Construction of an Activity Assessment Model for Sacroiliitis in Ankylosing Spondylitis Based on DCE-MRI Parameters and Peripheral Blood Th1/Th2 and Th17/Treg Ratios
ZHANG Meng
REN Jipeng
ZHAO Endian
DONG Fengjiao
QIN Ruijing
WANG Xuejia
Abstract：Objective To construct a model based on dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI)parameters,peripheral blood helper T cells(Th)1/Th2 and Th17/regulatory T cells(Treg)for assessing the activity of sacroiliac arthritis in ankylosing spondylitis(AS),and to analyze the evaluation value of the model,so as to provide reference for clinical diagnosis and treatment.Methods A total of 200 AS patients who admitted to the First Affiliated Hospital of Henan Medical University from January 2022 to February 2025 were selected and divided into the active group and the stable group according to AS disease activity score-C-reactive protein(ASDAS-CRP)score.DCE-MRI parameters,peripheral blood Th1/Th2 and Th17/Treg were compared between the two groups.LASSO regression was used for preliminary screening,and logistic regression was used to analyze the evaluation effect of each index on the activity of sacroiliac arthritis.XGBoost model was constructed,and the model was evaluated by receiver operating characteristic(ROC)curve,calibration curve and decision curve.Results The levels of C-reactive protein(CRP),Th1/Th2,Th17/Treg,volume transfer constant(Ktrans),reflux rate constant(kep),extravascular extracellular volume fraction(ve),time to peak(TTP),maximum concentration(Cmax)and area under the concentration-time curve(AUC)in the active group were higher than those in the stable group,with statistically significant differences(P＜0.05).LASSO-logistic regression analysis showed that CRP,Th1/Th2,Th17/Treg,Ktrans,ve and TTP were independent influencing factors of AS sacroiliac arthritis activity(P＜0.05).XGBoost model analysis showed that Ktrans,TTP,CRP,ve,Th1/Th2 and Th17/Treg were the key factors to evaluate the activity of AS sacroiliac arthritis.The AUC of the ROC curve of the XGBoost model in evaluating the activity of AS sacroiliac arthritis was 0.900(95％CI:0.859-0.942,P＜0.05).There was no significant difference between the accuracy of the XGBoost model in evaluating the activity of AS sacroiliac arthritis and the actual observation probability.In the 50％-80％threshold probability range,using this model to evaluate the activity of AS sacroiliitis can achieve significant net benefits.Conclusion CRP,Th1/Th2,Th17/Treg,Ktrans,ve and TTP are all effective indicators for evaluating the activity of AS sacroiliac arthritis.The XGBoost model based on DCE-MRI parameters,peripheral blood Th1/Th2,Th17/Treg can effectively evaluate the activity of AS sacroiliac arthritis,which has guiding significance for the targeted treatment of AS in clinical practice.
Keywords：ankylosing spondylitisdynamic contrast-enhanced magnetic resonance imaginghelper T cell 1/helper T cell 2helper T cell 17/regulatory T cellsXGBoost modelactivity of sacroiliac arthritis
Publication Date：2026-08-28
Online Publishing Date：2026-09-12(First online date of this platform, not the publication date of the document)
Pages：6( 2933-2938 )