基于贝叶斯网络构建晚期非小细胞肺癌生存预后模型

正根据我国最新发布的全国癌症报告,无论是发病率还是死亡率,肺癌均居于所有恶性肿瘤之首,其中非小细胞肺癌(non-small cell lung cancer,NSCLC)占所有肺癌病例的80%左右。根据2020年美国癌症协会发布的统计数据,高达57%的肺癌患者诊断时即为晚期,其5年生存率仅5.8%~(1])。因此,建立可信度高、预测效果好的NSCLC预后预测评估模型,对于患者的个体化治疗、临床医师决策制定以及社会医疗资源的合理利用具有重要的指导意义。本研究通过大量文献阅读整理出可能有预测作用的因素,

The survival prediction model of advanced non-small cell lung cancer based on Bayesian network

Objective To investigate the clinical value of Bayesian network in predicting survival of patients with advanced non-small cell lung cancer (NSCLC). Methods Patients with advanced NSCLC diagnosed in our hospital from January 2015 to October 2020 were analyzed retrospectively. The clinical manifestations and blood indicators at diagnoses including blood routine, blood biochemistry, coagulation function and tumor markers were included. The Cox regression model was performed to determine prognostic factors. Then, the new prediction model was metastases, lines of treatment, squamous cell carcinoma antigen, age and neutrophil-lymphocyte ratio were included in the survival prediction model, leading to a 69.44% accuracy. Conclusion The survival prediction model based on Bayesian network balancing clinical manifestations and blood indicators at the same time, has a high operability and accuracy, which could be used to guide the decision making and to predict the survival of patients with advanced NSCLC.