Classification Rule for 5-year Cardiovascular Diseases Risk using decision tree in Primary Care Chinese Patients with Type 2 Diabetes Mellitus. Issue 1 (December 2017)

• Record Type: Journal Article
• Authors: Wan, Eric; Fong, Daniel; Fung, Colman; Yu, Esther; Chin, Weng; Chan, Anca; Lam, Cindy
• Is Part Of: Scientific reports. Volume 7:Issue 1(2017)
• Page Start: 1
• Page End: 8
• Publication Date: 2017-12
• Subjects: Natural history -- Research -- Periodicals; Biology -- Research -- Periodicals; Physical sciences -- Research -- Periodicals; Earth sciences -- Research -- Periodicals; Environmental sciences -- Research -- Periodicals; 502.85
• DOI: 10.1038/s41598-017-15579-z
• Languages: English
• ISSNs: 2045-2322

Abstract

Abstract Cardiovascular disease(CVD) is the leading cause of mortality among patients with type 2 diabetes mellitus(T2DM), and a risk classification model for CVD among primary care diabetic patients is pivotal for risk-based interventions and patient information. This study developed a simple tool for a 5-year CVD risk prediction for primary care Chinese patients with T2DM. A retrospective cohort study was conducted on 137, 935 primary care Chinese T2DM patients aged 18–79 years without history of CVD between 1 January 2010 and 31 December 2010. New events of CVD of the cohort over a median follow up of 5 years were extracted from the medical records. A classification rule of 5-year CVD risk was obtained from the derivation cohort and validated in the validation cohort. Significant risk factors included in decision tree were age, gender, smoking status, diagnosis duration, obesity, unsatisfactory control on haemoglobin A1c and cholesterol, albuminuria and stage of chronic kidney disease, which categorized patients into five 5-year CVD risk groups(<5%; 5–9%; 10–14%; 15–19% and ≥20%). Taking the group with the lowest CVD risk, the hazard ratios varied from 1.92(1.77, 2.08) to 8.46(7.75, 9.24). The present prediction model performed comparable discrimination and better calibration from the plot compared to other current existing models.