【摘要】 目的:利用神经网络模型分析方法探索类风湿性关节炎(rheumatoid arthritis, ra)证候疾病信息对疗效的预测作用。方法:397例确诊为活动期ra的病例来自9个临床中心,随机分成中药治疗组203例和西药治疗组194例。西药治疗方案包括非甾体抗炎药和慢作用药,中药治疗包括基础治疗和辨证用药。治疗前后收集患者中医四诊信息和西医疾病诊查指标,治疗效果用美国风湿病学会20%改善标准(the american college of rheumatology 20, acr20)判断,抽取患者初诊时的信息进行分析,分析方法在sas 8.2上实施。通过单因素探索性分析,计算疗效与变量的比数比,以p<0.2作为入选模型的标准;采用神经网络模型进行数据分析,以疗效为分层变量,随机将数据集分为训练集(占75%)和验证集(占25%),对分析方法进行验证。结果:数据分析模型中,中药治疗组共纳入18个变量,西药治疗组纳入24个变量。中药治疗组中,晨僵、关节肿胀数、免疫球蛋白m、关节压痛数、关节压痛、类风湿因子、c反应蛋白和关节疼痛等与疗效正相关,病程和夜尿多与疗效呈负相关。西药治疗组中,血沉、腰膝酸软、苔白、关节疼痛、屈伸不利和关节肿胀等与疗效呈正相关,苔黄、舌红、白细胞检测与疗效呈负相关。在随机选取的验证集患者中,神经网络模型的预测作用表现为:ra中药治疗方案使用中,可预测20%患者有效率达到90%;ra西药治疗方案使用中,可预测20%患者有效率达到100%。结论:根据证候疾病信息与中西医疗法疗效的临床数据所建立的神经网络模型,能够显示证病信息对疗效的预测作用。 【关键词】 神经网络模型; 类风湿关节炎; 预测; 数据分析 predictive role of diagnostic information in treatment efficacy of rheumatoid arthritis based on neural network model analysis qinglin zha1, yiting he2, xiaoping yan3, li su4, yuejin song5, shengping zeng6, wei liu7, xinghua feng8, xian qian9, wanhua zhu10, seqi lin1, cheng l11, aiping l11, 12 1. national center of pharmaceutical engineering research, jiangxi university of traditional chinese medicine, nanchang, jiangxi province 330006, china 2. department of clinical epidemiology, second affiliated hospital, guangdong university of traditional chinese medicine, guangzhou, guangdong province 510120, china 3. department of rheumatology, chinajapan friendship hospital, beijing 100029, china 4. department of rheumatology, longhua hospital, shanghai university of traditional chinese medicine, shanghai 200032, china 5. hubei academy of traditional chinese medicine, wuhan, hubei province 430074, china 6. department of rheumatology, affiliated hospital, chengdu university of traditional chinese medicine, chengdu, sichuan province 610075, china 7. department of rheumatology, first affiliated hospital, tianjin college of traditional chinese medicine, tianjin 300193, china 8. department of rheumatology, guang'anmen hospital, china academy of chinese medicial sciences, beijing 100053, china 9. department of rheumatology, jiangsu provincial hospital of traditional chinese medicine, nanjing, jiangsu province 210029, china 10. nantong liangchun clinical research institute of traditional chinese medicine, nantong, jiangsu province 226000, china 11. institute of basic theory, china academy of chinese medicial sciences, beijing 100700, china 12. einstitute of shanghai education committee, shanghai university of traditional chinese medicine, shanghai 201203, china objective: to analyze the indications of the therapies for rheumatoid arthritis (ra) with neural network model analysis. |
|
来自: johnney908 > 《精读文章》