To the Editor Gomm and colleagues1 examine the association of proton pump inhibitor (PPI) use with the risk for incidental dementia in the elderly population. Using longitudinal data derived from the Allgemeine Ortskrankenkassen database, the largest German health insurer, the authors conclude that patients receiving regular PPIs were at significantly higher risk for developing incidental dementia (hazard ratio, 1.44; 95% CI, 1.36-1.52; P < .001) compared with patients who did not receive PPIs. Despite obvious merits in the study design and the structure of the database, the analysis should be interpreted with caution.