New tool emerges to predict risk of vision loss due to diabetic retinopathy


The future risk of developing new vision-threatening diabetic retinopathy, diabetic macular edema, and proliferative diabetic retinopathy can be predicted using the patient’s retinopathy status and hemoglobin A1c value.

Reviewed by Bobeck S. Modjtahedi, MD.

Investigators from Kaiser Permanente Southern California’s Eye Monitoring Center and Department of Research and Evaluation have reported the accuracy of a new tool to predict the 3-year risk of vision-threatening diabetic retinopathy (VTDR) in patients with type 2 diabetes mellitus. Bobeck Modjtahedi, MD, the lead author of the study, reported that the future risk of developing new VTDR, diabetic macular edema (DME), and proliferative DR (PDR) can be predicted using the patient’s retinopathy status and hemoglobin A1c assess.

The researchers believe this tool will prove valuable for more targeted monitoring and therapeutic intervention in patients with type 2 diabetes in an effort to prevent vision loss.

Retrospective cohort study

This search included patients aged 18 years and older who had been screened for DR from 2012 to 2015. Treatment-naïve patients were also required to have no history of DME, PDR, or other exudative macular vascular disease or retinal.

The investigators identified 215,154 patients who met the study inclusion criteria. Over 20 potential predictors of VTDR, defined as DME and/or PDR based on diagnostic codes with concurrent retinal intervention, were reviewed for inclusion in the model.

3-year risk prediction models of VTDR, DME and PDR were developed and validated.

Prediction model performance

The 215,154 patients had an average age of 60 years and 54% were women, about a third were Caucasian and 40% Hispanic.

The final models developed were able to predict future VTDR, DME and PDR using DR status and hemoglobin A1c.

“Although other variables such as kidney function and diabetes duration were significantly associated with outcomes, their inclusion did not improve the c-index enough to be included in the final model. The mean c-index was pooled more than 50 validation datasets and 10 test datasets were ≥92% and 94% for each outcome at 3 years, respectively,” Dr. Modjtahedi reported.

A risk calculator is available at

Based on their findings, the authors concluded that the future risk of developing VTDR, DME, and new-onset PDR can be accurately predicted using a patient’s retinopathy status and hemoglobin A1c level.

They also pointed out that these models can be used to help with patient education and management, including determining follow-up schedules and identifying patients who may benefit from tighter diabetes control and/or diabetes. prophylactic ophthalmic treatment.


Comments are closed.