Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (2): 411-417.DOI: 10.11772/j.issn.1001-9081.2023030260
• Artificial intelligence • Previous Articles
Kaitian WANG1, Qing YE1,2(), Chunlei CHENG1,2
Received:
2023-03-16
Revised:
2023-05-25
Accepted:
2023-05-26
Online:
2023-07-05
Published:
2024-02-10
Contact:
Qing YE
About author:
WANG Kaitian, born in 1999, M. S. candidate. His research interests include natural language processing, data mining.Supported by:
通讯作者:
叶青
作者简介:
王楷天(1999—),男,黑龙江牡丹江人,硕士研究生,主要研究方向:自然语言处理、数据挖掘基金资助:
CLC Number:
Kaitian WANG, Qing YE, Chunlei CHENG. Classification method for traditional Chinese medicine electronic medical records based on heterogeneous graph representation[J]. Journal of Computer Applications, 2024, 44(2): 411-417.
王楷天, 叶青, 程春雷. 基于异构图表示的中医电子病历分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 411-417.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023030260
信息类别 | 内容 |
---|---|
性别 | 女 |
望诊 | 面色偏滞;形体稍胖,神情平静,语速偏快、话多 |
脉诊 | 脉略滑,右脉边界欠清,左关稍旺,左寸上略浮 |
舌诊 | 舌质偏暗青,苔淡黄稍厚 |
查体 | 咽壁滤泡,分泌物多 |
主诉 | 右耳鸣半月余 |
中医诊断 | 感冒 |
Tab. 1 Example of TCM electronic medical records
信息类别 | 内容 |
---|---|
性别 | 女 |
望诊 | 面色偏滞;形体稍胖,神情平静,语速偏快、话多 |
脉诊 | 脉略滑,右脉边界欠清,左关稍旺,左寸上略浮 |
舌诊 | 舌质偏暗青,苔淡黄稍厚 |
查体 | 咽壁滤泡,分泌物多 |
主诉 | 右耳鸣半月余 |
中医诊断 | 感冒 |
真实情况 | 预测情况 | |
---|---|---|
预测为该疾病 | 预测不为该疾病 | |
预测准确 | TP | TN |
预测错误 | FP | FN |
Tab. 2 Confusion matrix
真实情况 | 预测情况 | |
---|---|---|
预测为该疾病 | 预测不为该疾病 | |
预测准确 | TP | TN |
预测错误 | FP | FN |
参数名 | 符号 | 值 |
---|---|---|
GCN学习率 | gcn_lr | 0.05 |
GCN权重衰减 | gcn_weight_decay | 10-5 |
GCN隐藏层特征维度 | n_hidden | 32 |
PMI阈值 | p | 0 |
LERT学习率 | lert_lr | 10-5 |
LERT权重衰减 | lert_weight_decay | 10-4 |
batch大小 | batch_size | 128 |
权重 | λ | 0.5 |
迭代次数 | epoch | 200 |
Tab. 3 Super parameter setting
参数名 | 符号 | 值 |
---|---|---|
GCN学习率 | gcn_lr | 0.05 |
GCN权重衰减 | gcn_weight_decay | 10-5 |
GCN隐藏层特征维度 | n_hidden | 32 |
PMI阈值 | p | 0 |
LERT学习率 | lert_lr | 10-5 |
LERT权重衰减 | lert_weight_decay | 10-4 |
batch大小 | batch_size | 128 |
权重 | λ | 0.5 |
迭代次数 | epoch | 200 |
模型 | 精确率 | 召回率 | F1 | AUC |
---|---|---|---|---|
LSTM | 0.666 5 | 0.664 8 | 0.663 1 | 0.882 9 |
Text-GCN | 0.749 5 | 0.750 9 | 0.748 3 | 0.930 7 |
LERT | 0.767 4 | 0.763 6 | 0.763 0 | 0.915 2 |
Text_CNN | 0.724 0 | 0.723 6 | 0.721 2 | 0.924 6 |
Text_RNN | 0.690 8 | 0.685 5 | 0.684 9 | 0.915 9 |
FastText | 0.725 0 | 0.714 5 | 0.713 4 | 0.937 3 |
TCM-GCN | 0.784 6 | 0.781 8 | 0.780 7 | 0.927 2 |
Tab. 4 Result comparison of different models
模型 | 精确率 | 召回率 | F1 | AUC |
---|---|---|---|---|
LSTM | 0.666 5 | 0.664 8 | 0.663 1 | 0.882 9 |
Text-GCN | 0.749 5 | 0.750 9 | 0.748 3 | 0.930 7 |
LERT | 0.767 4 | 0.763 6 | 0.763 0 | 0.915 2 |
Text_CNN | 0.724 0 | 0.723 6 | 0.721 2 | 0.924 6 |
Text_RNN | 0.690 8 | 0.685 5 | 0.684 9 | 0.915 9 |
