A potential biomarker based on clinical-radiomics nomogram for predicting survival and adjuvant chemotherapy benefit in resected node-negative, early-stage lung adenocarcinoma

Xiaoling Ma; Wenzhi Lv; Cong Wang; Dehao Tu; Jinhan Qiao; Chanyuan Fan; Jiandong Niu; Wen Zhou; Qiuyu Liu; Liming Xia

doi:10.21037/jtd-21-1520

A potential biomarker based on clinical-radiomics nomogram for predicting survival and adjuvant chemotherapy benefit in resected node-negative, early-stage lung adenocarcinoma

J Thorac Dis. 2022 Jan;14(1):1-17. doi: 10.21037/jtd-21-1520.

Authors

Xiaoling Ma¹, Wenzhi Lv², Cong Wang³, Dehao Tu⁴, Jinhan Qiao¹, Chanyuan Fan¹, Jiandong Niu⁵, Wen Zhou¹, Qiuyu Liu¹, Liming Xia¹

Affiliations

¹ Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
² Department of Artificial Intelligence, Julei Technology Company, Wuhan, China.
³ Jiangsu Key Laboratory of Medical Optics, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China.
⁴ Department of Thoracic surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
⁵ Department of Radiology, The General Hospital of Ningxia Medical University, Yinchuan, China.

Abstract

Background: We aimed to construct a clinical-radiomics nomogram to predict disease-free survival (DFS) and the added survival benefit of adjuvant chemotherapy (ACT) for node-negative, early-stage (I-II) lung adenocarcinoma (ADC).

Methods: In this retrospective study including 310 patients from two independent cohorts, the CT-derived radiomics features were selected by least absolute shrinkage and selection operator Cox regression to generate a radiomics signature associated with DFS. The radiomics signature was incorporated to construct a clinical-radiomics nomogram along with the independent clinical risk predictors. The model performance was evaluated with reference to discrimination quantified by Harrell concordance index (C-index), integrated discrimination improvement (IDI) and net reclassification index (NRI), calibration and clinical utility. The risk score (RS) for clinical-radiomics nomogram was calculated. The association between ACT and survival benefit was assessed in high and low RS subgroup.

Results: The clinical-radiomics nomogram achieved the highest C-index of 0.822 [95% confidence interval (CI): 0.769, 0.876] in training cohort and 0.802 (95% CI: 0.716, 0.888) in validation cohort. The incorporation of radiomics signature into clinical-radiomics nomogram showed an incremental benefit over clinical nomogram according to the improved NRI and IDI. The calibration curves and decision curve analysis further verified the clinical utility of clinical-radiomics nomogram. Further, patients with high RS based on clinical-radiomics nomogram were more prone to benefit from ACT.

Conclusions: The clinical-radiomics nomogram approach can feasibly conduct risk prediction and have potential to identify the beneficiaries of ACT among patients with node-negative, early-stage ADC, which might serve as a helpful tool in informing therapeutic decision-making.

Keywords: Adjuvant chemotherapy (ACT); computer tomography; lung adenocarcinoma (lung ADC); radiomics; survival.