Development and validation of risk prediction equations to estimate future risk of heart failure in patients with diabetes: a prospective cohort study

OBJECTIVE: To develop and externally validate risk prediction equations to estimate the 10-year risk of heart failure in patients with diabetes, aged 25–84 years. DESIGN: Cohort study using routinely collected data from general practices in England between 1998 and 2014 contributing to the QResearch and Clinical Research Practice Datalink (CPRD) databases. SETTING: We used 763 QResearch practices to develop the equations. We validated it in 254 different QResearch practices and 357 CPRD practices. PARTICIPANTS: 437 806 patients in the derivation cohort; 137 028 in the QResearch validation cohort, and 197 905 in the CPRD validation cohort. MEASUREMENT: Incident diagnosis of heart failure recorded on the patients’ linked electronic General Practitioner (GP), mortality, or hospital record. Risk factors included age, body mass index (BMI), systolic blood pressure, cholesterol/ high-density lipoprotein (HDL) ratio, glycosylated haemoglobin (HbA1c), material deprivation, ethnicity, smoking, diabetes duration, type of diabetes, atrial fibrillation, cardiovascular disease, chronic renal disease, and family history of premature coronary heart disease. METHODS: We used Cox proportional hazards models to derive separate risk equations in men and women for evaluation at 10 years. Measures of calibration, discrimination, and sensitivity were determined in 2 external validation cohorts. RESULTS: We identified 25 480 cases of heart failure in the derivation cohort, 8189 in the QResearch validation cohort, and 11 311 in the CPRD cohort. The equations included: age, BMI, systolic blood pressure, cholesterol/HDL ratio, HbA1c, material deprivation, ethnicity, smoking, duration and type of diabetes, atrial fibrillation, cardiovascular disease, and chronic renal disease. The equations had good performance in CPRD for women (R(2) of 41.2%; D statistic 1.71; and receiver operating characteristic curve (ROC) statistic 0.78) and men (38.7%, 1.63; and 0.77 respectively). CONCLUSIONS: We have developed and externally validated risk prediction equations to quantify absolute risk of heart failure in men and women with diabetes. These can be used to identify patients at high risk of heart failure for prevention or assessment of the disease.