An IoT and Fog Computing-Based Monitoring System for Cardiovascular Patients with Automatic ECG Classification Using Deep Neural Networks.

Telemedicine and all types of monitoring systems have proven to be a useful and low-cost tool with a high level of applicability in cardiology. The objective of this work is to present an IoT-based monitoring system for cardiovascular patients. The system sends the ECG signal to a Fog layer service by using the LoRa communication protocol. Also, it includes an AI algorithm based on deep learning for the detection of Atrial Fibrillation and other heart rhythms. The automatic detection of arrhythmias can be complementary to the diagnosis made by the physician, achieving a better clinical vision that improves therapeutic decision making. The performance of the proposed system is evaluated on a dataset of 8.528 short single-lead ECG records using two merge MobileNet networks that classify data with an accuracy of 90% for atrial fibrillation.

Chronic exercise impairs nitric oxide pathway in rabbit carotid and femoral arteries.

KEY POINTS: Some of the beneficial effects of exercise in preventing vascular related diseases are mediated by the enhancement of endothelial function where the role of nitric oxide (NO) is well documented, although the relevance of calcium activated potassium channels is not fully understood. The impact of oxidative stress induced by training on endothelial function remains to be clarified. By evaluating different endothelial vasodilator pathways on two vascular beds in a rabbit model of chronic exercise, we found a decreased NO bioavailability and endothelial nitric oxide synthase expression in both carotid and femoral arteries. Physical training induced carotid endothelial dysfunction as a result of an increase in oxidative stress and a reduction in superoxide dismutase expression. In the femoral artery, the lower production of NO was counteracted by an increased participation of large conductance calcium activated potassium channels, preventing endothelial dysfunction. ABSTRACT: The present study aimed to evaluate the effects of chronic exercise on vasodilator response in two different arteries. Rings of carotid and femoral arteries from control and trained rabbits were suspended in organ baths for isometric recording of tension. Endothelial nitric oxide synthase (eNOS), Cu/Zn and Mn-superoxide dismutase (SOD), and large conductance calcium activated potassium (BKCa) channel protein expression were measured by western blotting. In the carotid artery, training reduced the relaxation to ACh (10-9 to 3 × 10-6  m) that was reversed by N-acetylcysteine (10-3  m). l-NAME (10-4  m) reduced the relaxation to ACh in both groups, although the effect was lower in the trained group (in mean ± SEM, 39 ± 2% vs. 28 ± 3%). Physical training did not modify the relaxation to ACh in femoral arteries, although the response to l-NAME was lower in the trained group (in mean ± SEM, 41 ± 5% vs. 17 ± 2%). Charybdotoxin (10-7  m) plus apamin (10-6  m) further reduced the maximal relaxation to ACh only in the trained group. The remaining relaxation in both carotid and femoral arteries was abolished by KCl (2 × 10-2  m) and BaCl2 (3 × 10-6  m) plus ouabain (10-4  m) in both groups. Physical training decreased eNOS expression in both carotid and femoral arteries and Cu/Zn and Mn-SOD expression only in the carotid artery. BKCa channels were overexpressed in the trained group in the femoral artery. In conclusion, chronic exercise induces endothelial dysfunction in the carotid artery as a result of oxidative stress. In the femoral artery, it modifies the vasodilator pathways, enhancing the participation of BKCa channels, thus compensating for the impairment of NO-mediated vasodilatation.