目的 建立中医药干预治疗晚期结直肠癌的疗效预测模型进行疗效预测。方法 纳入120例晚期结直肠癌患者的人口学诊断、信息、治疗信息等深入观察随访，以生存时间为因变量，其他与生存时间相关的变量作为自变量建立Cox模型。通过Cox模型进行预后因素筛选，选取有显著统计学差异（P < 0.05）的变量包括发病部位、转移部位、基因分型、KPS评分、症状总评分、主症评分、生活质量评分，结合临床经验和描述分析的结果，加入中医证型作为自变量，把前期制定的中医优势、劣势、中间人群划分标准作为因变量进行判别分析，建立4种判别函数，根据模型预测结果选择预测效果最好的二次判别分析（QDA）模型作为最终晚期结直肠癌中医干预治疗疗效预测模型。结果 经验证，模型总的疗效预测准确率为84.2%，在中医劣势人群中的预测准确率为100%。结论 该模型可作为临床预测模型应用于晚期结直肠癌患者的中医药治疗，为进一步探求中医临床决策支持系统奠定相关基础。
Objective To establish a predictive model for the efficacy of traditional Chinese medicine (TCM) intervention in the treatment of advanced colorectal cancer. Methods The demographic, information, and treatment information of 120 patients with advanced colorectal cancer were included in the in-depth observation and follow-up. The survival time was used as the dependent variable, and other variables related to survival time were used as independent variables to establish the Cox proportional hazards model. Prognostic factors were screened by Cox proportional hazards model and variables with significant statistical difference (P < 0.05) including site of tumor incidence, metastatic site, genotyping, KPS scores, TCM symptoms scores, main symptom scores, quality of life scores, combined with clinical experience. And the results of descriptive analysis, adding TCM syndrome differentiation as independent variables, discriminating and analyzing the advantages and disadvantages of TCM formulated in the previous period as the dependent variable, establishing 4 different medical models by discriminant analysis. According to the model prediction results, the quadratic discriminant analysis (QDA) model with the best predictive effect was selected as the predictive model for the efficacy of TCM intervention in advanced colorectal cancer. Results The total accuracy of the model was 84.2%, and the prediction accuracy was 100% in the TCM non-beneficial population. Conclusion The model can be used as a clinical prediction model in the treatment of advanced colorectal cancer patients with TCM, and lay a foundation for further exploring the clinical decision support system (CDSS) of TCM.