ABSTRACT
This paper analyses the possibilities of using Machine learning to develop a forecasting model for COVID-19 with a publicly available dataset from the Johns Hopkins University COVID-19 Data Repository and with the addition of a percentage of each variant from the GISAID Variant database. Genetic programming (GP), a symbolic regressor algorithm, is used for the estimation of new confirmed infected cases, hospitalized cases, cases in intensive care units (ICUs), and deceased cases. This metaheuristics method algorithm was used on a dataset for Austria and neighboring countries Czechia, Hungary, Slovenia, and Slovakia. Machine learning was done to create individual models for each country. Variance-based sensitivity analysis was initiated using the obtained mathematical models. This analysis showed us which input variables the output of the obtained models is sensitive to, like in the case of how much each covid variant affects the spread of the virus or the number of deceased cases. Individual short-term models have achieved very high R2 scores, while long-term predictions have achieved lower R2 scores. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
The respiratory system has been mainly analyzed using experimental procedures. With technological development, new opportunities have been created to analyze the respiratory system using noninvasive procedures, such as numerical methods. Numerical methods have allowed researchers to obtain important information about minimally invasive procedure. It also allows to analyze diseases such as asthma, chronic obstructive pulmonary disease, lung cancer, pulmonary fibrosis, COVID-19, etc. The results obtained by these methods can be used to correlate with experimental data and to further improve treatments of patients. © 2022 Elsevier Inc. All rights reserved.
ABSTRACT
Since the novel SARS-CoV-2 virus appeared, interest in developing epidemiological mechanisms that would help in prevention of its spread has increased. Epidemiological models are the most important mechanisms for examining the spread of the virus. For that purpose, we propose deep learning approach, LSTM neural network model. LSTM is a special kind of neural network structure capable of learning long-term dependencies in sequence prediction problems. The model was fed with official statistical data available online for Belgium in the period of March 15th, 2020 to March 15th, 2021. Results show that LSTM is capable of predicting in long-term manner with the low values of RMSE and MAE. Higher values of RMSE and MAE are observed in the infected cases (RMSE was 397.23 and MAE was 315.35) which is expected due to thousands of infected people per day in Belgium. In future studies, we will include more phenomena, especially medical intervention and asymptomatic infection, in order to better describe the COVID-19 spread and development.
ABSTRACT
The year 2020 has been marked by the coronavirus disease 2019 (COVID-19) pandemic, caused by an RNA virus called SARS-COV2 (severe acute respiratory syndrome coronavirus). The fight against this epidemic has become the center of our daily clinical practice as well as of our private lives, in which avoiding infection has become one of our most important goals. Even though COVID-19 is a potentially lethal disease, especially for the elderly and people with chronic diseases, it did not cause all the other life-threatening diseases to vanish. On the contrary, many scheduled medical activities and procedures, especially preventive and non-urgent internal and surgical activities, had to be postponed due to COVID-19 crisis. This interruption in the health care system can negatively affect the diagnosis and management of our patients with other health issues, namely malignant skin tumors, of which melanoma is the most aggressive. In this letter, we as dermatovenereologists from the Croatian Referral Centre of The Ministry of Health for Melanoma needed to express our concern regarding the increasing number of patients with delayed diagnosis of skin cancer, with special emphasis on melanoma detection and treatment. In the last few months, a large number of our newly-diagnosed patients with melanoma, as well as those with non-melanoma skin cancers, reported that they had noticed a suspicious skin lesion a few months ago but decided not to seek help from dermatologist due to the worrisome epidemiologic situation. In the current environment, clinical skin examination may be viewed as less important and thus postponed, but neglecting melanoma throughout the virus outbreak may lead to increased rates of morbidity, mortality, and consequently a greater financial burden for the health system (1). There are several reasons for such a relaxed attitude towards skin health in our patients. Unlike cardiac, pulmonary, or digestive difficulties, which patients consider life-threatening and for which they seek emergency care despite the coronavirus pandemic, skin tumors do not cause great subjective or significantly noticeable objective symptoms. Moreover, all of the skin tumors and especially melanoma , mostly present as small changes of just a few millimeters in diameter in the early stage at which they are prognostically most favorable. For the average person with no medical education, such small lesions usually do not cause any concern as they have no awareness of the fact that small and inconspicuous skin lesions may be dangerous and potentially even lethal. According to the recommendations concerning patient management during COVID-19 pandemic, oncological examinations should still be performed regularly (2). In spite of that, the cancelation of appointments, especially by patients who are being monitored for high-risk lesions, is inevitable when COVID-19 is disrupting everyone's lives. With the pandemic evolving and no clear solutions in sight, now is the time to emphasize the importance of self-examination and teledermatology in early melanoma diagnosis. Even though diagnosing and managing pigmented skin lesions usually requires face-to-face examinations and dermoscopy as a crucial tool in early melanoma detection, in these times, and especially for people with a higher risk of SARS-COV2 infection, remote communication could prevent delays resulting in worse prognosis and could also eliminate the risk of infecting healthcare workers. Moreover, teledermatology can also be initiated by doctors asking patients to monitor lesions between clinical visits (3). However, we should not rely solely on this technology but should instead assess every patient individually and insist on a face-to-face examination for those at greater risk, with the aim that, if necessary, surgery be performed in timely manner. The collaboration between general practitioners and dermatologists represents an important aspect of achieving the most rational and effective health care in terms of performing triage of patients who can be assessed by teledermatology as
ABSTRACT
COVID-19 is one of the greatest challenges humanity has faced recently, forcing a change in the daily lives of billions of people worldwide. Therefore, many efforts have been made by researchers across the globe in the attempt of determining the models of COVID-19 spread. The objectives of this review are to analyze some of the open-access datasets mostly used in research in the field of COVID-19 regression modeling as well as present current literature based on Artificial Intelligence (AI) methods for regression tasks, like disease spread. Moreover, we discuss the applicability of Machine Learning (ML) and Evolutionary Computing (EC) methods that have focused on regressing epidemiology curves of COVID-19, and provide an overview of the usefulness of existing models in specific areas. An electronic literature search of the various databases was conducted to develop a comprehensive review of the latest AI-based approaches for modeling the spread of COVID-19. Finally, a conclusion is drawn from the observation of reviewed papers that AI-based algorithms have a clear application in COVID-19 epidemiological spread modeling and may be a crucial tool in the combat against coming pandemics.
ABSTRACT
A unique feature of COVID-19 interstitial pneumonia is an abrupt progression to respiratory failure. Our calculation shows that this abrupt deteriorate may be caused by a sudden shift in the spread of virus-laden bioaerosols through the airways to many different regions of the lungs from the initial site of infection.