Construction and validation of a nomogram model for prognosis of gastric cancer based on SEER database
Objective To investigate the prognostic risk factors of gastric cancer patients and construct a nomogram prognostic prediction model to predict the overall survival(OS)of gastric cancer patients.Methods Based on the SEER database,data on patients with gastric cancer diagnosed from 2010 to 2015 were gathered and retrospectively ex-amined.The factors affecting the survival of patients with gastric cancer were screened out using univariate and multiva-riate Cox regression analysis,and the Kaplan-Meier method was employed to plot the survival curve.The risk factors were taken into consideration according to clinical experience and statistical results,which were used to construct a prog-nostic model for gastric cancer patients and to draw a nomogram.The C-index,ROC curve and calibration curve were used to assess the clinical prediction model.Results There were 3 052 gastric cancer patients in this study.A nomo-gram,which was a 1-year,3-year and 5-year prognostic prediction model for patients with gastric cancer,was construc-ted.The C-index was used to assess the nomogram model's accuracy,which was 0.780(95％CI:0.769-0.793)in the training set and 0.763(95％CI:0.743-0.783)in the validation set.The ROC curve was used to assess the nomogram model.The area under the 1-year,3-year and 5-year survival curves of the ROC curves in the training set were 0.844,0.852 and 0.858,respectively.The area under the 1-year,3-year and 5-year survival curves of the ROC curves in the validation set were 0.824,0.829 and 0.842,respectively.The training set and verification set's calibration charts fur-ther demonstrated the model's great accuracy.Conclusion The nomogram prediction model can accurately predict the OS of patients with gastric cancer,which can help guide clinicians in personalized prognostic assessment and clinical decision-making.
NETL
NSTL
万方数据
