Preoperative CT-Based Radiomics Index to Predict Overall Survival and Postoperative Radiation Therapy Benefit in the elderly with NSCLC

Summary: The elderly make up the major proportion of both new cases and deaths of NSCLC, yet they are often underrepresented in clinical studies. The value of postoperative radiation therapy (PORT) for the elderly with non-small cell lung cancer (NSCLC) is uncertain. A subgroup of these patients could benefit from PORT. We aim to identify those who might benefit most from PORT. Patients aged ≥60 with pN2 NSCLC after radical surgery between January 1, 2011, and June 30, 2019, were included. The radiomics index was developed using radiomic texture features from preoperative CT scans. We used a least absolute shrinkage and selection operator-Cox regularization model for data dimension reduction, feature selection, and the construction of the radiomics index. The radiomics index's prediction capability was determined by the area under the curve (AUC) of the receiver operating characteristic. The overall survival (OS) was compared between patients who received PORT and those who did not in the subgroups determined by the radiomics index. A total of 578 patients were eligible. The radiomics index effectively predicted OS, with an AUC of 0.82 (95% CI, 0.77-0.88) for the 5-year OS. The high-radiomics index group had significantly worse OS than the low- radiomics index groups (5-year OS, 28.79% vs. 67.47%, p< 0.01). The median radiomics index was used to categorize individuals into two risk groups. Patients in the high-risk group benefited from PORT (5-year OS, 37.96% vs 72.07%, p< 0.01), while patients in low-risk groups did not (5-year OS, 79.56% vs 82.75%, p = 0.25). We developed a preoperative CT-based radiomics index capable of predicting OS and the benefits of PORT for the elderly with NSCLC. Zeliang Ma (he/him/his), MD (Presenting Author) - Cancer Hospital, Chinese Academy of Medical Science; Qian Liu, MD (Co-Author) - Cancer Hospital, Chinese Academy of Medical Science; Zhouguang Hui, MD (Co-Author) - Cancer Hospital, Chinese Academy of Medical Science