ABSTRACT
The early classification of COVID-19 patients severity can help save lives by giving to doctors valuable instructions and guidelines for the cases that may need more attention to survive. This paper aims to classify cases depending on their severity into three classes: "survivor”, "sudden death” and "death” using electronic health records (HER). The first class represents positive cases discharged from the hospital after being treated for COVID-19. While the second and the third classes are describing the level of cases severity based on the interval of death. We called the highest severity class "sudden death” to identify critical cases with a high risk of death in the first two days of admission, while the "death” class includes severe cases with an interval of death beyond two days. The sudden death class represents the biggest challenge for this classification as the number of samples representing this case is very small. This paper presents a triage system for COVID-19 cases using four machine learning algorithms (KNN, Logistic Regression, SVM, and Decision tree). The best classification results were obtained using Logistic Regression and SVM models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Mathematical epidemiology is one of the most important research areas, it has contributed to understanding the behavior and the impact also the prediction of infectious disease. One of the fundamental methods intended to see the behavior of the pandemic is the susceptible-infectious-recovered epidemic model. However, the deterministic approach of this model has some limitations in mathematical modeling, for that we propose to add a stochastic variation in SIR equations. In this paper we present a stochastic differential equation with jump-diffusion formula for COVID-19, then we estimate the parameters of our stochastic susceptible-infected-recovered model. Finally, we compare our result with real covid19 spread in Morocco. © 2021 IEEE.