Abstract
Objective: To establish early diagnosis model of inflammatory factors for atherosclerosis (AS), providing theoretical evidence for early detection of AS and development of plaques. Methods: Serum samples were collected to detect the inflammatory factors including CysC, Hcy, hs-CRP, UA, FIB, D-D, LP (a), IL-6, SAA, sCD40L and MDA. Using Logistic regression analysis, the inflammatory factors used for modeling were screened out, and then the AS early diagnosis models were established based on receiver operating characteristic (ROC) curve, support vector machine and BP neural network respectively. Results: No significant difference exists between the general materials of two groups. All 11 inflammatory factors had higher level in AS group than in control group. As shown in ROC curve, all inflammatory factors were helpful in AS diagnosis. In terms of sensitivity, UA ranked first (98) and FIB ranked last (55.5); in terms of specificity, UA ranked first (99) and FIB ranked last (78); in terms of area under the curve, UA and SAA ranked first (both were 0.995) and FIB ranked last (0.721). Based on Logistic regression equation, six factors were screened out, including Hcy, Hs-CRP, IL-6, D-D, CysC and MDA. According to classification, the final sixth steps had a prediction accuracy of 99%. When six inflammatory factors included in Logistic regression equation were detected jointly, the sensitivity, specificity and area under the curve were 57%, 97% and 0.821 respectively, while those of the model excluding D-D were 64%, 90% and 0.828, generally superior to results of joint detection including six factors. The ROC curve based on Hcy, Hs-CRP and MDA had a sensitivity of 87%, a specificity of 94% and an area under the curve of 0.869, being inferior to those of the ROC curve based on IL-6, D-D and Cys C, which were 87%, 92% and 0.936 respectively. The accuracy of SVM-AS diagnosis model and BP neural network model were 82.5% and 77.5% respectively. Conclusion: All 11 inflammatory factors are valuable in AS diagnosis. AS early diagnosis models based on Logistic regression analysis, ROC curve, support vector machine and BP neural network possess diagnostic value and can provide reference for clinical diagnosis.