Feasibility and reliability of whintings scanwatch to record 4-lead Electrocardiogram: A comparative analysis with a standard ECG.

The recent technological advances allowed us to produce some new wearable devices, such as smartphones and smartwatches (SW). These devices provide different services to their users through different software applications installed even in the SW or smartphones. Health monitoring functionalities, among these services, are nowadays the new technological fashion. In fact, the monitoring is ensured by the sensor incorporated in the SW. The SW allows the record of only one single lead Electrocardiogram (ECG), which is sufficient to screen or diagnosis of rhythm and conduction disorders, especially during the onset of cardiac symptoms, but insufficient for the detection of ischemic disease and cardiomyopathies. In this context, this paper aims to evaluate the feasibility, and reliability of a SW to obtain ECG recordings in comparison with a standard ECG. For that purpose, 140 patients were recruited for this analysis. At the first step, the 12 lead ECG followed with four lead SW-ECG; using the Withings Scanwatch device, were recorded in the same resting conditions. The four lead SW-ECG consists of Einthoven DI lead recorded with the SW, where the SW was on the left wrist and the right index finger on the crown, and three Wilson-type leads, in the which the V1 was recorded in the fourth right parasternal intercostal space, V3 was recorded in the fifth intercostal space on the midclavicular line, and V6 was recorded in the fifth intercostal space on the left midaxillary line with the right index finger placed on the crown and the left hand encompassing the right wrist. 700 ECGs recordings were collected and statistically analyzed in this study. In total, 97 % of the patients were able to obtain an ECG through the SW. A strong correlation was observed between the two recording methods concerning the duration of the studied parameters (r >90 %). The correlation coefficient showed that 33 out of 44 parameters have a strong correlation with the standard ECG. The similarity of the combined leads in the 4 established subgroups was significantly higher, meaning that increasing the number of leads would improve the detection of electrical anomalies. Our findings confirm the existing data on the high similarity between SW and standard 12-leads ECG. Despite SW not having the accuracy and utility of the standard ECG machine, they should be considered as an interesting screening tool for cardiac rhythm disorders, and a compelling solution to electrical documentation of general cardiac symptoms.

On the Implementation of a Post-Pandemic Deep Learning Algorithm Based on a Hybrid CT-Scan/X-ray Images Classification Applied to Pneumonia Categories.

The identification and characterization of lung diseases is one of the most interesting research topics in recent years. They require accurate and rapid diagnosis. Although lung imaging techniques have many advantages for disease diagnosis, the interpretation of medial lung images has always been a major problem for physicians and radiologists due to diagnostic errors. This has encouraged the use of modern artificial intelligence techniques such as deep learning. In this paper, a deep learning architecture based on EfficientNetB7, known as the most advanced architecture among convolutional networks, has been constructed for classification of medical X-ray and CT images of lungs into three classes namely: common pneumonia, coronavirus pneumonia and normal cases. In terms of accuracy, the proposed model is compared with recent pneumonia detection techniques. The results provided robust and consistent features to this system for pneumonia detection with predictive accuracy according to the three classes mentioned above for both imaging modalities: radiography at 99.81% and CT at 99.88%. This work implements an accurate computer-aided system for the analysis of radiographic and CT medical images. The results of the classification are promising and will certainly improve the diagnosis and decision making of lung diseases that keep appearing over time.

An experimental method for diagnostic of incipient broken rotor bar fault in induction machines.

Induction Motors (IMs) have multiple advantages, as they are robust and easy to maintain. A small fault in a single rotor bar could cause the break of this bar, subsequently breaking a large adjacent bar number because of the oscillations created by the unbalance of the rotor. For this reason, early detection of any small failure is recommended to remove some posterior damage and the maintenance expenses. This work proposes a new and original method that uses the cyclostationnarity of the electrical signal instead of the vibratory signal to detect the incipient failure. The experimental data has been manipulated. The results prove that this new designed strategy can identify and classify the level of cracking that occurs in a single rotor bar, even under various loads.

An efficient approach based on 3D reconstruction of CT scan to improve the management and monitoring of COVID-19 patients.

PURPOSE: To reconstruct a 3D visualization from CT images of COVID-19 patients in order to improve understanding of the disease for better management and follow-up. MATERIALS AND METHODS: We have retrieved CT images of 185 COVID-19 patients from the Cheikh Zaid International University Hospital in Rabat, Morocco. We then performed computer processing that allowed us to obtain a 3D visualization of these patients. RESULTS: In this article, we have chosen to do 3D reconstruction of three specific cases among 185 patients:- Cases (A1, A2) which are negative RT-PCR patient with normal CT images.- Cases (B1, B2) which are positive RT-PCR patient with abnormal CT images.- Case (C) which is a negative RT-PCR patient with CT abnormalities.To improve our results and have a better quality of the 3D reconstruction, we used different algorithms and a specific row data processing. CONCLUSION: 3D reconstruction has a significant role in the diagnosis and management of COVID-19 patients. The quality and reliability of 3D reconstructions allow the clinician to make a quick and efficient diagnosis and avoid an eventual false negative (produced by the RT-PCR test). We suggest including chest 3D reconstruction in the patient management and prognosis evaluation.