Predicting response to neoadjuvant chemotherapy using a nomogram model based on baseline MRI in patients with locally advanced rectal cancer

XU Min; CHENG Jinmei; ZHOU Chuanqinyuan; GUO Wenwen; CHEN Tianwu

doi:10.19300/j.2024.L21089

Abstract：Objective To develop a nomogram for predicting the response of locally advanced rectal cancer(LARC)to neoadjuvant chemotherapy(NAC)based on baseline MRI.Methods Clinical and MRI imaging data of 142 consecutive LARC patients undergoing NAC were retrospectively collected from two medical centers.Center 1 included 116 patients,which were randomly divided into a training set(n=87)and an internal validation set(n=29).Center 2 contributed 26 patients as an external validation set.Differences in each observed indicator between the objective response rate(ORR)and non-ORR groups in the training set were analyzed using chi-square test,Fisher's exact test,independent sample t-test,or Mann-Whitney U test.Univariate and multivariate logistic regression analysis were performed to identify potential determinants associated with the response to NAC,which were then incorporated to develop the prediction nomogram.Receiver operating characteristic curve(ROC)and area under the ROC curve(AUC)were used to evaluate the nomogram's effectiveness in predicting the LARC neoadjuvant chemotherapy response.Calibration curve was used to evaluate the nomogram's calibration ability,and decision curve was used to assess the clinical benefits of the nomogram model.Results In the training set,cT stage,cN stage,mesorectal fascia(MRF)invasion,extramural vascular invasion(EMVI),gross tumor volume(GTV),and the tumor maximum diameter in the ORR group significantly differed from those in the non-ORR group(all P<0.05).There were no significant differences in gender,age and positive node volume(all P>0.05).Univariate and multivariate analysis in training cohort showed that pretherapeutic cT stage,cN stage,GTV,and EMVI were independent predictive factors related to response to NAC(all P<0.05).The nomogram developed based on those independent prognostic factors showed excellent performance in predicting the response to NAC in training cohort,validation cohort,and external validation cohort,with AUC values of 0.902,0.877,and 0.872,respectively.The calibration curves indicated an effective coincidence between predicted and practical responses to NAC.The decision curve analysis showed that the nomogram model could bring clinical benefits to LARC patients.Conclusion This nomogram,constructed based on the independent predictorsy,including cT staging,cN staging,EMVI,and GTV,can effectively predict neoadjuvant chemotherapy response in LARC patients.