%0 Journal Article
%A Yang, Xinwei
%A Xue, Xiali
%A Zhou, Yuehua
%T Methodological Concerns and Potential Confounding Factors
%B JAMA Ophthalmology
%D 2024
%R 10.1001/jamaophthalmol.2024.1027
%J JAMA Ophthalmology
%@ 2168-6165
%X To the Editor We read with great interest a recent study by Tsang et al titled “Risk of Falls and Fractures in Individuals With Cataract, Age-Related Macular Degeneration, or Glaucoma.” The study contributes valuable insights into the association between major eye diseases and the risk of falls and fractures. However, we have several methodological concerns and suggestions.First, the study’s reliance on data from electronic health records, while comprehensive, may introduce selection bias. Patients who frequently visit health care facilities are more likely to have their falls and fractures recorded, potentially overestimating the risk associated with these eye conditions. Second, the study acknowledges the use of multivariable Cox proportional hazards regression models. However, the reader would benefit if the authors could provide greater detail regarding confounding factors, such as medications, comorbidities, and lifestyle choices that might affect falls, that were used for adjustment in the analysis models. The complexity of the association between eye diseases and falls or fractures is influenced by numerous factors, including medications, comorbidities, and lifestyle choices. Without a thorough understanding of these adjustments, the interpretation of the hazard ratios might be misleading.
%[ 5/20/2024
%U https://doi.org/10.1001/jamaophthalmol.2024.1027