Towards Machine Learning Algorithms in Predicting the Clinical Evolution of Patients Diagnosed with COVID-19

Abstract

Predictive modelling strategies can optimise the clinical diagnostic process by identifying patterns among various symptoms and risk factors, such as those presented in cases of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), also known as coronavirus (COVID-19). In this context, the present research proposes a comparative analysis using benchmarking techniques to evaluate and validate the performance of some classification algorithms applied to the same dataset, which contains information collected from patients diagnosed with COVID-19, registered in the Influenza Epidemiological Surveillance System (SIVEP). With this approach, 30,000 cases were analysed during the training and testing phase of the prediction models. This work proposes a comparative approach of machine learning algorithms (ML), working on the knowledge discovery task to predict clinical evolution in patients diagnosed with COVID-19. Our experiments show, through appropriate metrics, that the clinical evolution classification process of patients diagnosed with COVID-19 using the Multilayer Perceptron algorithm performs well against other ML algorithms. Its use has significant consequences for vital prognosis and agility in measures used in the first consultations in hospitals.

Artificial intelligence applied to analyzes during the pandemic: COVID-19 beds occupancy in the state of Rio Grande do Norte, Brazil

“…As for the deep learning models, SGD showed the best results in terms of accuracy (84.01%), precision (79.57%) and F1score (81.00%), and RMSprop showed the highest recall (84.67%), specificity (84.67%), and ROC-AUC (91.6%). The selection of SGD as the top optimizer for increasing accuracy also appears in the work of Andrade et al (2022), however, it does not converge with the work of Ahsan et al (2020), in which SGD was the worst optimizer selected. Nevertheless, it should be noted that the variability of the data model used to structure the neural network can produce different results, so experimentation with different classifiers is essential to determine the best one.…”

Prioritising Maintenance Work Orders in a Thermal Power Plant: A Multicriteria Model Application

“…In thermal plant operational inspection, other approaches for ranking the criticality of systems include many criteria [51,52]. The study's most pressing problems include incorporating artificial intelligence and machine learning principles to gather requirements, making dynamic determinations of criteria and subcriteria, and integrating the model with integrable systems [53].…”

The economics of deep and machine learning-based algorithms for COVID-19 prediction, detection, and diagnosis shaping the organizational management of hospitals

“…Deep and machine learning algorithms, benchmarking techniques, and predictive modeling tools can configure COVID-19 clinical diagnostic process (Andrade et al, 2022) by detecting disease symptoms and risk factor patterns and predicting patient evolution. Multilayer perceptron, decision tree, and k-nearest neighbor algorithms can shape COVID-19 patient clinical evolution classification, pattern identification and classification, vital prognosis, hospital consultations, and treatment recommendations.…”

“…Support vector machine and naive Bayes algorithms are pivotal in medical image identification, classification, and diagnosis (Andrade et al, 2022), optimizing COVID-19 prediction and screening by clinical decision support for severity risk forecasting. Deep and machine learning algorithms can predict and diagnose COVID-19 clinical evolution through patient signs and symptoms, data classification tasks, and risk factor analysis.…”