Epidemiology and long-term clinical and biologic risk factors for pneumonia in community-dwelling older Americans: analysis of three cohorts

Abstract

Background: Preventing pneumonia requires better understanding of incidence, mortality, and long-term clinical and biologic risk factors, particularly in younger individuals.

Methods: This was a cohort study in three population-based cohorts of community-dwelling individuals. A derivation cohort (n = 16,260) was used to determine incidence and survival and develop a risk prediction model. The prediction model was validated in two cohorts (n = 8,495). The primary outcome was 10-year risk of pneumonia hospitalization.

Results: The crude and age-adjusted incidences of pneumonia were 6.71 and 9.43 cases/1,000 person-years (10-year risk was 6.15%). The 30-day and 1-year mortality were 16.5% and 31.5%. Although age was the most important risk factor (range of crude incidence rates, 1.69-39.13 cases/1,000 person-years for each 5-year increment from 45-85 years), 38% of pneumonia cases occurred in adults < 65 years of age. The 30-day and 1-year mortality were 12.5% and 25.7% in those < 65 years of age. Although most comorbidities were associated with higher risk of pneumonia, reduced lung function was the most important risk factor (relative risk = 6.61 for severe reduction based on FEV1 by spirometry). A clinical risk prediction model based on age, smoking, and lung function predicted 10-year risk (area under curve [AUC] = 0.77 and Hosmer-Lemeshow [HL] C statistic = 0.12). Model discrimination and calibration were similar in the internal validation cohort (AUC = 0.77; HL C statistic, 0.65) but lower in the external validation cohort (AUC = 0.62; HL C statistic, 0.45). The model also calibrated well in blacks and younger adults. C-reactive protein and IL-6 were associated with higher pneumonia risk but did not improve model performance.

Conclusions: Pneumonia hospitalization is common and associated with high mortality, even in younger healthy adults. Long-term risk of pneumonia can be predicted in community-dwelling adults with a simple clinical risk prediction model.

Figure 1.

Proportion of pneumonia cases and crude incidence rates across different age groups.

Figure 2.

Model discrimination (using AUC) and calibration (using HL C statistic) for the pneumonia clinical risk prediction model in the derivation, internal validation, and external validation cohorts. AUC = area under curve; HL = Hosmer-Lemeshow.

Figure 3.

Proportion of pneumonia cases and the proportion of population that would have to be targeted using different thresholds of the clinical risk prediction model in the external validation cohort. To illustrate a strategy of targeting a more select population, such as those with risks of > 10%, would require treating approximately one-third of the population and identify one-half of pneumonia cases. Targeting only high-risk participants (> 15% risk) or 14% of the population would identify one-fourth of pneumonia cases, a subgroup that could be targeted initially to conduct randomized clinical trials to test pharmacologic interventions cost-effectively.