English

应用科学学报 >

2023 , Vol. 41 >Issue 1: 41 - 54

DOI: https://doi.org/10.3969/j.issn.0255-8297.2023.01.004

计算机应用专辑

基于深度学习的医疗电子数据特征学习方法

展开
  • 1. 中国农业科学院 农业信息研究所, 北京 100081;
    2. 农业农村部 农业大数据重点实验室, 北京 100081;
    3. 96962 部队, 北京 102206

收稿日期: 2022-07-01

  网络出版日期: 2023-02-03

基金资助

中国农业科学院协同创新任务基金（No.CAAS-ASTIP-2016-AII）；国家科技文献信息中心专项基金（No.2022XM2805）；2022年现代农业产业技术体系北京市创新团队建设项目基金（No.BAIC10-2022-E10）；中国国家留学基金委项目基金（No.201803250020）资助

收起

Medical Electronic Data Feature Learning Method Based on Deep Learning

Expand
  • 1. Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, China;
    2. Key Laboratory of Big Agri-data, Ministry of Agriculture and Rural Areas, Beijing 100081, China;
    3. Unit 96962, Beijing 102206, China

Received date: 2022-07-01

  Online published: 2023-02-03

Fold

摘要

面向高维异构的医疗电子数据，如何才能有效开展特征学习以优化患者联合用药不良预后的风险预测？针对此问题，提出一种基于深度学习的医疗电子数据特征学习方法。首先结合深度学习长短期记忆网络模型和深度稀疏自动编码模型学习具有时序特性的患者联合用药数据的特征表示，并通过二分k-均值聚类方法形成联合用药综合表达因子。然后构建风险预测特征向量和风险相关特征向量，分别用于联合用药的不良预后风险预测和风险相关性分析。最后将该方法与已有的传统方法在真实医疗电子数据集上进行对比实验，结果表明：该方法在患者联合用药的不良预后风险预测中，准确率比传统方法提高了5%~ 10%，误判率降低了3%~ 5%，具有较好的风险预测性能。

关键词： 深度学习; 特征学习; 医疗电子数据; 联合用药; 不良事件

本文引用格式

王婷, 王娜, 崔运鹏, 刘娟 . 基于深度学习的医疗电子数据特征学习方法[J]. 应用科学学报, 2023 , 41(1) : 41 -54 . DOI: 10.3969/j.issn.0255-8297.2023.01.004

Abstract

How can we effectively carry out the feature learning of high-dimensional and heterogeneous medical electronic data to optimize the risk prediction of concurrent medical use in patients? To address the problem, this paper proposed a method of multi-stage deep feature learning. Firstly, we performed the feature learning of medical use data with temporal properties by combining deep learning models of long short-term memory (LSTM) and auto-encoder (AE), and generated the synthetic factor of concurrent medical use with bisecting k-means clustering method. Secondly, we constructed two types of feature vectors for patients to predict adverse event risk, and analyzed the associated factors of high risk. Finally, we compared the performance of the proposed method with existing methods on real-word dataset, and the results show that the proposed method increases the accuracy by 5%~10%, and reduces the false rate by 3%~5% in the risk prediction of concurrent medical use.

Key words： deep learning; feature learning; medical electronic data; concurrent medical use; adverse events

