基于标签噪声鲁棒学习的疾病风险预测  

Disease Risk Prediction Based on Label Noise Robust Learning

作　　者：郭雨茜 李华玲 GUO Yu-Xi;LI Hua-Ling(School of Software,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学软件学院,太原030051

出　　处：《计算机系统应用》2023年第10期184-191,共8页Computer Systems & Applications

基　　金：山西省重点研发计划(202102020101009)。

摘　　要：疾病风险预测能够筛查易患人群,并在早期进行预防干预措施以降低疾病的发生率及死亡率.随着机器学习技术的快速发展,基于机器学习的疾病风险预测得到了广泛应用.然而,机器学习十分依赖于高质量的标注信息,医疗数据中存在的标签噪声会给构建高性能的疾病风险预测算法带来严峻挑战.针对这一问题,本文提出了一种基于深度神经网络和动态截断损失函数的噪声鲁棒学习方法用于疾病风险预测.该方法引入动态截断损失函数,融合了传统交叉熵函数的隐式加权特性和均方差损失函数的标签噪声鲁棒性;通过构造训练损失下界,并引入样本动态加权机制减小可疑样本的梯度,限制可能的带噪样本在训练过程中的权重,进一步增强模型的鲁棒性.以脑卒中筛查数据集为例进行实验,结果表明本文算法在各个标签噪声比例下均能取得良好的预测性能,可降低疾病风险预测中标签噪声的负面影响,实现了带有标签噪声数据的鲁棒学习.Disease risk prediction enables the screening of vulnerable populations and early preventive interventions to reduce disease incidence and mortality.With the rapid development of machine learning technologies,disease risk prediction based on machine learning has been widely used.However,machine learning is highly dependent on highquality labeling information,and the label noise in medical data will bring severe challenges to the construction of highperformance disease risk prediction algorithms.In order to solve this problem,a noise robustness learning method based on a deep neural network and dynamic truncation loss function is proposed for disease risk prediction.The dynamic truncation loss function is introduced in this method,which combines the implicit weighting characteristics of the traditional cross entropy function and the label noise robustness of the mean square error loss function.By constructing a training loss lower bound and introducing a dynamic sample weighting mechanism to reduce the gradient of suspicious samples,the weight of possible noisy samples in the training process is limited,and the robustness of the model is further enhanced.By taking the stroke screening dataset as an example,the experimental results show that the proposed algorithm can achieve excellent prediction performance under each ratio of label noises,reduce the negative impact of label noises in disease risk prediction,and realize robust learning of data with label noises.

关 键 词：标签噪声 鲁棒学习 疾病风险预测 深度学习 

分 类 号：R319[医药卫生—基础医学] TP18[自动化与计算机技术—控制理论与控制工程]