基于PSODE-LSTM模型的桥本甲状腺炎风险预测  

Risk Prediction of Hashimoto's Thyroiditis Based on PSODE-LSTM Model

作　　者：李瑞灵 光彪 赵玉凤[2] 马利 LI Rui-ling;GUANG Biao;ZHAO Yu-feng;MA Li(College of Information Engineering,Hubei University of Chinese Medicine,Wuhan Hubei 430065,China;National Data Center of Traditional Chinese Medicine,China Academy of Chinese Medical Sciences,Beijing 100700,China)

机构地区：[1]湖北中医药大学信息工程学院,湖北武汉430065 [2]中国中医科学院中医药数据中心,北京100700

出　　处：《计算机仿真》2024年第12期357-361,共5页Computer Simulation

基　　金：国家自然科学面向基金项目(81674101)。

摘　　要：为了提高桥本甲状腺炎不良结局风险的预测精度,提出一种改进粒子群(PSO)算法优化长短期记忆神经网络(LSTM)的风险预测模型。针对PSO算法存在陷入局部最优的问题,引入差分进化(DE)算法的变异、交叉和选择算子,并采用随机惯性权重和动态学习因子,有效平衡算法的全局搜索能力和局部搜索能力。将改进算法获得的最优参数组合用于LSTM的参数优化,提高模型的预测性能。通过对2018年6月至2021年12月医院桥本甲状腺炎患者门诊信息进行预处理和仿真,结果表明PSODE-LSTM模型较LSTM模型、PSO-LSTM模型及DE-LSTM模型具有更优的预测性能。In order to improve the prediction accuracy of adverse outcome risk for Hashimoto's thyroiditis(HT),a risk prediction model based on improved particle swarm optimization(PSO)and optimized long short-term memory(LSTM)is proposed.Aiming at the problem that the PSO algorithm is easy to fall into local optimization,mutation,crossover and selection operations of differential evolution(DE),random inertia weight and dynamic learning factor are introduced,so as to effectively balance the global and local search ability of the algorithm.Through pre-processing and simulation experiments on the outpatient information of HT patients in the hospital from June 2018 to December 2021,the results show that the PSODE-LSTM model has better prediction performance than the LSTM model,PSOLSTM model and DE-LSTM model.

关 键 词：粒子群优化算法 差分进化算法 长短期记忆神经网络 桥本甲状腺炎 风险预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]