Outcomes of Patients Living with HIV Hospitalized due to COVID-19: A 3-Year Nationwide Study (2020-2022)

Abstract

Scientific reports on the association between human immunodeficiency virus (HIV) in patients with COVID-19 and mortality have not been in agreement. In this nationwide study, we described and analyzed the demographic and clinical characteristics of people living with HIV (PLWH) and established that HIV infection is a risk factor for mortality in patients hospitalized due to COVID-19. We collected data from the National Hospital Data Information System at Hospitalization between 2020 and 2022. We included patients admitted to the hospital with a diagnosis of COVID-19. We established a cohort of patients with PLWH and compared them to patients without HIV (non-PLWH). For multivariate analyses, we performed binary logistic regression, using mortality as the dependent variable. To improve the interpretability of the results we also applied penalized regression and random forest, two well-known machine-learning algorithms. A broad range of comorbidities, as well as sex and age data, were included in the final model as adjusted estimators. Our data of 1,188,160 patients included 6,973 PLWH. The estimated hospitalization rate in this set was between 1.43% and 1.70%, while the rate among the general population was 0.83%. Among patients with COVID-19, HIV infection was a risk factor for mortality with an odds ratio (OR) of 1.25 (95% CI, 1.14-1.37, p < 0.001). PLWH are more likely to be hospitalized due to COVID-19 than are non-PLWH. PLWH are 25% more likely to die due to COVID-19 than non-PLWH. Our results highlight that PLWH should be considered a population at risk for both hospitalization and mortality.

Keywords: COVID.19; HIV; Mortality; Population-based.

Fig. 1

Population pyramid by age range among hospitalized people living with HIV between 2020 and 2022

Fig. 2

Evolution of the pandemic during the observation period regarding people living with HIV

Fig. 3

Lambda values for penalized regression (LASSO). Lambda values represent the penalization of the beta coefficients. Vertical lines represent the range of lambda for which accuracy is not adversely affected. Numbers across the top of the plot represent the number of variables in the model when a certain value of lambda was used (15 versus 3 features). We chose the lambda values that received the minimum number of features without losing accuracy (determined according to mean square error)

Fig. 4

Importance of features based on the random forest algorithm