Current forecast of COVID-19 in Mexico: A Bayesian and machine learning approaches

Abstract

The COVID-19 pandemic has been widely spread and affected millions of people and caused hundreds of deaths worldwide, especially in patients with comorbilities and COVID-19. This manuscript aims to present models to predict, firstly, the number of coronavirus cases and secondly, the hospital care demand and mortality based on COVID-19 patients who have been diagnosed with other diseases. For the first part, I present a projection of the spread of coronavirus in Mexico, which is based on a contact tracing model using Bayesian inference. I investigate the health profile of individuals diagnosed with coronavirus to predict their type of patient care (inpatient or outpatient) and survival. Specifically, I analyze the comorbidity associated with coronavirus using Machine Learning. I have implemented two classifiers: I use the first classifier to predict the type of care procedure that a person diagnosed with coronavirus presenting chronic diseases will obtain (i.e. outpatient or hospitalised), in this way I estimate the hospital care demand; I use the second classifier to predict the survival or mortality of the patient (i.e. survived or deceased). I present two techniques to deal with these kinds of unbalanced datasets related to outpatient/hospitalised and survived/deceased cases (which occur in general for these types of coronavirus datasets) to obtain a better performance for the classification.

Reported Adverse Effects and Attitudes among Arab Populations Following COVID-19 Vaccination: A Large-Scale Multinational Study Implementing Machine Learning Tools in Predicting Post-Vaccination Adverse Effects Based on Predisposing Factors

“…On the other hand, recent years have witnessed a runaway increase in the involvement of promising machine learning (ML) approaches in the field of medicine, from basic medical sciences research, to clinical decision-making [ 37 , 38 ]. Several studies have employed a variety of potential ML algorithms for the understanding of the nature of SARS-CoV-2 and its transmission dynamics [ 39 , 40 ], forecasting pandemic scenarios [ 41 , 42 ], predicting COVID-19 diagnosis and prognosis [ 43 ], drug repurposing [ 44 ], and vaccine development against COVID-19 [ 45 ], as well as for predicting COVID-19 vaccination willingness [ 46 ] and post-vaccination side effects [ 13 ]. Interestingly, for the post-vaccination stage, a few studies have utilized ML applications to build predictive models for the reactogenicity and morbidity incidences, and for the severity of side effects following COVID-19 vaccination [ 13 , 47 ].…”

Inference on a Multi-Patched Epidemic Model with Partial Mobility, Residency and Demography: The Case of 2020 COVID-19 Outbreak in Hermosillo, Mexico

“…COVID-19 which so far has a death toll of 6.6 Million and confirmed cases of 633 Million (less than 10% of total human population) [13]. However, the urgency in the need for more research on COVID-19 and other infectious diseases is qualified by the warnings from scientists in the recent past about the likelihood of another pandemic striking at any moment [14]. These studies seek understanding the dynamics of the infection propagation, control and mitigation and include but are not limited to model selection, statistical inference, uncertainty quantification and prediction using empirical epidemiological data.…”

“…Once an appropriate epidemic model has been formulated, a myriad of analysis relevant to epidemiologists, policy makers and public health officials can be conducted. These include but are not limited to theoretical analysis and numerical simulations (see e.g., [39,40,[45][46][47]), inference, uncertainty quantification and predictions using empirical data (see e.g., [14,[48][49][50][51][52]). Most studies modelling population mobility and the spread of infectious diseases, particularly using meta-population-multi-patched models, have tended to focus on theoretical and global properties and numerical simulations of such models.…”

Supervised Learning Models for the Preliminary Detection of COVID-19 in Patients Using Demographic and Epidemiological Parameters

“…The article concluded that neural networks could easily outperform conventional machine earning algorithms. Prieto [50] used the Mexican dataset to forecast COVID-19 using ML and Bayesian approaches. Parameter estimation techniques were used in the beginning.…”