RESUMEN
Novel coronavirus (COVID-19) has become a global problem in recent times due to the rapid spread of this disease. Almost all the countries of the world have been affected by this pandemic that made a major consequence on the medical system and healthcare facilities. The healthcare system is going through a critical time because of the COVID-19 pandemic. Modern technologies such as deep learning, machine learning, and data science are contributing to fight COVID-19. The paper aims to highlight the role of machine learning approaches in this pandemic situation. We searched for the latest literature regarding machine learning approaches for COVID-19 from various sources like IEEE Xplore, PubMed, Google Scholar, Research Gate, and Scopus. Then, we analyzed this literature and described them throughout the study. In this study, we noticed four different applications of machine learning methods to combat COVID-19. These applications are trying to contribute in various aspects like helping physicians to make confident decisions, policymakers to take fruitful decisions, and identifying potentially infected people. The major challenges of existing systems with possible future trends are outlined in this paper. The researchers are coming with various technologies using machine learning techniques to face the COVID-19 pandemic. These techniques are serving the healthcare system in a great deal. We recommend that machine learning can be a useful tool for proper analyzing, screening, tracking, forecasting, and predicting the characteristics and trends of COVID-19.
RESUMEN
Coronavirus disease 2019 in short COVID-19 is a contagious disease caused by coronavirus SARS-CoV-2, which has caused a global pandemic and still infecting millions around the globe. COVID-19 has made an enormous impact on everybody's day-to-day life. One of the main strengths of COVID-19 is its extraordinary infectious capability. Early detection systems can thus play a big role in curbing the exponential growth of COVID-19. Some medical radiography techniques, such as chest X-rays and chest CT scans, are used for fast and reliable detection of coronavirus-induced pneumonia. In this paper, we propose a histogram of oriented gradients and deep convolutional network-based model that can find out the specific abnormality in frontal chest X-ray images and effectively classify the data into COVID-19 positive, pneumonia positive, and normal classes. The proposed system performed effectively in terms of various performance measures and proved capable as an effective early detection system.
RESUMEN
BACKGROUND: Widal test is the most widely used laboratory investigation for diagnosis of typhoid. However, the test interpretation remains controversial in the context of endemic regions such as Bangladesh, as agglutination occurs at varied titrations among a large percentage of healthy population. Paired Widal tests are often not feasible; hence single unpaired test has to be used for screening, diagnosis and treatment. OBJECTIVE: We aimed to assess the normal range of baseline titre for Anti TO, TH, AO, AH, BO agglutinins among healthy population in an endemic country with a view to guide the researchers and the clinicians, facilitating further investigation on updating cut off points of single Widal test for screening and diagnosis of typhoid fever in the context of Bangladesh. METHODS: A cross-sectional study was carried out in Mymensingh Medical College, Bangladesh on 2925 male immigration applicants. A single blood sample was collected for Widal test and interpreted using standard guidelines. RESULTS: The highest baseline titer for Anti TO, TH, AO, AH, BO agglutinins among 95% of the healthy participants was found to be 1:80 for each respectively. A titre of 1: 40 was observed for BH antigen. CONCLUSION: In case of singular Widal test, baseline values for the normal range was found to be 1:20 - 1:80 for all the antigens (TO, TH, AO, AH, BO, BH), except BH, for which it was 1:20-1:40. Further studies, inclusive of other sociodemographic groups and positive controls are required to determine the updated cut off values.