DeepDiagnosis: DNN-Based Diagnosis Prediction from Pediatric Big Healthcare Data
DeepDiagnosis: DNN-Based Diagnosis Prediction from Pediatric Big Healthcare Data
复制标题
DeepDiagnosis：基于儿科医疗大数据的 DNN 诊断预测
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Wenbo Chen
中科院分区：
文献类型：
--
作者：
Jia Shi;Xiaoliang Fan;Jinzhun Wu;Jian Chen;Wenbo Chen
挖掘电子病历（EHRs）已被认为是临床诊断的主要决策工具。事实上，由于电子病历的文本书写自由、描述不完整以及疾病的高变异性，很难从电子病历中提取有价值的信息。特别是对于儿科电子病历，由于缺乏经验丰富的儿科医生，以及季节变化、幼儿园交叉感染等复杂的环境因素，使得进行精确诊断极具挑战性。为了解决这些挑战，我们提出了DeepDiagnosis，这是一种基于深度神经网络的诊断预测算法，通过挖掘大量的儿科电子病历。首先，对中文非结构化电子病历数据进行预处理，利用自然语言处理技术将数据转化为句子向量。其次，我们构建双向递归神经网络（BiRNN）模型来捕捉患者的临床症状及其相互作用。最后，我们使用包含81,476个儿科电子病历的真实数据集来训练和评估我们的模型。实验结果表明，该方法优于许多基线方法。
Mining electronic health records (EHRs) has been considered as a major decision-making tool for clinical diagnosis. In fact, it is difficult to extract the valuable information from EHRs due to free-text writing, incomplete description, and high variabilities of diseases. Especially for pediatric EHRs, the shortage of experienced pediatricians as well as complex environmental factors such as seasonal variations, cross infections from kindergartens, make it extremely challenging to conduct a precise diagnosis. To address those challenges, we proposed DeepDiagnosis, a novel deep neural network-based diagnosis prediction algorithm by mining massive pediatric EHRs. First, we pre-process the unstructured EHRs dataset in Chinese and transfer them into sentence vectors by natural language processing technologies. Second, we construct the bidirectional recurrent neural networks (BiRNN) model to catch the patients' clinical symptoms as well as their interaction. Finally, we train and evaluate our model using a real-world dataset containing 81,476 pediatric EHRs. Experimental results show that the proposed method outperforms many baseline methods.
DOI：
--
发表时间：
2016-02
期刊：
ArXiv
影响因子：
--
作者：
E. Choi;A. Schuetz;W. Stewart;Jimeng Sun
通讯作者：
E. Choi;A. Schuetz;W. Stewart;Jimeng Sun