, which improves the early diagnosis rate of hypertension. The AI expert system identifies complex etiology of hypertension, which makes up for the limitations of clinicians in diagnosis. In terms of hypertension assessment, the prediction model of hypertension complication constructed by AI could predict  complications in the heart and the brain blood vessel, and screen out highrisk population for early intervention. In terms of hypertension treatment, the application of clinical decisionmaking model, drug factor analysis model, monitoring and early warning system, humancomputer interaction, etc. could improve the accuracy, timeliness and patient compliance of hypertension treatment, and assist clinicians in making optimal treatment decisions. The exploration of AI in the field of hypertension diagnosis and treatment has established a new model for the chronic disease management of hypertension.

Significant prolongation of QT interval would easily cause malignant arrhythmias, and therefore in the research and development of new drugs, great importance should be attached to the evaluation of QT interval prolongation. As a necessary guiding principle for new drug research and development, ICH-E14 Guidelines, in the form of industry norms, stipulates that new non-antiarrhythmic drugs must be evaluated for QT/QTc interval prolongation before marketing. It means that electrocardiogram (ECG) monitoring will play an important role in the safety evaluation of this kind of drugs. In order to complete the collection and comprehensive analysis of ECG data with high standards and quality, this paper focuses on the methodology of QT/QTc interval measurement from several aspects. It introduces the requirements for instruments and personnel during QT interval measurement, the selection of measurement leads, the determination of QT interval starting and end points,  QT interval measurement under different circumstances，different correction methods for QT intervals, and notes during data measurement.

The prevalence rate of cardiovascular diseases in China has been increasing, therefore the precise diagnosis and treatment of arrhythmias is particularly critical. ECG examination is the main basis for the diagnosis of arrhythmias. At present, artificial intelligence ECG analysis technology has brought new possibilities to improve the efficiency and accuracy of clinical diagnosis and treatment of arrhythmias. This paper reviews the latest progress in the application of artificial intelligence ECG analysis technology at home and abroad, and summarizes the prospects and challenges of the technology in the diagnosis of arrhythmias.

Heart rate variability (HRV) is a non-invasive index for assessing the autonomic nervous system’s regulation of cardiac rhythm. This index reflects the automaticity of the heart and information related to physiological states. HRV has been used to evaluate the cardiac health, predict the risk of cardiovascular events, and monitor the efficacy of diseases. In recent years, related studies have found that HRV also has important values in evaluating non-cardiovascular system diseases, as well as mental stress and stress responses. This article reviews the history, recent advances in research and application of HRV, aiming to provide more information for clinical physicians.

In an order of the abstract structure of the human body from inside to outside, this paper lists the stateoftheart research advances of artificial intelligence (AI) especially deep neural network in ECG analysis from aspects of  electrical  conduction system and the structure of the heart (including heart valves, myocardium, coronary arteries, etc.), other systems out of the heart, ect. This paper introduces the application of AIenabled ECG analysis technology in identifying arhythmias, electrolyte disturbances, valvular heart disease, coronary heart disease, and diseases of the circulation system and digestive system. This paper also covers its innovative application in the field of personal identification, and how to use AI technologies such as transfer learning in practical research. This paper is aimed to promote more crossfield cooperations, explore deep values of ECG, and help to realize the screening, diagnosis and treatment of multisystem diseases.

The National Medical Products Administration demands that the relevant requirements for  drug clinical studies initiated since July 31, 2023 follow the “E14: the clinical evaluation of QT/QTc interval prolongation and proarrhythmic potential for non-antiarrhythmic drugs”. This paper introduces QT interval and QTc, non-antiarrhythmic drugs potentially leading to QT interval prolongation and even torsade de pointes, the mechanism of QT interval prolongation, predisposing factors, and other related issues. It is aimed to arouse more attention to the effects of new nonantiarrhythmic drugs on QT/QTc interval among clinicians, and to improve the safety of drug use.

