Probabilistic survival modeling in health research: an assessment using cohort data from hospitalized patients with COVID-19 in a Latin American city.

Probabilistic survival methods have been used in health research to analyze risk factors and adverse health outcomes associated with COVID-19. The aim of this study was to employ a probabilistic model selected among three distributions (exponential, Weibull, and lognormal) to investigate the time from hospitalization to death and determine the mortality risks among hospitalized patients with COVID-19. A retrospective cohort study was conducted for patients hospitalized due to COVID-19 within 30 days in Londrina, Brazil, between January 2021 and February 2022, registered in the database for severe acute respiratory infections (SIVEP-Gripe). Graphical and Akaike Information Criterion (AIC) methods were used to compare the efficiency of the three probabilistic models. The results from the final model were presented as hazard and event time ratios. Our study comprised of 7,684 individuals, with an overall case fatality rate of 32.78%. Data suggested that older age, male sex, severe comorbidity score, intensive care unit admission, and invasive ventilation significantly increased risks for in-hospital mortality. Our study highlights the conditions that confer higher risks for adverse clinical outcomes attributed to COVID-19. The step-by-step process for selecting appropriate probabilistic models may be extended to other investigations in health research to provide more reliable evidence on this topic.

Machine learning and comorbidity network analysis for hospitalized patients with COVID-19 in a city in Southern Brazil.

The large amount of data generated during the COVID-19 pandemic requires advanced tools for the long-term prediction of risk factors associated with COVID-19 mortality with higher accuracy. Machine learning (ML) methods directly address this topic and are essential tools to guide public health interventions. Here, we used ML to investigate the importance of demographic and clinical variables on COVID-19 mortality. We also analyzed how comorbidity networks are structured according to age groups. We conducted a retrospective study of COVID-19 mortality with hospitalized patients from Londrina, Parana, Brazil, registered in the database for severe acute respiratory infections (SIVEP-Gripe), from January 2021 to February 2022. We tested four ML models to predict the COVID-19 outcome: Logistic Regression, Support Vector Machine, Random Forest, and XGBoost. We also constructed a comorbidity network to investigate the impact of co-occurring comorbidities on COVID-19 mortality. Our study comprised 8358 hospitalized patients, of whom 2792 (33.40%) died. The XGBoost model achieved excellent performance (ROC-AUC = 0.90). Both permutation method and SHAP values highlighted the importance of age, ventilatory support status, and intensive care unit admission as key features in predicting COVID-19 outcomes. The comorbidity networks for old deceased patients are denser than those for young patients. In addition, the co-occurrence of heart disease and diabetes may be the most important combination to predict COVID-19 mortality, regardless of age and sex. This work presents a valuable combination of machine learning and comorbidity network analysis to predict COVID-19 outcomes. Reliable evidence on this topic is crucial for guiding the post-pandemic response and assisting in COVID-19 care planning and provision.

The impact of COVID-19 vaccination on case fatality rates in a city in Southern Brazil.

BACKGROUND: Recent studies have established that vaccination plays a significant role in reducing COVID-19-related deaths. Here, we investigated differences in COVID-19 case fatality rates (CFRs) among vaccinated and unvaccinated populations, and analyzed whether the age composition of confirmed cases has a significant effect on the variations in the observed CFRs across these groups. METHODS: The study considered 59,853 confirmed cases and 1,687 deaths from COVID-19, reported between January 1 to October 20, 2021, by the Health Department of Londrina, a city in Southern Brazil. We used Negative Binomial regression models to estimate CFRs according to vaccination status and age range. RESULTS: There are significant differences between the CFR for fully vaccinated and unvaccinated populations (IRR = 0.596, 95% CI [0.460 - 0.772], P < .001). Vaccinated populations experience fatality rates 40.4% lower than non-vaccinated. In addition, the age composition of confirmed cases explains more than two-thirds of the variation in the CFR between these 2 groups. CONCLUSIONS: Our novel findings reinforce the importance of vaccination as an essential public health measure for reducing COVID-19 fatality rates in all age groups. The results also provide means for accurately assessing differences in CFRs across vaccinated and unvaccinated populations. Such assessment is essential to inform and determine appropriate containment and mitigation interventions in Brazil and elsewhere.