Development and validation of prediction rules to target care intensification in veteran patients with diabetes

BACKGROUND: Diabetes affects 30.3 million people in the USA. Among these people, a major risk factor for microvascular complications is having a glycated haemoglobin (HbA1c) value of ≥75 mmol/mol; therefore, it would be helpful to identify patients who will obtain future HbA1c values of <75 mmol/mol. OBJECTIVES: To develop and validate two prediction rules among patients with diabetes having a baseline HbA1c value of ≥75 mmol/mol: (1) HbA1c measurement ever <75 mmol/mol and (2) final HbA1c measurement of <75 mmol/mol. METHODS: Retrospective cohort study using a registry extracting data from the Department of Veterans Affairs’s (VA’s) electronic health records system. Baseline was 1 Jul 2013–30 June 2014; patients were followed up until 31 July 2016. RESULTS: Our population consisted of 145 659 patients. Across models, predictors were age, sex, minority status, baseline HbA1c value, time, HbA1c≥75 mmol/mol, receiving insulin treatment and consecutive number of HbA1c values of 75 mmol/mol. The overall likelihood of a patient ever having an HbA1c<75 mmol/mol was 73.65%; with the rule, predicted probabilities were 38.94%, 50.75% and 78.88%. The overall likelihood of patients having a final HbA1c measurement of <75 mmol/mol was 55.35%; the rule provided predicted probabilities of 29.93%, 50.17% and 68.58%. CONCLUSIONS: Within each rule, there were similar observed and predicted tertile probabilities; maintaining HbA1c values of <75 mmol/mol resulted in probability shifts in the majority of patients. We recommend psychosocial screening for 15% of patients for whom there is less than one-third chance of maintaining HbA1c<75 mmol/mol. We plan to conduct additional research to see whether this approach helps.