Importance of family history of diabetes in computing a diabetes risk score in Korean prediabetic population

Abstract

Prediabetic subjects represent a vulnerable population, requiring special care to reduce the risk of diabetes onset. We developed and validated a diabetes risk score for prediabetic subjects using the Korea National Diabetes Program (KNDP) cohort. Subjects included in the multicenter and prospective cohort (n = 1162) had high diabetes risk at baseline (2005) and were followed until 2012. Survival analysis was performed to analyze the prospective cohort over time, and the bootstrap method was used to validate our model. We confirmed our findings in an external cohort. A diabetes risk score was calculated and the cut-off defined using a receiver operating characteristic curve. Age, body mass index, total cholesterol, and family history of diabetes were associated with diabetes. The model performed well after correction for optimism (Cadj = 0.735). A risk score was defined with a cut-off of >/=5 that maximized sensitivity (72%) and specificity (62%), with an area under the curve of 0.73. Prediabetic subjects with a family history of diabetes had a higher probability of diabetes (risk score = 5) irrespective of other variables: this result was confirmed in the external cohort. Hence, prediabetic subjects with a family history of diabetes have a higher probability of developing diabetes, regardless of other clinical factors.