 Objective  To establish the normal reference range of electrocardiogram (ECG) in healthy neonates with different sexes. Methods  We recorded and measured routine 12-lead synchronous ECGs of 906 healthy neonates (including 474 males and 432 females), and made statistical analysis of the collected data. We  obtained the normal  reference  ranges of the related ECG indexes  (including heart rate, mean QRS axis, P-wave duration, PR interval, P-wave amplitude, QRS duration, QRS amplitude, QTc, T-wave amplitude, etc.), and the morphologies of P-wave, QRS complex and T-wave in the neonates with different sexes. Results  There are significant differences of P-wave amplitude in leads Ⅰ,Ⅱ, aVL, aVR, V₂ and  V₄-V₆, QRS duration in leads Ⅰ,Ⅱ,Ⅲ, aVR, aVL, aVF, V₁ and V₃-V₆, QRS amplitude in leads Ⅲ, aVR, aVF and V₁-V₄, T-wave amplitude in leads aVR, aVL and V₄-V₆, QRS complex morphology in leads Ⅰ,Ⅱ, aVR, aVF, V₁ and V₃-V₆, and T-wave morphology in leads Ⅰ, aVL and V₆ between the male and female neonates (P<0.05). Conclusion  The normal  reference ranges of ECG indexes recorded by 12lead synchronous ECGs in healthy neonates are different between the sexes.

Atrial fibrillation (AF) is one of the most common arrhythmias. It is characterized by concealment, paroxysmal nature, complexity, and high mortality and disability rate; the prevalence rate of AF is on the rise. The new emergence of artificial intelligence technology breaks through the limitations of traditional methods of AF screening, showing unique advantages and broad application prospects in the screening, diagnosis and prediction of AF. Intelligent wearable devices have higher feasibility, specificity and sensitivity in the screening  of AF, with high cost-effectiveness in clinical application.

The etiology of sudden unexplained death (SUD) is complicated, and its  incidence remains significant at present. The key to its prevention and treatment lies in identifying the underlying pathogenic factors. With the progress of molecular biology techniques, numerous  studies at home and abroad have substantiated a strong association between sudden cardiac death (SCD) caused by pathogenic gene mutations and SUD. The conspicuous clustering characteristics observed in cases of Yunnan sudden unexplained death (YNSUD) indicate the potential involvement of molecular genetics. In the population of the affected area, the detection rates of abnormal electrocardiogram (ECG) indicators increased while cardiac pathological changes were found in 90% of sudden death cases, which further implies a possible correlation between YNSUD and pathogenic gene mutations related to SCD. Understanding the genetic predisposition, genetic mutation, risk factors, and pathogenic mechanisms of SCD contributes to identifying the highrisk factors associated with this kind of sudden death, so as to carry out targeted prevention and treatment. This paper reviews the current research trends in hereditary arrhythmias and hereditary cardiomyopathy related to SUD, and summarizes the latest research results and pathogenic factors.It is aimed to provide a foundation for further investigations on the etiology.

Objective  To investigate the importance of standard operation of ECG examination for quality control of remote ECG network. Methods  We analyzed ECGs transmitted through the network from January 1,2022 to June 30,2023 at the ECG Network Center of the First People’s Hospital of Xianyang. During the time period, we took every six months as a stage, and performed targeted operation training of ECG examination at each stage. We compared the graphic quality problems and the number of ECGs with quality problems among different stages. Results  After regular ECG operation training for clinical medical staff and instrument maintenance, the quality of ECG graphics has been greatly improved. Conclusion  Standard operation of remote ECG network directly affects the diagnostic accuracy of ECGs. Regular standardized training of ECG operation for clinical medical staff could improve the accuracy of ECG examination results, and avoid the occurrence of medical adverse events.

Leadless pacemakers (LPMs), which have emerged in recent years, avoid the lead and pocketrelated complications associated with conventional lead pacemakers, such as tricuspid regurgitation, lead fracture, lead endocarditis or pocket infection. Not only has LPM a significant advantage over conventional pacemakers in terms of safety, but also its stability of pacingrelated parameters has been demonstrated during a relatively long followup period.  At present, LPM has been approved for marketing in China. Although the application of LPM is still in its infancy, the implantation volume is growing rapidly, therefore its development prospect in the future is good. This article reviews  the clinical application evidences of existing LPM, related techniques and postoperative management of LPM implantation, future development direction of LPM, and so on.

