Risk prediction model based on laboratory indicators for disease progression in patients with early-stage lung adenocarcinoma after surgery

LUO Lifeng; TIAN Feng; CAO Wanying

doi:10.3969/j.issn.1009-0460.2025.01.008

Abstract：Objective To investigate the risk factors of disease progression in patients with early-stage lung adenocarcinoma after surgery and construct risk prediction model based on laboratory indicators.Methods A total of 213 patients with early-stage lung adenocarcinoma after surgery from January 2017 to January 2020 were retrospectively reviewed and were divided into progression group and non-progression group according to whether there was disease progression after surgery or not.Risk factors for disease progression after operation of early lung adenocarcinoma was analyzed by Logistic multivariate model.Construction and efficacy analysis of risk prediction model for disease progression after operation of early lung adenocarcinoma was performed by receiver operating characteristic(ROC)curve.Results There were 41 cases in all 213 patients with early lung adenocarcinoma developed disease progression after surgery,with disease progression rate of 19.2%.The results of univariate analysis showed that the maximum lesion diameter,preoperative serum CEA level,preoperative NLR level and preoperative prognostic nutrition index were related to the postoperative disease progression of early lung adenocarcinoma(P<0.05).Logistic multivariate analysis showed that maximum lesion diameter,preoperative serum CEA level,preoperative NLR level and preoperative prognostic nutrition index were all independent factors for postoperative disease progression of early lung adenocarcinoma(P<0.05).The independent influencing factors of Logistic regression model and the prediction probability of P-value were used to predict the risk of postoperative disease progression of early lung adenocarcinoma.The area under the curve was 0.756,0.688,0.773,0.623 and 0.903,respectively.Conclusion The postoperative disease progression of early lung adenocarcinoma are independently related to the maximum lesion diameter,preoperative serum CEA level,NLR level and prognostic nutritional index.The data model constructed by using the above four factors has shown good efficacy in predicting postoperative disease progression,which is worthy of further analysis.