参考文献

[1] Shen Y, Zhang L, Zhang J, et al. CBN:constructing a clinical Bayesian network based on data from the electronic medical record[J]. Journal of Biomedical Informatics, 2018, 88:1-10.
[2] Gao X T, Stephen L, Wong Y T. Automatic feature learning to grade nuclear cataracts based on deep learning[J]. IEEE Transactions on Biomedical Engineering, 2015, 62(11):2693-2701.
[3] Cirean D C, Giusti A, Gambardella L M, et al. Mitosis detection in breast cancer histology images with deep neural networks[C]//2013 International Conference on Medical Image Computing and Computer-Assisted Intervention, 2018:1-8.
[4] Suk H I, Lee S W, Shen D, et al. Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis[J]. Neuroimage, 2014, 101:569-582.
[5] Ithapu V K, Singh V, Okonkwo O C, et al. Imaging-based enrichment criteria using deep learning algorithms for efficient clinical trials in mild cognitive impairment[J]. The Journal of the Alzheimers Association, 2015, 11(12):1489-1499.
[6] Suk H II, Lee S W, Shen D. Deep sparse multi-task learning for feature selection in Alzheimer's disease diagnosis[J]. Brain Structure & Function, 2016, 221(5):2569-2587.
[7] Suk H I, Lee S W, Shen D. Latent feature representation with stacked auto-encoder for AD/MCI diagnosis[J]. Brain Structure & Function, 2013, 220(2):841-859.
[8] Wee C Y, Liu C, Lee A, et al. Cortical graph neural network for AD and MCI diagnosis and transfer learning across populations[J]. NeuroImage:Clinical, 2019, 23:19-29.
[9] Agah A. Medical applications of artificial intelligence[EB/OL]. (2013-10-30)[2022-10-15]. https://doi.org/10.1201/b15618.
[10] Xu J, Lei X, Hang R L, et al. Stacked sparse autoencoder for nuclei detection on breast cancer histopathology images[J]. IEEE Transactions on Medical Imaging, 35(1):19-30.
[11] Fakoor R, Ladhak F, Nazi A, et al. Using deep learning to enhance cancer diagnosis and classification[R/OL]. (2013-06-10)[2022-10-15]. https://www.researchgate.net/publication/281857285_Using_deep_learning_to_enhance_cancer_diagnosis_and_classification.
[12] Zuluaga G J, Almasry Z, Benaggoune K, et al. A CNN-based methodology for breast cancer diagnosis using thermal images[J]. Computer Methods in Biomechanics and Biomedical Engineering:Imaging & Visualization, 2021, 9(2):131-145.
[13] Shamshirband S, Fathi M, Dehzangi A, et al. A review on deep learning approaches in healthcare systems:taxonomies, challenges, and open issues[J]. Journal of Biomedical Informatics, 2021, 113:27-36.
[14] Liu G P, Yan J J, Wang Y Q, et al. Deep learning based syndrome diagnosis of chronic gastritis[J]. Computational and Mathematical Methods in Medicine, 2014:1-8.
[15] Ikenoyama Y, Hirasawa T, Ishioka M, et al. Detecting early gastric cancer:comparison between the diagnostic ability of convolutional neural networks and endoscopists[J]. Digestive Endoscopy, 2021, 33(1):141-150.
[16] Kumar D, Wong A, Clausi D A. Lung nodule classification using deep features in CT images[J]. Wireless Personal Communications, 2015, 116(2021):655-690.
[17] Ma J, Sheridan R P, Liaw A, et al. Deep neural nets as a method for quantitative structure-activity relationships[J]. Journal of Chemical Information & Modeling, 2015, 55(2):263-274.
[18] Bhinder B, Gilvary C, Madhukar N S, et al. Artificial intelligence in cancer research and precision medicine[J]. Cancer Discovery, 2021, 11(4):900-915.
[19] Prasoon A, Petersen K, Igel C, et al. Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network[C]//2013 International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Heidelberg:Springer, 2013:246-253.
[20] Song Y, Zhang L, Chen S, et al. A deep learning based framework for accurate segmentation of cervical cytoplasm and nuclei[C]//The 36th Annual International Conference of IEEE Engineering in Medicine and Biology Society, 2014:2903.
[21] Majumdar A. Real-time dynamic MRI reconstruction using stacked denoising autoencoder[R/OL]. (2015-03-22)[2022-10-15]. https://arxiv.org/ftp/arxiv/papers/1503/1503.06383.pdf.
[22] Chaudhari A S, Sandino C M, Cole E K, et al. Prospective deployment of deep learning in MRI:a framework for important considerations, challenges, and recommendations for best practices[J]. Journal of Magnetic Resonance Imaging, 2021, 54(2):357-371.
[23] Zhang W, Li R, Deng H, et al. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation[J]. Neuroimage, 2015, 108:214-224.
[24] Zeng T, Li R J, Mukkamala R, et al. Deep convolutional neural networks for annotating gene expression patterns in the mouse brain[J]. BMC Bioinformatics, 2015, 16:147-157.
[25] Wang D, Shang Y. Modeling physiological data with deep belief networks[J]. International Journal of Information and Education Technology, 2013, 3(5):505-511.
[26] Spencer M, Eickholt J, Jianlin C. A deep learning network approach to ab initio protein secondary structure prediction[J]. IEEE/ACM Transactions on Computational Biology & Bioinformatics, 2015, 12(1):103-112.
[27] Heffernan R, Paliwal K, Lyons J, et al. Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning[J]. Scientific Reports, 2015, 5:47-53.
[28] Zhou J, Troyanskaya O G. Deep supervised and convolutional generative stochastic network for protein secondary structure prediction[J]. Journal of Machine Learning Research, 2014, 32(1):745-753.
[29] Lena P D, Nagata K, Baldi P. Deep architectures for protein contact map prediction[J]. Bioinformatics, 2012, 28(19):2449-2457.
[30] Yuvaraj N, Srihari K, Chandragandhi S, et al. Analysis of protein-ligand interactions of SARS-Cov-2 against selective drug using deep neural networks[J]. Big Data Mining and Analytics, 2021, 4(2):76-83.
[31] Quang D, Chen Y, Xie X. DANN:a deep learning approach for annotating the pathogenicity of genetic variants[J]. Bioinformatics, 2014, 31(5):761-763.
[32] Li J, Pu Y, Tang J, et al. A hybrid category attention neural network for identifying functional effects of DNA sequences[J]. Briefings in Bioinformatics, 2021, 22(3):159-170.
[33] Leung M K K, Xiong H Y, Lee L J, et al. Deep learning of the tissue-regulated splicing code[J]. Bioinformatics, 2014, 30(12):121-129.
[34] Xiong H Y, Alipanahi B, Lee L J, et al. The human splicing code reveals new insights into the genetic determinants of disease[J]. Science, 2015, 347(6218):1254806.
[35] Bhattacharjee S, Ghosh A, Saha B, et al. Machine learning and systems biology in genomics and health[M].[S.l.]:Springer, 2022:69-90.
[36] Tibshirani R, Walther G, Hastie T. Estimating the number of clusters in a data set via the gap statistic[J]. Journal of the Royal Statistical Society:Series B (Statistical Methodology), 2001, 63(2):411-423.
Options
文章导航

/

〈 〉