Development and validation of a radiomics-based nomogram for predicting a major pathological response to neoadjuvant immunochemotherapy for patients with potentially resectable non-small cell lung cancer

Abstract

Introduction: The treatment response to neoadjuvant immunochemotherapy varies among patients with potentially resectable non-small cell lung cancers (NSCLC) and may have severe immune-related adverse effects. We are currently unable to accurately predict therapeutic response. We aimed to develop a radiomics-based nomogram to predict a major pathological response (MPR) of potentially resectable NSCLC to neoadjuvant immunochemotherapy using pretreatment computed tomography (CT) images and clinical characteristics.

Methods: A total of 89 eligible participants were included and randomly divided into training (N=64) and validation (N=25) sets. Radiomic features were extracted from tumor volumes of interest in pretreatment CT images. Following data dimension reduction, feature selection, and radiomic signature building, a radiomics-clinical combined nomogram was developed using logistic regression analysis.

Results: The radiomics-clinical combined model achieved excellent discriminative performance, with AUCs of 0.84 (95% CI, 0.74-0.93) and 0.81(95% CI, 0.63-0.98) and accuracies of 80% and 80% in the training and validation sets, respectively. Decision curves analysis (DCA) indicated that the radiomics-clinical combined nomogram was clinically valuable.

Discussion: The constructed nomogram was able to predict MPR to neoadjuvant immunochemotherapy with a high degree of accuracy and robustness, suggesting that it is a convenient tool for assisting with the individualized management of patients with potentially resectable NSCLC.

Keywords: NSCLC; major pathological response; neoadjuvant immunochemotherapy; nomogram; radiomics.

Figure 1

(A) patient selection and distribution flowchart. (B) model construction and assessment flowchart.

Figure 2

Radiomic feature selection using a least absolute shrinkage and selection operator (LASSO) binary logistic regression model (A, B), with a comparison of the Rad-scores of the MPR and N-MPR groups (C): Red represents the N-MPR group and blue represents the MPR group. There was a significant difference in Rad-score between MPR and N-MPR patients in the training (P<0.001) and validation cohorts (P = 0.037). (A) Selection of the tuning parameter (λ) for the LASSO model via 10-fold cross-validation based on minimum criteria. The y-axis indicates binomial deviance. The lower x-axis indicates the log (λ). Numbers along the upper x-axis represent the average number of predictors. The optimal λ value of 0.035 with log (λ)= - 3.353 was selected. (B) LASSO coefficient profiles (y-axis) of the 20 texture features. The upper and lower x-axis has the same meaning as in Fig. 2A. A black vertical line was drawn at the value selected using 10-fold cross-validation in Fig. 2A. The 7 resulting features with non-zero coefficients are shown in the plot. (C) Comparison of Rad-scores between the MPR and N-MPR groups. Red represents the N-MPR group and blue represents the MPR group. There was a significant difference in the Rad-scores of MPR and N-MPR patients in both the training (P<0.001) and validation cohorts (P = 0.037).

Figure 3

Receiver operating characteristic curve analysis of three models in the training set (A) and the validation set (B) for predicting Major Pathological Response.

Figure 4

Nomogram, Calibration curve and Decision curve analysis. (A) Nomogram and (B) Calibration curve for Major Pathological Response in the training and validation groups. (C) Decision curve analysis for each model (clinical (Clinics) model, radiomics (Radiomics) model, and integrated (combined) model).