Individualised variable-interval risk-based screening for sight-threatening diabetic retinopathy: the Liverpool Risk Calculation Engine

Aims/hypothesis Individualised variable-interval risk-based screening offers better targeting and improved costeffectiveness in screening for diabetic retinopathy. We developed a generalisable risk calculation engine (RCE) to assign personalised intervals linked to local population characteristics, and explored differences in assignment compared with current practice. Methods Data from 5 years of photographic screening and primary care for people with diabetes, screen negative at the first of > 1 episode, were combined in a purpose-built nearreal-time warehouse. Covariates were selected from a dataset created using mixed qualitative/quantitative methods. Markov modelling predicted progression to screen-positive (referable diabetic retinopathy) against the local cohort history. Retinopathy grade informed baseline risk and multiple imputation dealt with missing data. Acceptable intervals (6, 12, 24 months) and risk threshold (2.5%) were established with patients and professional end users. Results Data were from 11,806 people with diabetes (46,525 episodes, 388 screen-positive). Covariates with sufficient predictive value were: duration of known disease, HbA(1c), age, systolic BP and total cholesterol. Corrected AUC (95% CIs) were: 6 months 0.88 (0.83, 0.93), 12 months 0.90 (0.87, 0.93) and 24 months 0.91 (0.87, 0.94). Sensitivities/specificities for a 2.5% risk were: 6 months 0.61, 0.93, 12 months 0.67, 0.90 and 24 months 0.82, 0.81. Implementing individualised RCE-based intervals would reduce the proportion of people becoming screenpositive before the allocated screening date by > 50% and the number of episodes by 30%. Conclusions/interpretation The Liverpool RCE shows sufficient performance for a local introduction into practice before wider implementation, subject to external validation. This approach offers potential enhancements of screening in improved local applicability, targeting and cost-effectiveness