Logistic regression study on chronic pancreatitis grade diagnostic model
10.3760/cma.j.issn.1674-1935.2017.03.003
- VernacularTitle:慢性胰腺炎分级诊断模型的回归分析
- Author:
Yu SHENG
;
Yun BIAN
;
Xu FANG
;
Chenwei SHAO
;
Jianping LU
;
Li WANG
- Keywords:
Pancreatitis;
chronic;
Diagnosis;
Magnetic resonance imaging;
Factor analysis;
Logistic regression
- From:
Chinese Journal of Pancreatology
2017;17(3):153-157
- CountryChina
- Language:Chinese
-
Abstract:
Objective To establish a MRI grading diagnostic model for chronic pancreatitis (CP) to acquire better combination for CP diagnosis and improve the diagnostic ability of CP grading.Methods To collecte the data of 68 CP patients who were clinically diagnosed and 23 health volunteers from Dec 2012 to Oct 2014.There were 23 mild CP, 14 moderate CP and 31 severe CP according to Cambridge classification.3.0 T MRI data were analyzed, and 14 features were extracted to compare the MRI features among groups.The single ordinal regression analysis was conducted on the variables with significant difference between groups, and the collinearity was diagnosed.The factor analysis was used for multicollinearity.The multiple ordinal logistic regression was finally conducted to establish the regression model.Results There was no significant difference between control groups and CP groups on pancreas divisum (X14), but significant differences were found in other 13 features (P<0.05).Single ordinal regression analysis of 13 features showed that all features except pancreatic parenchymal bubble (X12) were significantly correlated with CP grading diagnosis(P<0.05).The effect of multicollinearity was validated among 9 continuous variables.Three common factors were identified, including F1(X3、X4、X5、X9、X8), F2(X7、X6) and F3 (X1、X2) which represented the exocrine function, the features of main pancreatic ducts and pancreatic parenchyma, respectively.Six features were implemented into the multi Logistic regression model, which included F1, F2, F3, X10 (the visualizations of branch pancreatic duct after secretin stimulation), X11 (pancreatic shape) and X13 (the filling defects of main pancreatic duct).Finally, the most appropriate regression model was gotten, which was the scale model of the probit link function.The model′s diagnostic accuracy for normal, mild CP, moderate CP, severe CP and total CP was 96.65%,100%, 71.42%,100% and 94.50%, respectively.Conclusions The ordinal logistic regression model proposed in this study may accurately predict the CP grades and can offer valuable references for clinic diagnosis and therapy of CP.
