Host and environmental determinants of in-hospital mortality in community-acquired pneumonia: evidence of seasonality, socioeconomic factors, and hospital differentiation in Portugal

Abstract

Background: Community-Acquired Pneumonia (CAP) is regarded as a substantial part of the global burden of disease and a public health priority. In addition to host factors, such as demographic characteristics, comorbidities, CAP clinical severity, and in-hospital mortality may also be influenced by factors such as socioeconomic status, seasonal variations, and hospital differentiation. This study aims to analyse trends in hospital mortality among patients hospitalized with CAP in National Health Service (NHS) hospitals in mainland Portugal and the impact of various host and environmental factors on in-hospital mortality. METHODS: This retrospective cross-sectional study analyzed 378,449 hospitalization episodes with CAP as the primary diagnosis (ICD-9-CM and ICD-10-CM/PCS) in mainland Portugal from 2010 to 2018. Data were sourced from the National Hospital Discharge Database and population census records. Variables included host factors (demographic characteristics, secondary diagnoses, CAP clinical severity indicators, Charlson score) as well as environmental factors, such as seasonality, socioeconomic factors and hospital differentiation. Trend analysis of hospitalization episodes and in-hospital mortality due to CAP was performed. Multivariable logistic regression was used to examine associations with in-hospital mortality, with statistical significance set at p < 0.05.

Results: A decrease in the number of hospitalization episodes and in-hospital mortality rate over time was observed. The regression model identified advanced age, male gender, secondary diagnoses, CAP clinical severity, high Charlson score, the summer season, early school leaving rate, higher unemployment rate, and lower hospital differentiation as factors associated with an increased probability of death (p < 0.001). CONCLUSIONS: Throughout the nine-year period, a steady decline in in-hospital mortality rates was observed. In-hospital mortality exhibited a dual influence, shaped by host factors (such as age, gender, secondary diagnoses, CAP clinical severity, Charlson score) and environmental factors, including the summer season, socioeconomic vulnerability and hospital capabilities. Therefore, effectively reducing CAP in-hospital mortality requires comprehensive policies that focus on at-risk groups and address a broad range of both host and environmental risk factors. These policies should aim to improve healthcare access, increase vaccination coverage, and enhance thermal housing conditions, with particular attention to socially vulnerable individuals.

Keywords: Age factors; Community-Acquired Pneumonia; Comorbidity; Gender; Hospital mortality; Low socioeconomic status; Risk factors; Weather.

Fig. 1

Conceptual model of in-hospital mortality among CAP patients

Fig. 2

Sensitivity Analysis of Seasonality Effects on CAP Mortality (A) Comparison of Adjusted and Sensitivity Analysis Odds Ratios (ORs) for age groups, showing how seasonality modifies mortality risk across different age categories. B Comparison of Adjusted and Sensitivity Analysis ORs for comorbidities (Charlson Score) and hospital differentiation. C Seasonal trends in CAP mortality from 2010 to 2018, displaying yearly mortality fluctuations across Winter, Spring, Summer, and Fall. D Comparison of Poisson and Negative Binomial model predictions, demonstrating that both models yield nearly identical mortality estimates. Error bars represent 95% confidence intervals in (A) and (B), and the dashed diagonal line in (D) represents the perfect agreement between observed and predicted deaths

Fig. 3

Evolution of the number of hospitalization episodes for CAP (A) and in-hospital mortality (B) by age group, between 2010 and 2018

Fig. 4

CAP hospitalizations in-hospital mortality adjusted Odd Ratios by age group, gender, Charlson score, secondary diagnoses, procedures performed, triennium, quarter, early school leaving rate, unemployment rates and hospital service differentiation