Establishment and validation of prognostic nomograms in female lung adenocarcinoma patients

The incidence of lung adenocarcinoma in women is gradually increasing, but the prognostic factors affecting this group of patients have not been systematically studied, so we hope that we can construct a prognostic prediction model for this group of patients to provide a more accurate survival prediction. We performed a retrospective analysis of female patients with pathologically diagnosed lung adenocarcinoma, constructed nomograms of overall survival (OS) and cancer-specific survival (CSS) at 1, 3, and 5 years using COX regression analyses, and evaluated the prediction using the consistency index (C-index), calibration curves, receiver operating characteristic (ROC) curves, and decision curve analysis (DCA) model performance with internal and external validation. We included a total of 11,562 patients, which were divided into 2 groups in a ratio of 7:3 Analysis using the chi-square test revealed that there was no statistically significant difference in the baseline information between the 2 data groups (P > .05). Age, race, marital status, AJCC stage, surgery, radiotherapy, chemotherapy, and distant metastasis were found to be influential factors for OS using COX regression analysis, and we used these influences to construct prognostic nomograms for OS. The same method was then used to screen the independent prognostic influences affecting CSS were age, marital status, AJCC stage, surgery, radiotherapy, chemotherapy, and distant metastasis, and prognostic nomograms for CSS were constructed using these factors. The prognostic models for OS and CSS were validated using ROC curves, C-indexes, correction curves, and DCA curves after the construction was completed, proving the accuracy and reliability of our models. This prediction model can more accurately predict the prognosis of female lung adenocarcinoma patients.