Résumé
Purpose: In December 2019, the Covid-19 pandemic began in the world. To reduce mortality, in addiction to mass vaccination, it is necessary to massify and accelerate clinical diagnosis, as well as creating new ways of monitoring patients that can help in the construction of specific treatments for the disease. Objective: In this work, we propose rapid protocols for clinical diagnosis of COVID-19 through the automatic analysis of hematological parameters using evolutionary computing and machine learning. These hematological parameters are obtained from blood tests common in clinical practice. Method: We investigated the best classifier architectures. Then, we applied the particle swarm optimization algorithm (PSO) to select the most relevant attributes: serum glucose, troponin, partial thromboplastin time, ferritin, D-dimer, lactic dehydrogenase, and indirect bilirubin. Then, we assessed again the best classifier architectures, but now using the reduced set of features. Finally, we used decision trees to build four rapid protocols for Covid-19 clinical diagnosis by assessing the impact of each selected feature. The proposed system was used to support clinical diagnosis and assessment of disease severity in patients admitted to intensive and semi-intensive care units as a case study in the city of Paudalho, Brazil. Results: We developed a web system for Covid-19 diagnosis support. Using a 100-tree random forest, we obtained results for accuracy, sensitivity, and specificity superior to 99%. After feature selection, results were similar. The four empirical clinical protocols returned accuracies, sensitivities and specificities superior to 98%. Conclusion: By using a reduced set of hematological parameters common in clinical practice, it was possible to achieve results of accuracy, sensitivity, and specificity comparable to those obtained with RT-PCR. It was also possible to automatically generate clinical decision protocols, allowing relatively accurate clinical diagnosis even without the aid of the web decision support system. © 2023, The Author(s), under exclusive licence to The Brazilian Society of Biomedical Engineering.
Résumé
In December 2019 an outbreak of a new disease happened, in Wuhan city, China, in which the symptoms were very similar to pneumonia. The disease was attributed to SARS-CoV-2 as the infectious agent and it was called the new coronavirus or Covid-19. In March 2020, the World Health Organization declared a worldwide pandemic of the new coronavirus. We have already counted more than 110 million cases and almost 2.5 million deaths worldwide. In order to assist in decision-making to contain the disease, several scientists around the world have engaged in various efforts, and they have proposed a lot of systems and solutions for tracking, monitoring, and predicting confirmed cases and deaths from Covid-19. Mathematical models help to analyze and understand the evolution of the disease, but understanding the disease was not enough, it was necessary to understand the problem in a quantitative way to lead the decision-making during the pandemic. Several initiatives have made use of Artificial Intelligence, and models were designed using machine learning algorithms with features for temporal and spatio-temporal investigation and prediction of cases of Covid-19. Among the algorithms used are Support Vector Machine (SVM), Random Forest, Multilayer Perceptron (MLP), Graph Neural Networks (GNNs), Ecological Niche Models (ENMs), Long-Short Term Memory Networks (LSTM), linear regression, and others. And these had good results, and to analyze them, the Root Mean Squared Error (RMSE), Log Root Mean Squared Error (RMSLE), correlation coefficient, and others were used as metrics. Covid-19 presents a huge problem to public health worldwide, so it is of utmost importance to investigate it, and with these two approaches it is possible to track not only how the disease evolves but also to know which areas are at risk. And these solutions can help in supporting decision-making by health managers to make the best decisions for the disease that is in the outbreak. This chapter aims to present a literature review and a brief contribution to the use of machine learning methods for temporal and spatio-temporal prediction of Covid-19, using Brazil and its federative units as a case study. From canonical methods to deep networks and hybrid committee-based, approaches will be investigated. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
Résumé
Multifrequency electrical impedance tomography (MfEIT) is a technique that allows the visualization of images inside the body through the characterization of electrical impedance, conductivity or permissiveness in a given frequency range, as well as the characterization of body tissue analyzed. Usually, several alternating electrical currents are injected through electrodes connected to the surface of the body under study, and the resulting voltages are measured and stored for processing and obtaining an image. The image reconstruction algorithm uses the data set of measurements of applied currents and voltages measured at each electrode, calculating the distributions of conductivity, permittivity, or resistivity within the conductive volume studied. The reconstruction of images by direct methods is widely used in applications that require rapid reconstruction and lower computational cost, such as the monitoring of pulmonary mechanical ventilation in ICU beds in patients intubated due to COVID-19. In this chapter, we present the basic characteristics so that a wireless, low-cost, and portable MfEIT system can be implemented, as well as the definitions and modeling of the two-dimensional D-bar method for image reconstruction. Clinical parameters of patients diagnosed with COVID-19 are used to implement some reconstructions of images, as well as to bring a discussion about the efficiency of this technology for this clinical condition. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
Résumé
This book comprehensively covers the topic of COVID-19 and other pandemics and epidemics data analytics using computational modelling. Biomedical and Health Informatics is an emerging field of research at the intersection of information science, computer science, and health care. The new era of pandemics and epidemics bring tremendous opportunities and challenges due to the plentiful and easily available medical data allowing for further analysis. The aim of pandemics and epidemics research is to ensure high-quality, efficient healthcare, better treatment and quality of life by efficiently analyzing the abundant medical, and healthcare data including patient's data, electronic health records (EHRs) and lifestyle. In the past, it was a common requirement to have domain experts for developing models for biomedical or healthcare. However, recent advances in representation learning algorithms allow us to automatically learn the pattern and representation of the given data for the development of such models. Medical Image Mining, a novel research area (due to its large amount of medical images) are increasingly generated and stored digitally. These images are mainly in the form of: computed tomography (CT), X-ray, nuclear medicine imaging (PET, SPECT), magnetic resonance imaging (MRI) and ultrasound. Patients' biomedical images can be digitized using data mining techniques and may help in answering several important and critical questions related to health care. Image mining in medicine can help to uncover new relationships between data and reveal new and useful information that can be helpful for scientists and biomedical practitioners. Assessing COVID-19 and Other Pandemics and Epidemics using Computational Modelling and Data Analysis will play a vital role in improving human life in response to pandemics and epidemics. The state-of-the-art approaches for data mining-based medical and health related applications will be of great value to researchers and practitioners working in biomedical, health informatics, and artificial intelligence. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.