Wearable Analytics and Early Diagnostic of COVID-19 Based on Two Cohorts

The outbreak of the COVID-19 pandemic forced a need to create screening tests to diagnose the disease. To answer this challenge, this paper introduces the support methodology for COVID-19 early detection based on wearable and machine learning likewise on two various cohorts. We compare the level of detection of the COVID-19 disease, Influenza, and Healthy Control (HC) thanks to the usage of machine learning classifiers likewise changes in heart rate and daily activity. The features obtained as the parameters of the ratio of heart rate to the variable of the number of steps proved to have the highest statistical importance. The COVID-19 cases versus HC were possible to be distinguished with 0.73 accuracy by the XGBoost algorithm, whereas COVID-19 cases, Influenza vs. HC were able to be differentiated on similar level of accuracy: in 0.72 by Support Vector Machine. The multiclass classification between the cases achieved a 0.57 F1-score for three classes by XGBoost. For early diagnosis, this solution could serve as an extra test for clinicians during the pandemic, and the result shows which metric could be useful for creating the machine learning model. © 2022 IEEE.

Diagnosis at early stage Based on smartwatches and machine learning Techniques

Early detection of COVID-19 positive people are now extremely needed and considered to be one of the most effective ways how to limit spreading the infection. Commonly used screening methods are reverse transcription polymerase chain reaction (RT-PCR) or antigen tests, which need to be periodically repeated. This paper proposes a methodology for detecting the disease in non-invasive way using wearable devices and for the analysis of bio-markers using artificial intelligence. This paper have reused a publicly available dataset containing COVID-19, influenza, and Healthy control data. In total 27 COVID-19 positive and 27 healthy control were pre-selected for the experiment, and several feature extraction methods were applied to the data. This paper have experimented with several machine learning methods, such as XGBoost, k-nearest neighbour k-NN, support vector machine, logistic regression, decision tree, and random forest, and statistically evaluated their perfomance using various metrics, including accuracy, sensitivity and specificity. The proposed experiment reached 78 % accuracy using the k-NN algorithm which is significantly higher than reported for state-of-the-art methods. For the cohort containing influenza, the accuracy was 73 % for k-NN. Additionally, we identified the most relevant features that could indicate the changes between the healthy and infected state. The proposed methodology can complement the existing RT-PCR or antigen screening tests, and it can help to limit the spreading of the viral diseases, not only COVID-19, in the non-invasive way. CCBY

Pakistan’s economy: A sign of a blossoming recovery

Pakistan’s economy has seriously affected by COVID-19, which devastated the economic activities and the individuals’ daily lives. This paper discusses some important economic indicators, i.e., GDP growth, inflation, GDP per capita income, entrepreneurship activities and the impacts of the COVID-19 on the economy of Pakistan. Besides, the study highlights the prediction of the upcoming year, taking into consideration of such indicators. This study is a desk review where secondary data is derived from reliable sources. The findings of the study highlight that Pakistan’s economy has been collapsed with different issues. Among these issues, the arrival of the COVID-19 has appeared as a dangerous situation for the economy. It has been devastated all segments of business and individuals’ lives and also entrepreneurship. However, the different predictions regarding Pakistan’s economy claim a massive increase in GDP, per capita income, entrepreneurship activities and inflation decline. In other words, Pakistan’s economy is proving to be a sign of a blossoming recovery in the future. The study's findings would provide some summarized outcomes for policymakers, government agents, and ordinary individuals towards the economy's growth.

Managing COVID-19 Global Pandemic With High-Tech Consumer Wearables: A Comprehensive Review

The novel corona virus (COVID-19) created a havoc all around the globe without any prediction of its eradication. All the previous methods seemed to fail and exceptional considerations are now required to be deployed in order to deal with this pandemic. The aim of this retrospective study is to highlight the new solutions to manage and deal with the pandemic. This study discusses different e-health wearable devices that help in early diagnosis of COVID-19 symptoms and also presents an overview of some artificial intelligence and machine learning techniques applied on CT-scan or Chest X-ray images to refine the correct diagnosis of patients. Finally, this work addresses the importance of smart chat-bots that provides assistance to the people suffering from stress and anxiety during quarantine. These chat-bots can offer psychological therapies in isolation and can be very useful.

Robust technique to detect COVID-19 using chest X-ray images

COVID-19 typically known as Coronavirus disease is an infectious disease caused by a newly discovered coronavirus. Currently detection of coronovirus depends on factors like the patients' signs and symptoms, location where the person lives, travelling history and close contact with any COVID-19 patient. In order to test a COVID-19 patient, a healthcare provider uses a long swab to take a nasal sample. The sample is then tested in a laboratory setting. If person is coughing up then the saliva (sputum), is emitted for testing. The diagnosis becomes even more critical when there is a lack of reagents or testing capacity, tracking the virus and its severity and coming in contact with COVID-19 positive patients by a healthcare practitioner. In this scenario of COVID-19 pendamic, there is a need of streaming diagnosis based on retrospective study of laboratory data in form of chest X-rays using deep learning. This paper proposed a demystify technique to detect COVID-19 using assembling medical images with the help of deep nets. The study shows promising results with accuracy of 91.67% for diagnosis of COVID-19 and 100\% accuracy in proving the survival ratio. © 2020 IEEE.