论文部分内容阅读
目的运用支持向量机(SVM)建立预测鼻咽癌患者5年生存状态的预测模型,并与医学领域中广泛运用的人工神经网络(ANN)模型进行比较,探索鼻咽癌预后研究的新方法。方法收集2005年1月至2007年12月医院诊治的130例鼻咽癌患者的临床资料,分为两组,一组作为训练样本,用于筛选变量及建立预测模型,计104例;一组作为验证样本,用于评价模型效果,计26例。采用单因素分析筛选建模变量,然后利用ANN及SVM建立鼻咽癌患者5年生存状态预测模型并评价其效果。结果单因素分析显示,年龄、T分期、N分期、M分期、92福州分期、卡氏生活质量评分(KPS评分)、颅底骨质破坏、颅神经损伤、咽旁间隙侵犯、确诊到放疗时间、鼻咽疗效、颈部淋巴结疗效共12项指标与鼻咽癌患者的5年生存状态相关(P<0.05)。验证组验证显示,ANN模型预测患者5年生存状态的准确率、敏感度和特异度分别为88.5%,87.5%和90.0%,而SVM模型预测患者5年生存状态的准确率、敏感度和特异度分别为96.2%,93.8%和100%。结论采用SVM预测模型能较好地判断鼻咽癌患者5年后的生存状态,为个体化地预测患者的预后提供了一种新方法,其效能优于ANN预测模型。
Objective To establish a prediction model predicting the 5-year survival status of patients with nasopharyngeal carcinoma using Support Vector Machine (SVM) and compare with the widely used artificial neural network (ANN) model in the medical field to explore a new method for the prognosis research of nasopharyngeal carcinoma. Methods The clinical data of 130 patients with nasopharyngeal carcinoma who were hospitalized from January 2005 to December 2007 were collected and divided into two groups. One group was used as a training sample for screening variables and establishing a predictive model, and 104 cases were included. One group As a verification sample, used to evaluate the model effect, accounting for 26 cases. The univariate analysis was used to screen the model variables. Then ANN and SVM were used to establish the 5-year survival prediction model of NPC and evaluate the effect. Results Univariate analysis showed that age, T stage, N stage, M stage, 92 Fuzhou stage, Karnofsky quality of life score (KPS score), skull base bone destruction, cranial nerve injury, parapharyngeal space invasion were confirmed to radiotherapy time , Nasopharyngeal efficacy and curative effect of cervical lymph node were all associated with 5-year survival of patients with nasopharyngeal carcinoma (P <0.05). Verification group validation showed that the accuracy, sensitivity and specificity of the ANN model in prediction of 5-year survival were 88.5%, 87.5% and 90.0%, respectively, whereas the accuracy, sensitivity and specificity of the SVM model in predicting the 5-year survival of patients Degrees were 96.2%, 93.8% and 100% respectively. Conclusion SVM prediction model can better determine the survival status of patients with nasopharyngeal carcinoma after 5 years, which provides a new method for individual prognosis prognosis of patients with NPC. Its efficacy is superior to ANN prediction model.