FastText | 0.725 0 | 0.714 5 | 0.713 4 | 0.937 3 |
TCM-GCN | 0.784 6 | 0.781 8 | 0.780 7 | 0.927 2 |
实验 | 构图方法 | 精确率 | 召回率 | F1 | AUC |
---|---|---|---|---|---|
1 | LERT+one-hot+PMI | 0.771 5 | 0.770 9 | 0.770 0 | 0.916 2 |
2 | LERT+ BW25 | 0.763 4 | 0.761 8 | 0.760 5 | 0.906 2 |
3 | BW25+PMI | 0.767 1 | 0.765 5 | 0.764 3 | 0.913 3 |
4 | LERT+TF-IDF+PMI | 0.774 1 | 0.772 7 | 0.771 4 | 0.916 2 |
5 | LERT+BW25+PMI | 0.784 6 | 0.781 8 | 0.780 7 | 0.927 2 |
Tab. 5 Results of ablation experiments
实验 | 构图方法 | 精确率 | 召回率 | F1 | AUC |
---|---|---|---|---|---|
1 | LERT+one-hot+PMI | 0.771 5 | 0.770 9 | 0.770 0 | 0.916 2 |
2 | LERT+ BW25 | 0.763 4 | 0.761 8 | 0.760 5 | 0.906 2 |
3 | BW25+PMI | 0.767 1 | 0.765 5 | 0.764 3 | 0.913 3 |
4 | LERT+TF-IDF+PMI | 0.774 1 | 0.772 7 | 0.771 4 | 0.916 2 |
5 | LERT+BW25+PMI | 0.784 6 | 0.781 8 | 0.780 7 | 0.927 2 |
1 | 俞华,陶正玄,赵英英.围手术期智能临床辅助决策系统的构建与应用[J].中国卫生信息管理杂志,2022,19(6):911-917. 10.3969/j.issn.1672-5166.2022.06.022 |
YU H, TAO Z X, ZHAO Y Y. Construction and application of preoperative period intelligent clinical decision support system[J]. Chinese Journal of Health Informatics and Management,2022,19(6):911-917. 10.3969/j.issn.1672-5166.2022.06.022 | |
2 | 张文博,陈希,张美霞,等.考虑适应性达成过程的慢性疾病个性化辅助决策方法[J].系统工程, 2023, 41(4): 127-136. |
ZHANG W B, CHEN X, ZHANG M X, et al. A personalized assistant-decision making method for chronic diseases considering the adaptive reaching process[J]. Systems Engineering, 2023, 41(4): 127-136. | |
3 | 王红迁,汪鹏,王飞,等.多元数据融合的临床辅助决策系统的研究与应用[J].中国数字医学,2019,14(11):18-20. 10.3969/j.issn.1673-7571.2019.11.005 |
WANG H Q, WANG P, WANG F, et al. Research and application of clinical decision support system based on multivariate data fusion[J]. China Digital Medicine, 2019,14(11):18-20. 10.3969/j.issn.1673-7571.2019.11.005 | |
4 | YANG R, YE Q, CHENG C, et al. Decision-making system for the diagnosis of syndrome based on traditional Chinese medicine knowledge graph[J]. Evidence-Based Complementary and Alternative Medicine, 2022, 2022: No.8693937. 10.1155/2022/8693937 |
5 | RUAN C, WU Y, YANG Y, et al. Semantic-aware graph convolutional networks for clinical auxiliary diagnosis and treatment of traditional Chinese medicine[J]. IEEE Access, 2021, 9: 8797-8807. 10.1109/access.2020.3048932 |
6 | 张玉洁,白如江,许海云,等.融合多自然语言处理任务的中医辅助诊疗方案研究——以糖尿病为例[J].数据分析与知识发现,2022,6(1):122-133. |
ZHANG Y J, BAI R J, XU H Y, et al. Assisted TCM diagnosis and treatment for diabetes with multi NLP tasks[J]. Data Analysis and Knowledge Discovery, 2022, 6(1): 122-133. | |
7 | 蔡秀军, 林辉, 乔凯, 等.智能辅助决策支持系统在临床诊疗决策中的应用研究[J].中国数字医学, 2019, 14(3): 111-113. 10.3969/j.issn.1673-7571.2019.03.031 |
