CT radiomics for predicting the prognosis of patients with stage II rectal cancer during the three-year period after surgery, chemotherapy and radiotherapy

Hanjing Zhang; Yu Deng; M A Xiaojie; Qian Zou; Huanhui Liu; Ni Tang; Yuanyuan Luo; Xuejing Xiang

doi:10.1016/j.heliyon.2023.e23923

CT radiomics for predicting the prognosis of patients with stage II rectal cancer during the three-year period after surgery, chemotherapy and radiotherapy

Heliyon. 2023 Dec 27;10(1):e23923. doi: 10.1016/j.heliyon.2023.e23923. eCollection 2024 Jan 15.

Authors

Hanjing Zhang¹, Yu Deng², M A Xiaojie¹, Qian Zou¹, Huanhui Liu¹, Ni Tang¹, Yuanyuan Luo¹, Xuejing Xiang¹

Affiliations

¹ Department of Oncology, Affiliated Hospital of Chuanbei Medical College, Nanchong, Sichuan Province, 637000, China.
² The Affiliated Cancer Hospital of Guizhou Medical University, GuiYang, Guizhou Province, 550000, China.

Abstract

Objective: Pre-treatment enhanced CT image data were used to train and build models to predict the efficacy of non-small cell lung cancer after conventional radiotherapy and chemotherapy using two classification algorithms, Logistic Regression (LR) and Gaussian Naive Baye (GNB).

Methods: In this study, we used pre-treatment enhanced CT image data for region of interest (ROI) sketching and feature extraction. We utilized the least absolute shrinkage and selection operator (LASSO) mutual confidence method for feature screening. We pre-screened logistic regression (LR) and Gaussian naive Bayes (GNB) classification algorithms and trained and modeled the screened features. We plotted 5-fold and 10-fold cross-validated receiver operating characteristic (ROC) curves to calculate the area under the curve (AUC). We performed DeLong's test for validation and plotted calibration curves and decision curves to assess model performance.

Results: A total of 102 patients were included in this study, and after a comparative analysis of the two models, LR had only slightly lower specificity than GNB, and higher sensitivity, accuracy, AUC value, precision, and F1 value than GNB (training set accuracy: 0.787, AUC value: 0.851; test set accuracy: 0.772, AUC value: 0.849), and the LR model has better performance in both the decision curve and the calibration curve.

Conclusion: CT can be used for efficacy prediction after radiotherapy and chemotherapy in NSCLC patients. LR is more suitable for predicting whether NSCLC prognosis is in remission without considering the computing speed.