AUTHOR=Chen Juan , Meng Ting , Xu Jia , Ooi Joshua D. , Eggenhuizen Peter J. , Liu Wenguang , Li Fang , Wu Xueqin , Sun Jian , Zhang Hao , Zhou Ya-Ou , Luo Hui , Xiao Xiangcheng , Pei Yigang , Li Wenzheng , Zhong Yong TITLE=Development of a radiomics nomogram to predict the treatment resistance of Chinese MPO-AAV patients with lung involvement: a two-center study JOURNAL=Frontiers in Immunology VOLUME=14 YEAR=2023 URL=https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2023.1084299 DOI=10.3389/fimmu.2023.1084299 ISSN=1664-3224 ABSTRACT=Background

Previous studies from our group and other investigators have shown that lung involvement is one of the independent predictors for treatment resistance in patients with myeloperoxidase (MPO)–anti-neutrophil cytoplasmic antibody (ANCA)-associated vasculitis (MPO-AAV). However, it is unclear which image features of lung involvement can predict the therapeutic response in MPO-AAV patients, which is vital in decision-making for these patients. Our aim was to develop and validate a radiomics nomogram to predict treatment resistance of Chinese MPO-AAV patients based on low-dose multiple slices computed tomography (MSCT) of the involved lung with cohorts from two centers.

Methods

A total of 151 MPO-AAV patients with lung involvement (MPO-AAV-LI) from two centers were enrolled. Two different models (Model 1: radiomics signature; Model 2: radiomics nomogram) were built based on the clinical and MSCT data to predict the treatment resistance of MPO-AAV with lung involvement in training and test cohorts. The performance of the models was assessed using the area under the curve (AUC). The better model was further validated. A nomogram was constructed and evaluated by DCA and calibration curves, which further tested in all enrolled data and compared with the other model.

Results

Model 2 had a higher predicting ability than Model 1 both in training (AUC: 0.948 vs. 0.824; p = 0.039) and test cohorts (AUC: 0.913 vs. 0.898; p = 0.043). As a better model, Model 2 obtained an excellent predictive performance (AUC: 0.929; 95% CI: 0.827–1.000) in the validation cohort. The DCA curve demonstrated that Model 2 was clinically feasible. The calibration curves of Model 2 closely aligned with the true treatment resistance rate in the training (p = 0.28) and test sets (p = 0.70). In addition, the predictive performance of Model 2 (AUC: 0.929; 95% CI: 0.875–0.964) was superior to Model 1 (AUC: 0.862; 95% CI: 0.796–0.913) and serum creatinine (AUC: 0.867; 95% CI: 0.802–0.917) in all patients (all p< 0.05).

Conclusion

The radiomics nomogram (Model 2) is a useful, non-invasive tool for predicting the treatment resistance of MPO-AAV patients with lung involvement, which might aid in individualizing treatment decisions.