Deep Learning-Based Arrhythmia Detection in Electrocardiograph

This study aimed to explore the application of electrocardiograph (ECG) in the diagnosis of arrhythmia based on the deep convolutional neural network (DCNN). ECG was classified and recognized with the DCNN. The specificity (Spe), sensitivity (Sen), accuracy (Acc), and area under curve (AUC) of the DCNN were evaluated in the Chinese Cardiovascular Disease Database (CCDD) and Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database, respectively. The results showed that in the CCDD, the original model tested by the small sample set had an accuracy (Acc) of 82.78% and AUC of 0.882, while the Acc and AUC of the translated model were 85.69% and 0.893, respectively, so the difference was notable ( P < 0.05); the Acc of the original model and the translated model was 80.12% and 82.63%, respectively, in the large sample set, so the difference was obvious ( P < 0.05). In the MIT-BIH database, the Acc of normal (N) heart beat (HB) (99.38%) was higher than that of the atrial premature beat (APB) (87.45%) ( P < 0.05). In a word, applying the DCNN could improve the Acc of ECG for classification and recognition, so it could be well applied to ECG signal classification.

Significant abnormal glycemic variability increased the risk for arrhythmias in elderly type 2 diabetic patients

Background Little is known about whether the influence of glycemic variability on arrhythmia is related to age in type 2 diabetes mellitus (T2DM). Therefore, we aimed to compare the association between glycemic variability and arrhythmia in middle-aged and elderly T2DM patients. Methods A total of 107 patients were divided into two groups: elderly diabetes mellitus group (EDM, n = 73) and middle-aged diabetes mellitus group (MDM, n = 34). The main clinical data, continuous glucose monitoring (CGM) and dynamic ECG reports were collected. The parameters including standard deviation of blood glucose (SDBG), largest amplitude of glycemic excursions (LAGE), mean amplitude of glycemic excursions (MAGE), absolute means of daily differences (MODD), time in range (TIR), time below range (TBR), time above range (TAR), coefficient of variation (CV) were tested for glycemic variability evaluation. Results In terms of blood glucose fluctuations, MAGE (5.77 ± 2.16 mmol/L vs 4.63 ± 1.89 mmol/L, P = 0.026), SDBG (2.39 ± 1.00 mmol/L vs 2.00 ± 0.82 mmol/L, P = 0.048), LAGE (9.53 ± 3.37 mmol/L vs 7.84 ± 2.64 mmol/L, P = 0.011) was significantly higher in EDM group than those of MDM group. The incidences of atrial premature beat, couplets of atrial premature beat, atrial tachycardia and ventricular premature beat were significantly higher in EDM group compared with the MDM group (all P < 0.05). Among patients with hypoglycemia events, the incidences of atrial premature beat, couplets of atrial premature beat, atrial tachycardia and ventricular premature beat (all P < 0.05) were significantly higher in the EDM group than those in the MDM group. In EDM group, TIR was negatively correlated with atrial tachycardia in the MAGE1 layer and with atrial tachycardia and ventricular premature beat in the MAGE2 layer, TBR was significantly positively correlated with atrial tachycardia in the MAGE2 layer (all P < 0.05). In MDM group, TAR was positively correlated with ventricular premature beat and atrial tachycardia in the MAGE2 layer (all P < 0.05). Conclusions The study demonstrated the elderly patients had greater glycemic variability and were more prone to arrhythmias. Therefore, active control of blood glucose fluctuation in elderly patients will help to reduce the risk of severe arrhythmia.

Significant Abnormal Glycemic Variability Increased the Risk for Arrhythmias in Middle-Aged and Elderly Type 2 Diabetic Patients

Background: Little is known about whether the influence of glycemic variability on arrhythmia is related to age in type 2 diabetes mellitus (T2DM). Therefore, we aimed to compare the association between glycemic variability and arrhythmia in middle-aged and elderly T2DM patients. Methods: A total of 107 patients were divided into two groups: elderly diabetes mellitus group (EDM, n=73) and middle-aged diabetes mellitus group (MDM, n=34). The main clinical data, continuous glucose monitoring (CGM) and dynamic ECG reports were collected. The parameters including standard deviation (SDBG), largest amplitude of glycemic excursions (LAGE), mean amplitude of glycemic excursions (MAGE), absolute means of daily differences (MODD) were tested for glycemic variability evaluation. Results: In terms of blood glucose fluctuations, MAGE (5.77±2.16mmol/L vs 4.63 ±1.89mmol/L, P=0.026), SDBG (2.39±1.00mmol/L vs 2.00±0.82mmol/L, P=0.048), LAGE (9.53±3.37mmol/L vs 7.84±2.64 mmol/L, P=0.011) was significantly higher in EDM group than those of MDM group. The incidences of atrial premature beat, couplets of atrial premature beat, atrial tachycardia and ventricular premature beat were significantly higher in EDM group compared with the MDM group (all P<0.05). Among patients with hypoglycemia events, the incidences of atrial premature beat, couplets of atrial premature beat, atrial tachycardia and ventricular premature beat (all P<0.05) were significantly higher in the EDM group than those in the MDM group. Conclusions: The study demonstrated the elderly patients had greater glycemic variability and were more prone to arrhythmias. Therefore, active control of blood glucose fluctuation in elderly patients will help to reduce the risk of severe arrhythmia.

Automatic ECG Diagnosis Using Convolutional Neural Network

Cardiovascular disease (CVD) is the most common class of chronic and life-threatening diseases and, therefore, considered to be one of the main causes of mortality. The proposed new neural architecture based on the recent popularity of convolutional neural networks (CNN) was a solution for the development of automatic heart disease diagnosis systems using electrocardiogram (ECG) signals. More specifically, ECG signals were passed directly to a properly trained CNN network. The database consisted of more than 4000 ECG signal instances extracted from outpatient ECG examinations obtained from 47 subjects: 25 males and 22 females. The confusion matrix derived from the testing dataset indicated 99% accuracy for the “normal” class. For the “atrial premature beat” class, ECG segments were correctly classified 100% of the time. Finally, for the “premature ventricular contraction” class, ECG segments were correctly classified 96% of the time. In total, there was an average classification accuracy of 98.33%. The sensitivity (SNS) and the specificity (SPC) were, respectively, 98.33% and 98.35%. The new approach based on deep learning and, in particular, on a CNN network guaranteed excellent performance in automatic recognition and, therefore, prevention of cardiovascular diseases.

Using Deep Learning Detection Of Arrhythmia

The field of deep learning applications is becoming more widespread. The use of traditional algorithms for arrhythmia detection is cumbersome and the algorithm complexity is relatively high. Using the deep learning model to directly input data into the model will make it difficult to effectively segment the data, which will have a large error in the recognition accuracy. We collected data from six commonly used ECG databases and then used the label shuffling method to amplify the samples, effectively overcoming the effects of sample imbalance. The LSTM model is used for feature point detection to effectively locate the key feature points of the ECG signal, thereby completing the segmentation and processing of the data. Finally, the use of a multiple input model single output for arrhythmia detection has achieved significant results. The average accuracy of the final arrhythmia classification of the model reached 0.711. The accuracy of detecting the fusion of ventricular and normal beat and the aberrated atrial premature beat exceeds 0.9.