The article by Meer et al1 in this issue of JAMA Ophthalmology evaluates a population of 150 252 patients older than 18 years with nonproliferative diabetic retinopathy but without vision-threatening disease. Patient data were gathered from a large commercial and Medicare Advantage database over a 17-year interval from 2002 to 2019. Of these individuals, 5835 had been prescribed fenofibrate as a lipid-lowering agent at baseline. This was a very large, nonrandomized study population, which does not meet the current definition of big data, which involves “…data sets that are too large or complex to be dealt with by traditional data-processing application software.”2 The results of these authors’ analysis showed fenofibrates to be associated with a decreased risk of vision-threatening diabetic retinopathy (hazard ratio [HR], 0.92; 95% CI, 0.87-0.98; P = .01) and proliferative diabetic retinopathy (HR, 0.76; 95% CI, 0.64-0.90; P = .001). Two earlier randomized clinical trials from much smaller groups of participants, the Action to Control Cardiovascular Risk in Diabetes (ACCORD) Eye3 and the Fenofibrate Intervention and Event Lowering in Diabetes (FIELD)4 studies, had shown significant reduction in vision-threatening diabetic retinopathy from the use of fenofibrate. The present report1 is from a much larger, but not population-based, data sample, which makes these results especially noteworthy. Although much larger than the numbers that are usually involved in many clinical trials, or even in some population-based studies, the population size here is impressive, and suggests that fenofibrate may be used as an oral therapy to prevent progression of diabetic retinopathy, for which it has already been approved in Australia.5