Zhang Xiaoqing, Zhao Hongling, Zhang Shuo, Li Runzhi
Collaborative Innovation Center of Internet Healthcare, Zhengzhou University, Zhengzhou, China.
Front Genet. 2019 Apr 24;10:351. doi: 10.3389/fgene.2019.00351. eCollection 2019.
Chronic diseases are one of the biggest threats to human life. It is clinically significant to predict the chronic disease prior to diagnosis time and take effective therapy as early as possible. In this work, we use problem transform methods to convert the chronic diseases prediction into a multi-label classification problem and propose a novel convolutional neural network (CNN) architecture named GroupNet to solve the multi-label chronic disease classification problem. Binary Relevance (BR) and Label Powerset (LP) methods are adopted to transform multiple chronic disease labels. We present the correlated loss as the loss function used in the GroupNet, which integrates the correlation coefficient between different diseases. The experiments are conducted on the physical examination datasets collected from a local medical center. In the experiments, we compare GroupNet with other methods and models. GroupNet outperforms others and achieves the best accuracy of 81.13%.
慢性病是对人类生命的最大威胁之一。在诊断前预测慢性病并尽早采取有效治疗具有重要的临床意义。在这项工作中，我们使用问题转换方法将慢性病预测转换为多标签分类问题，并提出了一种名为GroupNet的新型卷积神经网络（CNN）架构来解决多标签慢性病分类问题。采用二元相关性（BR）和标签幂集（LP）方法来转换多个慢性病标签。我们提出相关损失作为GroupNet中使用的损失函数，它整合了不同疾病之间的相关系数。实验是在从当地医疗中心收集的体检数据集上进行的。在实验中，我们将GroupNet与其他方法和模型进行了比较。GroupNet表现优于其他方法，达到了81.13%的最佳准确率。
