Search

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Since the outbreak of corona virus disease 2019, deep learning has been widely used in predicting epidemic trends, screening high-risk groups and making early diagnosis. Novel coronavirus infection mainly causes pulmonary diseases, and also affects cardiovascular system, resulting in electrocardiogram (ECG) abnormalities. ECG tracking image technology is a hot spot in the research of deep learning. Compared with traditional ECG judgment methods, its accuracy and sensitivity are both higher. It can be used in the effective diagnosis, clinical decision-making and prognosis evaluation of patients with novel coronavirus infection. This paper reviews on the ECG changes after novel coronavirus infection, and the advances of ECG tracking image technology applied in the auxiliary diagnosis of novel coronavirus infection, so as to provide references for clinical healthcare workers. [ABSTRACT FROM AUTHOR]

Since its first clinical application 120 years ago, electrocardiogram (ECG) has still been one of the most important routine examinations in clinical practice till now. The accelerated popularity of remote, portable ECG and cloud ECG platforms promotes ECG technology—from hospitals to the society, family and even every one. The arrival of body surface three-dimensional electroanatomical mapping visualizes the presentation of abstract ECG morphologies, and clearly reveals the origin of arrhythmia and ECG signal conduction process. This amounts to a “pathological anatomy” like gold-standard validation diagnosis for the ECG. Through deep learning, artificial intelligence (AI)-ECG can explore the fields that cannot be interpreted by ECG before, which greatly expands the connotation of ECG. This paper briefly reviews the development process of ECG technology from remote ECG, three-dimensional ECG and portable ECG to AI-ECG in the past 120 years, and looks forward to its development trend in the future. [ABSTRACT FROM AUTHOR]

Since its first clinical application 120 years ago, electrocardiogram (ECG) has still been one of the most important routine examinations in clinical practice till now. The accelerated popularity of remote, portable ECG and cloud ECG platforms promotes ECG technology—from hospitals to the society, family and even every one. The arrival of body surface three-dimensional electroanatomical mapping visualizes the presentation of abstract ECG morphologies, and clearly reveals the origin of arrhythmia and ECG signal conduction process. This amounts to a “pathological anatomy” like gold-standard validation diagnosis for the ECG. Through deep learning, artificial intelligence (AI)-ECG can explore the fields that cannot be interpreted by ECG before, which greatly expands the connotation of ECG. This paper briefly reviews the development process of ECG technology from remote ECG, three-dimensional ECG and portable ECG to AI-ECG in the past 120 years, and looks forward to its development trend in the future. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

As one of the most common arrhythmias in clinical practice, atrial fibrillation is characterized by being occult, paroxysmal, complex, and high mortality and disability. It is considered as a “silent killer”. This paper summarizes the progress of artificial intelligence applied in the diagnosis and prediction of atrial fibrillation, assistance for decision-making in ablation, plasma drug concentration monitoring, prognosis prediction, etc. from clinical perspectives. [ABSTRACT FROM AUTHOR]

With the development of medical technology and wireless network technology, wearable ECG device has attracted more and more attention in recent years, and is applied to diagnose various kinds of arrhythmias such as atrial fibrillation. Combined with scatter plot and artificial intelligence, wearable ECG device strengthens its abilities to identify and diagnose arrhythmias. It facilitates patients to monitor arrhythmia events out of hospital, and obtain timely diagnosis and treatment. This paper discusses the functional and technological innovation of wearable ECG devices, and reviews their clinical application progress in patients with arrhythmia. [ABSTRACT FROM AUTHOR]

With the emerging and mutation of various pathogenic genes,the prevalence of corresponding genetic diseases also increases year by year. The penetrance of potentially pathogenic mutation is often atypical or the mutation manifests itself only in one’s later years,which tends to complicate and delay the diagnosis of genetic heart diseases. With the development and application of new technologies such as machine learning,artificial intelligence（ AI） has become a powerful tool in many fields including personalized medicine,medical imaging,and disease diagnosis. By using AI,we can specifically analyze and summarize the characteristic manifestations of ECG in patients with genetic arrhythmias,contributing to the early diagnosis of related diseases. This paper reviews the latest research progress of AI-enabled ECG utilized in the diagnosis of inherited arrhythmias,mainly including congenital long QT syndrome,Brugada syndrome,and catecholaminergic polymorphic ventricular tachycardia. [ABSTRACT FROM AUTHOR]