Market-applicable concurrent electrocardiogram (ECG) diagnosis for multiple heart abnormalities that covers a wide range of arrhythmias, with better-than-human accuracy, has not yet been developed. We therefore aimed to engineer a deep learning approach for the automated multilabel diagnosis of heart rhythm or conduction abnormalities by real-time ECG analysis. We used a dataset of ECGs (standard 10 s, 12-channel format) from adult patients (aged ≥18 years), with 21 distinct rhythm classes, including most types of heart rhythm or conduction abnormalities, for the diagnosis of arrhythmias at multilabel level. The ECGs were collected from three campuses of Tongji Hospital (Huazhong University of Science and Technology, Wuhan, China) and annotated by cardiologists. We used these datasets to develop a convolutional neural network approach to generate diagnoses of arrythmias. We collected a test dataset of ECGs from a new group of patients not included in the training dataset. The test dataset was annotated by consensus of a committee of board-certified, actively practicing cardiologists. To evaluate the performance of the model we assessed the F1 score and the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, as well as quantifying sensitivity and specificity. To validate our results, findings for the test dataset were compared with diagnoses made by 53 ECG physicians working in cardiology departments who had a wide range of experience in ECG interpretation (range 0 to >12 years). An external public validation dataset of 962 ECGs from other hospitals was used to study generalisability of the diagnostic model. Our training and validation dataset comprised 180 112 ECGs from 70 692 patients, collected between Jan 1, 2012, and Apr 30, 2019. The test dataset comprised 828 ECGs corresponding to 828 new patients, recorded between Sept 11, 2012, and Aug 30, 2019. At the multilabel level, our deep learning approach to diagnosing heart abnormalities resulted in an exact match in 658 (80%) of 828 ECGs, exceeding the mean performance of physicians (552 [67%] for physicians with 0-6 years of experience; 571 [69%] for physicians with 7-12 years of experience; 621 [75%] for physicians with more than 12 years of experience). Our model had an overall mean F1 score of 0·887 compared with 0·789 for physicians with 0-6 years of experience, 0·815 for physicians with 7-12 years of experience, and 0·831 for physicians with more than 12 years of experience. The model had a mean AUC ROC score of 0·983 (95% CI 0·980-0·986), sensitivity of 0·867 (0·849-0·885) and specificity of 0·995 (0·994-0·996). Promising F1 scores were also obtained from the external public database using our proposed model without any model modifications (mean F1 scores of 0·845 in multilabel and 0·852 in single-label ECGs). Our model is more accurate than physicians working in cardiology departments at distinguishing a range of distinct arrhythmias in single-label and multilabel ECGs, laying a promising foundation for computational decision-support systems in clinical applications. National Natural Science Foundation of China and Hubei Science and Technology Project.

Background: Severe acute respiratory syndrome coronavirus 2 causes acute myocardial damage and arrhythmia in coronavirus disease 2019 (COVID‐19) patients. Studying the changes of electrocardiogram is of great significance for the diagnosis of patients with COVID‐19.Methods: A retrospective analysis method was adopted to compare the electrocardiogram changes between COVID‐19 critically severe and severe patients. Univariate and multivariate logistic regression were used to analyze the correlation of the levels of serum indexes and past medical history with ST‐T changes and atrial fibrillation. And the correlation of ECG parameters with in‐hospital death and ventilator use were investigated by using the same methods.Results: The incidence of male, stroke, elevated cardiac troponin I (cTnI), N‐terminal of the prohormone brain natriuretic peptide (NT‐proBNP), d‐dimer, high‐sensitivity C‐reactive protein (hs‐CRP), hyperkalemia, and hypocalcemia in the critically ill patients was higher than that in severe patients. There were differences in ST‐T changes, sinus tachycardia, atrial fibrillation, and atrial tachycardia between the two groups. Multivariate logistic regression analysis showed that elevated cTnI and NT‐proBNP were the independent risk factors of ST‐T changes. Elevated NT‐proBNP and age were the independent risk factors of atrial fibrillation. Sinus tachycardia and atrial fibrillation were the independent risk factors of in‐hospital death and ventilator use.Conclusion: ST‐T changes, sinus tachycardia, and atrial fibrillation are with great significance in the diagnosis of the severity, myocardia injury, and cardiac insufficiency of COVID‐19 patients. Sinus tachycardia and atrial fibrillation could be used as independent variables predicting in‐hospital death and ventilator use.

