Abstract Background Despite clinical practice guideline recommendations to use doxycycline as part of combination therapy for some patients hospitalized with pneumonia, there is minimal evidence supporting this recommendation. Our aim was to examine the association between beta-lactam plus doxycycline and mortality for patients hospitalized with community-acquired pneumonia. Methods We identified patients >65 years of age admitted to any US Department of Veterans Affairs hospital in fiscal years 2002–2012 with a discharge diagnosis of pneumonia. We excluded those patients who did not receive antibiotic therapy concordant with the 2019 American Thoracic Society/Infectious Diseases Society of America (ATS/IDSA) clinical practice guidelines. Using propensity score matching, we examined the association of doxycycline with 30- and 90-day mortality. Results Our overall cohort was comprised of 70533 patients and 5282 (7.49%) received doxycycline. Unadjusted 30-day mortality was 6.4% for those who received a beta-lactam plus doxycycline versus 9.1% in those who did not (P < .0001), and 90-day mortality was 13.8% for those who received a beta-lactam + doxycycline versus 16.8% for those who did not (P < .0001). In the propensity score matched models, both 30- (odds ratio 0.72, 95% confidence interval [CI], .63–.84) and 90-day (0.83, 95% CI, .74–.92) mortality were significantly lower for those who received doxycycline. Conclusions In this retrospective observational cohort study, we found that doxycycline use, as part of guideline-concordant antibiotic therapy, was associated with lower 30- and 90-day mortality than regimens without doxycycline. While this supports the safety and effectiveness of antibiotic regimes that include doxycycline, additional studies, especially randomized clinical trials, are needed to confirm this.