Predicting 10 year incidence of dyslipidemia based on novel anthropometric indices, using exploratory regression models and data mining

Background: This study aimed to establish a 10 year dyslipidemia incidence model, investigating novel anthropometric indices using exploratory regression and data mining. Methods: A total of 1776 individuals without dyslipidemia were enrolled from phase 1 of the Mashhad Stroke and Heart Atherosclerotic Disorder (MASHAD) study. People who were diagnosed with dyslipidemia in phase 2 (n = 1097) were compared with healthy people in this phase. The association of dyslipidemia with novel anthropometric indices including C-Index (conicity index), BRI (body roundness index), VAI (Visceral Adiposity Index), LAP (Lipid Accumulation Product), AVI (Abdominal volume index), WWI (weight-adjusted-waist index), BMI (body mass index), BAI (Body Adiposity Index) and BSA (body surface area) have been evaluated in this study. Logistic regression (LR) and decision tree (DT) analysis were utilized to evaluate the association. The accuracy, sensitivity, and specificity of DT were assessed through the performance of a receiver operating characteristic (ROC) curve using R software. Results: A total of 1776 subjects including 1097 and 679 individuals with and without dyslipidemia encountered the study. There were 586 (53.4%) females and 511(46.6%) males with dyslipidemia. According to the results, VAI has been identified as the most significant risk factor for dyslipidemia (OR: 2.81, (95% CI: 2.07, 3.81)) in all models. Moreover, the DT showed that VAI followed by BMI and LAP as the most critical variables in the prediction of dyslipidemia incidence. Conclusions: Based on our findings, the VAI was the principal anthropometric factor for predicting dyslipidemia incidence.