Heart rate variability (HRV) is a noninvasive index for evaluating cardiac autonomic function, which is closely related to many diseases. It could be used for disease screening, risk stratification, diagnosis and treatment, efficacy evaluation and so on. With the development of technology and optimization of algorithms, the application of HRV in pacemakers and wearable devices has developed  further. This paper mainly illustrates the research background, progress in clinical application and research trends of HRV, and looks forward to the  research directions in the future.

Atrial fibrillation (AF) has become an important disease that endangers the health of middle-aged and elderly people in China, and it is related to the risk of stroke and death. At present, pathophysiological mechanisms such as atrial structural remodeling, electrical remodeling, inflammation, autonomic nervous system disorders, and non-coding RNA may explain the occurrence and development of AF. The treatment of AF mainly includes anticoagulation, conversion of sinus rhythm, and control of ventricular rate. In addition, antiinflammatory, autonomic nerve intervention and genomics intervention therapy may become  new types of therapies for AF. This article reviews the research progress in the   pathogenesis and treatment of AF.

Atrial fibrillation (AF) is the most common arrhythmia and may easily lead to various complications. Therefore, precision medical methods are needed to identify and enhance AF detection to achieve early diagnosis and treatment. Artificial intelligencebased wearable devices are of great value for the screening and management of AF patients. This article reviews the relevant literature on recent applications of such devices for AF screening.

Brugada wave is a special ECG pattern that presents as a “triad” of right bundle branch block, STsegment elevation in the right chest lead, and T wave inversion. It could lead to arrhythmia and sudden cardiac death. It has been previously considered that Brugada wave is associated with genetics, electrophysiological mechanism, nerve crest hypothesis and so on. The latest studies have found that mutations in mitochondrial DNA and tRNA, inflammation, and myocardial stroma abnormalities may also be involved in the occurrence and development of Brugada wave. This paper mainly reviews the latest research progress of the electrocardiographic mechanism of Brugada wave.

More and more studies have shown that the risk of arrhythmias in diabetes patients is significantly increased, but their mechanisms are complex and have not been fully clarified at present. Based on explaining the relationship between  diabetes and arrhythmias, this article  reviews the mechanisms of diabetes related arrhythmias from aspects of inflammation, oxidative stress, autonomic nervous dysfunction, mitochondrial dysfunction, electrical remodeling, blood glucose levels, glucose fluctuations, etc. It is aimed at providing a novel strategy for the prevention and treatment of this disease.

How to determine the antithrombotic strength in patients with atrial fibrillation (AF) complicating stable coronary artery disease (SCAD) after one year has always been a clinical challenge and a controversial issue. In the past, most of these people were considered to take longterm single anticoagulation, however the related evidencebased medicine evidences were not sufficient. At present, it is recommended that individualized and accurate management should be performed according to the risk stratification of ischemia and bleeding. Not only should the embolization score of AF be evaluated, but the complexity of the coronary artery disease should also be evaluated. The CHA2DS2VASc, SYNTAX Ⅱ and DAPT scores should be combined to comprehensively assess the ischemic risk of individuals while the HASBLED or BARC score should be combined to assess the bleeding risk for antithrombotic stratified management and dynamic evaluation. Anticoagulation combined with antiplatelet dual pathway inhibition can be given to the population with high ischemia risk and low bleeding risk. Longterm single anticoagulant therapy is suggested to be given to the population with low ischemia risk and high bleeding risk. This article mainly discusses the optimal antithrombotic strategy for patients with AF complicating SCAD after one year.

Valvular heart disease (VHD) is a common organic heart disease, and its incidence gradually increases with age. With the crossintegration of artificial intelligence and medical field, artificial intelligence algorithm models have become effective  tools for identifying a variety of heart diseases. Artificial intelligenceenabled ECG (AIECG) diagnostic models can identify VHD patients by analyzing their ECG features, which may become an auxiliary tool for the identification of VHD in clinical practice. This paper summarizes the research progress of AIECG diagnostic models in the identification of VHD.

