Résumé
Objective To analyze the factors affecting the prognosis of soft tissue sarcomas originating from the mediastinum and lung using relevant data from the SEER database. Methods The data of 376 patients were collected from the SEER database, and were randomly divided into the train set (n=263) and validation set (n=113). The relationship between each variable and patient survival and prognosis was analyzed using the Kaplan-Meier method and Cox proportional risk regression to establish a nomogram, to predict the overall survival of patients. The calibration curves, consistency index, and ROC curves were used to evaluate the performance of the nomogram. Results Histological type, surgery, chemotherapy, tumor size, and tumor stage were the factors affecting the prognosis of primary mediastinal and pulmonary soft tissue sarcomas. The established nomogram could predict the 6-month, 1-year, and 2-year overall survival of patients, and the calibration curves showed good prediction accuracy with measured values. C index of the train set and validation set were 0.754 and 0.745, respectively. The areas under the curve of ROC were 0.849 and 0.924. Conclusion The nomogram established in this study can predict 6-month, 1-year, and 2-year overall survival in patients with primary mediastinal and pulmonary soft tissue sarcoma.