To the Editor The study of 3 Danish cohorts by Dr Afzal and colleagues1 concluded that the BMI value associated with the lowest all-cause mortality increased by 3.3 in cohorts enrolled from 1976-1978 through 2003-2013. The authors used Cox proportional hazards regression to estimate hazard ratios, with age as the time scale. By doing so, the authors stated that the age differences among the 3 cohorts were automatically adjusted for. However, some concerns about the study design may directly affect the results of the study.
Zhiqiang Wang. Body Mass Index and All-Cause Mortality. JAMA. 2016;316(9):991–992. doi:10.1001/jama.2016.10288