The importance of an embedded wearable device with automatic detection and alarming cannot be overstated, given that 15–30% of patients with atrial fibrillation are reported to be asymptomatic. These asymptomatic patients do not seek medical care, hence traditional diagnostic tools including Holter are not effective for the further prevention of associated stroke or heart failure. This is likely to be more so in the era of COVID-19, in which patients become more reluctant on hospitalization and checkups. However, little literature is available on this important topic. For this reason, this study developed efficient deep learning with model compression, which is designed to use ECG data and classify arrhythmia in an embedded wearable device. ECG-signal data came from Korea University Anam Hospital in Seoul, Korea, with 28,308 unique patients (15,412 normal and 12,896 arrhythmia). Resnets and Mobilenets with model compression (TensorFlow Lite) were applied and compared for the diagnosis of arrhythmia in an embedded wearable device. The weight size of the compressed model registered a remarkable decrease from 743 MB to 76 KB (1/10000), whereas its performance was almost the same as its original counterpart. Resnet and Mobilenet were similar in terms of accuracy, i.e., Resnet-50 Hz (97.3) vs. Mo-bilenet-50 Hz (97.2), Resnet-100 Hz (98.2) vs. Mobilenet-100 Hz (97.9). Here, 50 Hz/100 Hz denotes the down-sampling rate. However, Resnets took more flash memory and longer inference time than did Mobilenets. In conclusion, Mobilenet would be a more efficient model than Resnet to classify arrhythmia in an embedded wearable device.

Accurate electrocardiogram (ECG) interpretation is crucial in the clinical ECG workflow because it is most likely associated with a disease that can cause major problems in the body. In this study, we proposed an ECG-signal multi-classification model using deep learning. We used a squeeze-and-excitation residual network (SE-ResNet), which is a residual network(ResNet) with a squeeze-and-excitation block. Experiments were performed for seven different types of lead-II ECG data obtained from the Korea University Anam Hospital in South Korea. These seven types are normal sinus rhythm, atrial fibrillation, atrial flutter, sinus bradycardia, sinus tachycardia, premature ventricular contraction and first-degree atrioventricular block. We compared the SE-ResNet with a ResNet, as a baseline model, for various depths of layer (18/34/50/101/152). We confirmed that the SE-ResNet had better classification performance than the ResNet, for all layers. The SE-ResNet classifier with 152 layers achieved F1 scores of 97.05% for seven-class classifications. Our model surpassed the baseline model, ResNet, by +1.40% for the seven-class classifications. For ECG-signal multi-classification, considering the F1 scores, the SE-ResNet might be better than the ResNet baseline model.

Chung WJ, et al. J Korean Med Sci. 2008 Apr;23(2):284-287. http://dx.doi.org/10.3346/jkms.2008.23.2.284

Background: The global age-adjusted mortality rate related to atrial fibrillation (AF) registered a rapid growth in the last four decades, i.e., from 0.8 to 1.6 and 0.9 to 1.7 per 100,000 for men and women during 1990–2010, respectively. In this context, this study uses convolutional neural networks for classifying (diagnosing) AF, employing electrocardiogram data in a general hospital. Methods: Data came from Anam Hospital in Seoul, Korea, with 20,000 unique patients (10,000 normal sinus rhythm and 10,000 AF). 30 convolutional neural networks were applied and compared for the diagnosis of the normal sinus rhythm vs. AF condition: 6 Alex networks with 5 convolutional layers, 3 fully connected layers and the number of kernels changing from 3 to 256; and 24 residual networks with the number of residuals blocks (or kernels) varying from 8 to 2 (or 64 to 2). Results: In terms of the accuracy, the best Alex network was one with 24 initial kernels (i.e., kernels in the first layer), 5,268,818 parameters and the training time of 89 s (0.997), while the best residual network was one with 6 residual blocks, 32 initial kernels, 248,418 parameters and the training time of 253 s (0.999). In general, the performance of the residual network improved as the number of its residual blocks (its depth) increased. Conclusion: For AF diagnosis, the residual network might be a good model with higher accuracy and fewer parameters than its Alex-network counterparts.

Jun Hee Lee, M.D., Jong Yun Won, M.D., Ji Eon Kim, M.D., Hee Jung Kim, M.D., Ph.D., Jae Seung Jung, M.D., Ph.D., Ho Sung Son, M.D., Ph.D.. J Chest Surg 2021;54:36-44. https://doi.org/10.5090/kjtcs.20.123

Summary: We measured heating of isotonic saline by three fluid warmers in six experiments: saline at 5 °C or 20 °C delivered at 30, 50 or 100 ml.min ⁻¹ . At the three flow rates, the enFLOW ^® , buddy lite ^™ and ThermoSens ^® systems heated 5 °C saline to mean ( SD ) temperatures of: 41.1 (0.5) °C, 37.7 (0.6) °C and 39.1 (0.6) °C; to 40.3 (0.8) °C, 33.9 (1.6) °C and 39.3 (0.7) °C; and to 37.1 (0.8) °C, 24.0 (1.3) °C and 37.6 (1.0) °C, respectively, p < 0.0001 for each experiment. The mean ( SD ) times taken to heat 5 °C saline were: 16.6 (1.7) s, 258.4 (58.9) s and 134.2 (79.6) s; 16.9 (1.8) s, 256.2 (62.2) s and 182.5 (74.5) s; and 21.5 (1.5) s, 275.9 (49.3) s and 313.5 (18.0) s, respectively, p < 0.0003 for each experiment. The results for saline at 20 °C were similar. The enFLOW system heated saline above 36 °C faster than the ThermoSens system, whereas the buddy lite often failed to achieve 36 °C.