In recent years, the combination of remote ECG monitoring and artificial intelligence (AI) technology has greatly assisted the diagnosis and treatment of cardiovascular diseases, and shows extremely broad development prospect. This paper summarizes the progress in the application of AIbased remote ECG monitoring technology in the intelligent diagnosis, hierarchical diagnosis and treatment, prognosis evaluation, and individualized management of acute coronary syndrome. It also introduces the active health intelligent management system of the heart which has been constructed and gradually improved in China on this basis.

Subclinical atrial fibrillation (SCAF) refers to atrial fibrillation with no or almost no symptoms which occurs in a subclinical form. It is detected by the programming of cardiac implantable electronic devices (CIED). In recent years, with the development of CIED, SCAF has gradually been recognized by scholars, and become the focus of research. This article mainly reviews the latest progress in aspects of screening methods, risk of stroke and therapy of SCAF.

With biological identification features of universality, portability, uniqueness and stability, electrocardiogram (ECG) as a novel identification method has crossover application in the information field. It enriches and improves the existing biometric identification techniques, and is suitable for customer  identification in the insurance industry. This paper firstly introduces common biometric identification techniques used in the insurance industry, and ECG biometric identification technique and its advantages. It then explains the main content of ECG biometric identification technique, and systematically reviews the latest research advances at home and abroad related to the characteristic points of ECG identification and their extraction. Based on the application practice of ECG identification technique in the domestic insurance industry for nearly 20 years, this paper outlines its technical identification process. Finally, this paper looks forward to the development of the technique in the future. It is aimed to further promote the application of this technique in the insurance industry and other industries.

 Objective  To analyze the value of exercise stress test (EST) and related parameters on diagnosing coronary heart disease (CHD), and to explore the influence of individual factors [such as age, sex and body mass index(BMI)] on its diagnostic accuracy. Methods  We selected 439 patients who had performed treadmill or bicycle exercise test and coronary angiography (CAG). There were 318 CAG positive patients and 121 negative cases among those patients. The sensitivity and specificity of their EST results were observed. All the enrolled patients were grouped according to age, sex, BMI, the number of lesioned vessels, the lesioned vessels whether including the left main artery (LM) and(or) the proximal branch of the left anterior descending artery (LAD1), and the presence or absence of ventricular arrhythmias. The reference value of EST parameters on the definite diagnosis of CHD was analyzed in each group.Results  The sensitivity and specificity of EST in diagnosing CHD is separately 81.22% and 34.71%. The true positive rate of the multibranch coronary artery lesion group is significantly higher than that of the singlebranch vascular lesion group (88.12% vs. 73.96%, P=0.011), however its false negative rate is lower than that of the singlebranch vascular lesion group (11.88% vs. 26.04%, P=0.011). The true positive rate of the LM and(or) LAD1 lesion group does not vary significantly from that of the nonLM and(or) LAD1 lesion group (76.92% vs. 8602%, P=0.103). In the EST true positive group, the peak heart rate (HR) during exercise, attainment rate of target HR, and 1 and 2 min HR during the recovery period are all lower than those in the false positive group (P＜0.05). Among the true positive cases, the peak HR during exercise, attainment rate of target HR, and 1 and 2 min HR during the recovery period of the singlebranch vascular lesion group are all higher than those of the multibranch coronary artery lesion group (P＜0.05). The incidence of ventricular arrhythmias of the true positive group is significantly higher than that of the false positive group (63.06% vs. 18.02%, P=0.048) and the false negative group (63.06% vs. 7.21%, P=0.046). Conclusion  EST has some diagnostic value for CHD. For the elderly overweight males with abnormal peak HR during exercise, attainment rate of target HR, and 1 and 2 min HR during the recovery period, and with ventricular arrhythmias, positive EST results suggest further CAG examination. For the patients with high suspicion of CHD and negative EST results, the related individual factors should be comprehensive analyzed.