Predicting prognosis in patients with stage IA lung adenocarcinoma with a micropapillary component using a nomogram based on computed tomography radiomics and clinicopathologic factors: a retrospective analysis
Related Experiment Video
Updated: Jul 22, 2026
Using Micro-computed Tomography for the Assessment of Tumor Development and Follow-up of Response to Treatment in a Mouse Model of Lung Cancer
Published on: May 20, 2016
Ying Li1, Junfeng Zhao2, Ruyue Li3
1Department of Respiratory Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, and Shandong Academy of Medical Sciences, Jinan, China.
Background:
Patients with stage IA lung adenocarcinoma (ADC) with an micropapillary (MIP) component are at a higher risk of recurrence after radical surgical resection; however, adding adjuvant chemotherapy (ACT) to their postoperative course remains controversial. This study determined the predictive factors that influence the prognosis of these patients and identified those at high risk of recurrence.
Methods:
Between January 2012 and December 2018, 254 eligible patients with stage IA lung ADC with an MIP component were categorized into training (n=169) and validation (n=85) cohorts. Clinicopathological and radiomics features were included in univariate and multivariate analyses, and statistically significant predictors were used to develop the nomogram. Area under the curve (AUC) of receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were used to validate the model. The calculated risk scores for each patient were risk-stratified using the X-tile procedure, and survival analyses were performed among the different risk subgroups.
Results:
T1c stage, MIP ≥1%, spread through air space (STAS), carcinoembryonic antigen (CEA) >5 µg/L, and radiomics features were independent predictors of overall survival (OS) and disease-free survival (DFS) in patients with lung ADC with an MIP component at stage IA. Incorporating this into the nomogram, the AUCs of the nomogram predicting 3-, 5-, and 7-year OS and DFS were 0.910, 0.914, and 0.904 and 0.868, 0.838, and 0.848, respectively, in the training cohort and 0.879, 0.895, and 0.899 and 0.817, 0.805, and 0.811, respectively, in the validation cohort, showing good differentiation. The OS and DFS survival analyses among different risk subgroups showed that the nomogram could well distinguish between low- and high-risk groups.
Conclusions:
We developed and validated a nomogram based on clinicopathological factors and radiomics features, which can be used as a powerful tool for predicting postoperative recurrence and survival in patients with stage IA lung ADC containing an MIP component.
