Dorte Vistisen1, Gregers Stig Andersen2, Christian Stevns Hansen2, Adam Hulman2, Jan Erik Henriksen2, Henning Bech-Nielsen2, Marit Eika Jørgensen2. 1. From Steno Diabetes Center, Gentofte, Denmark (D.V., G.S.A., C.S.H., M.E.J.); Department of Public Health, Aarhus University, Denmark (A.H.); Danish Diabetes Academy, Odense, Denmark (A.H., H.B.-N.); Odense University Hospital, Denmark (J.E.H., H.B.-N.); and University of Southern Denmark, Copenhagen (H.B.-N.). dtvs@steno.dk. 2. From Steno Diabetes Center, Gentofte, Denmark (D.V., G.S.A., C.S.H., M.E.J.); Department of Public Health, Aarhus University, Denmark (A.H.); Danish Diabetes Academy, Odense, Denmark (A.H., H.B.-N.); Odense University Hospital, Denmark (J.E.H., H.B.-N.); and University of Southern Denmark, Copenhagen (H.B.-N.).
Abstract
BACKGROUND: Patients with type 1 diabetes mellitus are at increased risk of developing cardiovascular disease (CVD), but they are currently undertreated. There are no risk scores used on a regular basis in clinical practice for assessing the risk of CVD in type 1 diabetes mellitus. METHODS AND RESULTS: From 4306 clinically diagnosed adult patients with type 1 diabetes mellitus, we developed a prediction model for estimating the risk of first fatal or nonfatal CVD event (ischemic heart disease, ischemic stroke, heart failure, and peripheral artery disease). Detailed clinical data including lifestyle factors were linked to event data from validated national registers. The risk prediction model was developed by using a 2-stage approach. First, a nonparametric, data-driven approach was used to identify potentially informative risk factors and interactions (random forest and survival tree analysis). Second, based on results from the first step, Poisson regression analysis was used to derive the final model. The final CVD prediction model was externally validated in a different population of 2119 patients with type 1 diabetes mellitus. During a median follow-up of 6.8 years (interquartile range, 2.9-10.9) a total of 793 (18.4%) patients developed CVD. The final prediction model included age, sex, diabetes duration, systolic blood pressure, low-density lipoprotein cholesterol, hemoglobin A1c, albuminuria, glomerular filtration rate, smoking, and exercise. Discrimination was excellent for a 5-year CVD event with a C-statistic of 0.826 (95% confidence interval, 0.807-0.845) in the derivation data and a C-statistic of 0.803 (95% confidence interval, 0.767-0.839) in the validation data. The Hosmer-Lemeshow test showed good calibration (P>0.05) in both cohorts. CONCLUSIONS: This high-performing CVD risk model allows for the implementation of decision rules in a clinical setting.
BACKGROUND:Patients with type 1 diabetes mellitus are at increased risk of developing cardiovascular disease (CVD), but they are currently undertreated. There are no risk scores used on a regular basis in clinical practice for assessing the risk of CVD in type 1 diabetes mellitus. METHODS AND RESULTS: From 4306 clinically diagnosed adult patients with type 1 diabetes mellitus, we developed a prediction model for estimating the risk of first fatal or nonfatal CVD event (ischemic heart disease, ischemic stroke, heart failure, and peripheral artery disease). Detailed clinical data including lifestyle factors were linked to event data from validated national registers. The risk prediction model was developed by using a 2-stage approach. First, a nonparametric, data-driven approach was used to identify potentially informative risk factors and interactions (random forest and survival tree analysis). Second, based on results from the first step, Poisson regression analysis was used to derive the final model. The final CVD prediction model was externally validated in a different population of 2119 patients with type 1 diabetes mellitus. During a median follow-up of 6.8 years (interquartile range, 2.9-10.9) a total of 793 (18.4%) patients developed CVD. The final prediction model included age, sex, diabetes duration, systolic blood pressure, low-density lipoprotein cholesterol, hemoglobin A1c, albuminuria, glomerular filtration rate, smoking, and exercise. Discrimination was excellent for a 5-year CVD event with a C-statistic of 0.826 (95% confidence interval, 0.807-0.845) in the derivation data and a C-statistic of 0.803 (95% confidence interval, 0.767-0.839) in the validation data. The Hosmer-Lemeshow test showed good calibration (P>0.05) in both cohorts. CONCLUSIONS: This high-performing CVD risk model allows for the implementation of decision rules in a clinical setting.
Authors: Magnus T Jensen; Peter Sogaard; Ida Gustafsson; Jan Bech; Thomas F Hansen; Thomas Almdal; Simone Theilade; Tor Biering-Sørensen; Peter G Jørgensen; Søren Galatius; Henrik U Andersen; Peter Rossing Journal: Diabetologia Date: 2019-10-30 Impact factor: 10.122