Development and validation of a novel model for patients with soft tissue sarcoma who received neoadjuvant chemotherapy.
AI interpretation is pending for this paper.
Open original publication →What the AI sees
Not AI summarized yet.
Research significance
Pending deeper interpretation.
Source abstract
Although surgical resection combined with radiotherapy is still the preferred treatment for soft tissue sarcoma, neoadjuvant chemotherapy is becoming more popular. The goal of this research is to get a large, multicenter retrospective analysis to build a practical and validated method to predict overall survival in patients. This study was a retrospective study of 902 soft tissue sarcoma patients from the Surveillance, Epidemiology, and End Results database who received neoadjuvant chemotherapy. We used the Cox multivariate model to build a nomogram for predicting overall survival and converted it into a web-based nomogram. To identify and calibrate the model, bootstrap resampling was used to draw receiver operating characteristic curves and calibration curves, as well as to test the clinical applicability of the model by plotting decision curves. A total of 634 patients were included in the training cohort, while the remaining 268 patients were included in the validation cohort. Overall survival was significantly influenced by disease stage, age, tumor size, grade, and radiation, and nomograms were created to predict overall survival. The area under the curve for predicting overall survival at 1, 3, and 5 years in the training cohort was 0.797, 0.751, and 0.739, respectively; the area under the curve for the validation cohort was 0.726, 0.747, and 0.698, respectively. The calibration curves showed that the model performs well in terms of calibration (prediction accuracy). In addition, the decision curve analysis demonstrates the good clinical application of the model, allowing for a greater net clinical benefit. For soft tissue sarcoma patients who have received neoadjuvant chemotherapy, we have developed the first novel tool to accurately predict overall survival. This tool improves clinicians' ability to assess patient prognosis, enhances prognosis-based treatment decisions, and can be used as a guide for clinicians to consult with patients.