The objective of this study was to evaluate the feasibility of ATA category 2 Web-based screening for diabetic retinopathy in a primary care population in the Netherlands. A total of 1,676 patients in a primary care setting, with diabetes, without known diabetic retinopathy, and without previous screening by an ophthalmologist, were included between January 1 and December 31, 2003. Patients underwent a brief questionnaire and two field retinal photography. Photographs were independently read by two ophthalmologists. Outcome measures were gradability of the photographs, need for pharmacologic pupil dilation, assessment as suspect for presence of diabetic retinopathy, of neovascularization and of diabetic retinopathy, and agreement between graders. Of the population studied, 11.3% of patients required pupil dilation, average transmission time of images was 73 sec, 12.0% of patients had ungradable photographs, 10.4% of the patients with gradable photographs were assessed as "suspect for diabetic retinopathy," and 2.0% were assessed to need urgent referral. Red lesions were present in 3.5% and bright lesions were present in 1.6% of all gradable patients. Neovascularization of the disk was found in one patient. Type 1 patients had much higher rates of "suspect for diabetic retinopathy" (34.5%) than type 2 patients (9.4%). Interrater agreement kappa was 0.93. Web-based screening, using open source technology and uncompressed images, is feasible in a primary care setting, with a high rate of inter-rater agreement. Dilate-as-needed may be a sensible approach for retinal photography. The high incidence of "suspect for diabetic retinopathy" in type 1 diabetes patients illustrates that web-based diabetic retinopathy screening programs for these patients may detect diabetic retinopathy that would otherwise have gone undetected.