RESUMO
Purpose: Stereotactic body radiation therapy (SBRT) is a standard treatment for early primary lung cancer patients. However, there are few simple models for predicting the clinical outcomes of these patients. Our study analyzed the clinical outcomes, identified the prognostic factors, and developed prediction nomogram models for these patients. Materials and Methods: We retrospectively analyzed 114 patients with primary lung cancer treated with SBRT from 2012 to 2020 at our institutions and assessed patient's clinical outcomes and levels of toxicity. Kaplan-Meier analysis with a log-rank test was used to generate the survival curve. The cut-off values of continuous factors were calculated with the X-tile tool. Potential independent prognostic factors for clinical outcomes were explored using cox regression analysis. Nomograms for clinical outcomes prediction were established with identified factors and assessed by calibration curves. Results: The median overall survival (OS) was 40.6 months, with 3-year OS, local recurrence free survival (LRFS), distant disease-free survival (DDFS) and progression free survival (PFS) of 56.3%, 61.3%, 72.9% and 35.8%, respectively, with grade 3 or higher toxicity rate of 7%. The cox regression analysis revealed that the clinical stage, immobilization device, and the prescription dose covering 95% of the target area (D95) were independent prognostic factors associated with OS. Moreover, the clinical stage, and immobilization device were independent prognostic factors of LRFS and PFS. The smoking status, hemoglobin (Hb) and immobilization device were significant prognostic factors for DDFS. The nomograms and calibration curves incorporating the above factors indicated good predictive accuracy. Conclusions: SBRT is effective and safe for primary lung cancer. The prognostic factors associated with OS, LRFS, DDFS and PFS are proposed, and the nomograms we proposed are suitable for clinical outcomes prediction.
RESUMO
PURPOSE: Stereotactic body radiotherapy (SBRT) is an important treatment modality for lung cancer patients, however, tumor local recurrence rate remains some challenge and there is no reliable prediction tool. This study aims to develop a prediction model of local control for lung cancer patients undergoing SBRT based on radiomics signature combining with clinical and dosimetric parameters. METHODS: The radiomics model, clinical model and combined model were developed by radiomics features, incorporating clinical and dosimetric parameters and radiomics signatures plus clinical and dosimetric parameters, respectively. Three models were established by logistic regression (LR), decision tree (DT) or support vector machine (SVM). The performance of models was assessed by receiver operating characteristic curve (ROC) and DeLong test. Furthermore, a nomogram was built and was assessed by calibration curve, Hosmer-Lemeshow and decision curve. RESULTS: The LR method was selected for model establishment. The radiomics model, clinical model and combined model showed favorite performance and calibration (Area under the ROC curve (AUC) 0.811, 0.845 and 0.911 in the training group, 0.702, 0.786 and 0.818 in the validation group, respectively). The performance of combined model was significantly superior than the other two models. In addition, Calibration curve and Hosmer-Lemeshow (training group: P = 0.898, validation group: P = 0.891) showed good calibration of combined nomogram and decision curve proved its clinical utility. CONCLUSIONS: The combined model based on radiomics features plus clinical and dosimetric parameters can improve the prediction of 1-year local control for lung cancer patients undergoing SBRT.