The accurate electrocardiogram (ECG) interpretation is important for several potentially life-threatening cardiac diseases. Recently developed deep learning methods show their ability to distinguish some severe heart diseases. However, since deep neural network requires a high cost on memory consumption and computation, implementation scenarios of these interpretation methods are constrained to nonportable devices. Few commercial portable devices only have heartbeat detection ability, and therefore, only a few simple cardiac diseases can be diagnosed. In this article, to achieve diagnosing a wide range of cardiac diseases and continuous monitoring, a homecare-oriented ECG diagnosis platform is designed based on a large-scale multilabel deep conventional neural network. The accuracy of the proposed neural network model is guaranteed by our constructed large-scale ECG dataset, which is comprised of 206 468 standard 12-lead ECG recordings from 89 488 patients, with respect to 26 types of most common heart rhythms and conduction abnormalities. Meanwhile, targeting lightweight homecare or wearable applications, algorithm-hardware co-optimization is conducted to accelerate the model computation on an embedded platform with field-programmable gate array (FPGA) for continuous monitoring. Channel-level pruning and parameters quantization strategy are employed to optimize the network, and a reconfigurable accelerator hardware architecture is designed to accelerate the convolution computation on FPGA. The final quantified model achieved a promising $F_{1}$ score of 0.913% and 86.7% exact match ratio, in which parameters and floating-point operations per second (FLOPs) are significantly penalized compared to the original large-scale model. Real-time analysis is performed. Specifically, the average processing time for each ECG record is 2.895 s, and it can be applied to homecare or portable ECG diagnosis devices for continuous monitoring.

Paroxysmal atrial fibrillation (AF) is generally diagnosed by long-term dynamic electrocardiogram (ECG) monitoring. Identifying AF episodes from long-term ECG data can place a heavy burden on clinicians. Many machine-learning-based automatic AF detection methods have been proposed to solve this issue. However, these methods require numerous annotated data to train the model, and the annotation of AF in long-term ECG is extremely time-consuming. Reducing the demand for labeled data can effectively improve the clinical practicability of automatic AF detection methods. In this study, we developed a novel semi-supervised learning method that generated modified low-entropy labels of unlabeled samples for training a deep learning model to automatically detect paroxysmal AF in 24 h Holter monitoring data. Our method employed a 1D CNN-LSTM neural network with RR intervals as input and used few labeled training data with numerous unlabeled data for training the neural network. This method was evaluated using a 24 h Holter monitoring dataset collected from 1000 paroxysmal AF patients. Using labeled samples from only 10 patients for model training, our method achieved a sensitivity of 97.8%, specificity of 97.9%, and accuracy of 97.9% in five-fold cross-validation. Compared to the supervised learning method with complete labeled samples, the detection accuracy of our method was only 0.5% lower, while the workload of data annotation was significantly reduced by more than 98%. In general, this is the first study to apply semi-supervised learning techniques for automatic AF detection using ECG. Our method can effectively reduce the demand for AF data annotations and can improve the clinical practicability of automatic AF detection.

Background: Deceleration capacity (DC) is a newly found predictor of mortality after myocardial infarction. Age‐, gender‐, and circadian rhythm–related differences in DC may limit its predictive value, which should be considered in clinical settings.Methods: DC, average heart rate, and HRV parameters, including 24 hours, awaking state (15:00–20:00) and sleeping mode (00:00–05:00) strips from 24 hours Holter recordings in 636 subjects without heart diseases were examined. Heart rate variability was analyzed in time domains (standard deviation of all normal‐to‐normal intervals [SDNN], normal‐to‐normal RR intervals in all 5‐minute segments [SDANN], and root mean square successive difference [RMSSD]).Results: The DC, SDNN, SDANN, RMSSD, and heart rate decreased with age. Deceleration capacity was significantly lower in patients greater than 50 years of age. The largest decrease of SDNN, SDANN, and RMSSD occurred in patients 30–39 years of age. The values of SDNN, SDANN, and DC of women were lower than that of men in the young and middle‐aged groups, but age‐related decrease of DC in men was greater than that in women. Heart rate of women was significantly higher than that of men in younger subjects, especially in a sleeping mode. There were higher values of DC and RMSSD during sleeping than that during a waking state.Conclusions: The age, gender, and circadian rhythm may be useful when evaluating cardiac autonomic function and need to be considered when evaluating DC and HRV in clinical and scientific researches.

We present a complete, end-to-end computer-aided detection (CAD) system for identifying lesions in the colon, imaged with computed tomography (CT). This system includes facilities for colon segmentation, candidate generation, feature analysis, and classification. The algorithms have been designed to offer robust performance to variation in image data and patient preparation. By utilizing efficient 2D and 3D processing, software optimizations, multi-threading, feature selection, and an optimized cascade classifier, the CAD system quickly determines a set of detection marks. The colon CAD system has been validated on the largest set of data to date, and demonstrates excellent performance, in terms of its high sensitivity, low false positive rate, and computational efficiency.