An Extended Weibull Regression for Censored Data: Application for COVID-19 in Campinas, Brazil

Abstract

This work aims to study the factors that increase the risk of death of hospitalized patients diagnosed with COVID-19 through the odd log-logistic regression model for censored data with two systematic components, as well as provide new mathematical properties of this distribution. To achieve this, a dataset of individuals residing in the city of Campinas (Brazil) was used and simulations were performed to investigate the accuracy of the maximum likelihood estimators in the proposed regression model. The provided properties, such as stochastic representation, identifiability, and moments, among others, can help future research since they provide important information about the distribution structure. The simulation results revealed the consistency of the estimates for different censoring percentages and show that the empirical distribution of the modified deviance residuals converge to the standard normal distribution. The proposed model proved to be efficient in identifying the determinant variables for the survival of the individuals in this study, which can help to find more opportune treatments and medical interventions. Therefore, the new model can be considered an interesting alternative for future works that evaluate censored lifetimes.

Weibull Regression Model on Hospitalization Time Data of COVID-19 Patients at Abdul Wahab Sjahranie Hospital Samarinda

“…Pada penelitian ini akan dilakukan pemodelan Regresi Weibull pada data COVID-19 di RSUD Abdul Wahab Sjahranie Samarinda. Penelitian mengenai Regresi Weibull yang diaplikasikan pada data COVID-19 juga dilakukan di Campinas, Brazil [14]. Selain itu, dengan menggunakan metode yang sama juga dilakukan penelitian mengenai faktor yang memengaruhi pasien COVID-19 di rumah sakit Al-Shiffa Kota Mosul, Irak [18].…”

Influence Diagnostic in Log-Exponential-Inverse- Exponential {Weibull} Regression Failure Model

“…We can write the model ( 4) as a log-linear model (6) where is a variable with density function (7) and hazard function where , and…”

“…Now, suppose that the scale parameter of the EIEW distribution depends on the matrix of explanatory variables , as: Also, suppose that the regression model based on EIEW distribution given in (6) relates the response variable and the covariate vector . Hence, the conditional dependence of can be expressed as (8) where is the explanatory vector, , are unknown parameters and is a variable with the distribution function in (7).…”

“…A location-scale regression model has been commonly used in clinical trials, and has been discussed by many researchers. These include log-Burr XII regression models by [1], a log-extended Weibull regression model by [2], the log-Burr XII regression model for grouped survival data by [3], the log-generalized modified Weibull regression model by [4], the Marshall-Olkin truncated Poisson Weibull regression model by [5], an extended Weibull regression model by [6], the log-beta Weibull regression model by [7,8] proposed two new regressions, one is parametric and the other is partially linear based on an extended Birnbaum-Saunders distribution, and [9] defined a class of survival models for modeling time-to-event with long-term and obtained some of its structural properties. Also, [10] introduced and study the log-odd log-logistic Weibull (LOLLW) distribution and constructed the LOLLW regression model to investigate the informative censoring mechanism in a type of location-scale regression model, [11] introduced the generalized odd log-logistic flexible Weibull regression model, [12] proposed the heteroscedastic log-odd log-logistic generalized gamma (LOLLGG) regression model for censored data, [13] introduced the logit exponentiated power exponential regression model, [14] proposed the generalized odd log-logistic Maxwell semiparametric regression model which is very flexible for modeling response variable with positive support, [15] introduced a new regression based on the odd log-logistic Marshall-Olkin normal distribution, and [16] proposed two different zero-inflated-rightcensored regression models, assuming Weibull and gamma distributions.…”

Developing an interpretable machine learning model for predicting COVID-19 patients deteriorating prior to intensive care unit admission using laboratory markers

“…Analysis of pre-existing comorbidities has been proven to be valuable in predicting COVID-19 outcomes [8] , [39] , [40] , diagnosis [10] , even in survival analysis on censored data [41] . However, their applicability might be hampered due to the fact that: i) comorbidities prevalence varies along countries and regions [42] due to socio-political factors, health equity issues, and environmental threats [43] , [44] ; ii) there are discrepancies and variability in data collection systems as well as in the version of international classification of diseases (ICD) used across different institutions and countries, hindering meaningful comparison or introducing research bias [42] , [45] by producing skewed results as a consequence of the relationship between some comorbidities and death rates [46] ; iii) inclusion of pre-existing comorbidities analysis is required [37] ; iv) Achieving a high level of digital transformation maturity is necessary [42] , [47] to ensure models robustness and usability.…”