CAI X J, LIN H, QIAO K, et al. Research on the application of the intelligent decision-aid support system in clinical diagnosis and treatment decision support[J]. China Digital Medicine, 2019, 14(3): 111-113. 10.3969/j.issn.1673-7571.2019.03.031 | |
8 | CUI Y, CHE W, WANG S, et al. LERT: a linguistically-motivated pre-trained language model [EB/OL]. [2023-02-17]. . |
9 | DOGRA V, VERMA S, CHATTERJEE P, et al. A complete process of text classification system using state-of-the-art NLP models[J]. Computational Intelligence and Neuroscience, 2022, 2022: No.1883698. 10.1155/2022/1883698 |
10 | KIM Y. Convolutional neural networks for sentence classification[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsberg: ACL, 2014: 1746-1751. 10.3115/v1/d14-1181 |
11 | DEVLIN J, CHANG M-W, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding [EB/OL]. [2022-08-17]. . 10.18653/v1/n18-2 |
12 | KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks [EB/OL]. [2022-10-21]. . 10.48550/arXiv.1609.02907 |
13 | YAO L, MAO C, LUO Y. Graph convolutional networks for text classification[C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2019: 7370-7377. 10.1609/aaai.v33i01.33017370 |
14 | LIN Y, MENG Y, SUN X, et al. BertGCN: Transductive text classification by combining GCN and BERT [EB/OL]. [2023-01-22]. . 10.18653/v1/2021.findings-acl.126 |
15 | 李明浩,刘忠,姚远哲.基于LSTM-CRF的中医医案症状术语识别[J].计算机应用,2018,38(S2):42-46. |
LI M H, LIU Z, YAO Y Z. LSTM-CRF based symptom term recognition on traditional Chinese medical case[J]. Journal of Computer Applications, 2018, 38(S2): 42-46. | |
16 | 杜琳,曹东,林树元,等.基于BERT与Bi-LSTM融合注意力机制的中医病历文本的提取与自动分类[J].计算机科学,2020,47(S2):416-420. 10.11896/jsjkx.200200020 |
DU L, CAO D, LIN S Y, et al. Extraction and automatic classification of TCM medical records based on attention mechanism of BERT and Bi-LSTM[J]. Computer Science, 2020,47(S2):416-420. 10.11896/jsjkx.200200020 | |
17 | WU F, SOUZA A, ZHANG T, et al. Simplifying graph convolutional networks[C]// Proceedings of the 36th International Conference on Machine Learning. New York: PMLR, 2019, 97: 6861-6871. 10.48550/arXiv.1902.07153 |
18 | CHE W, FENG Y, QIN L, et al. N-LTP: an open-source neural language technology platform for Chinese [EB/OL]. [2022-11-19]. . 10.18653/v1/2021.emnlp-demo.6 |
19 | LOSHCHILOV I, HUTTER F. SGDR: stochastic gradient descent with restarts [EB/OL]. [2022-03-19]. . |
20 | VINYALS O, BLUNDELL C, LILLICRAP T, et al. Matching networks for one shot learning[C]// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2016: 3637-3645. |
21 | LIU P, QIU X, HUANG X. Recurrent neural network for text classification with multi-task learning [EB/OL]. [2023-01-22]. . 10.18653/v1/d16-1012 |
22 | JOULIN A, GRAVE E, BOJANOWSKI P, et al. Bag of tricks for efficient text classification [EB/OL]. [2022-12-29]. . 10.18653/v1/e17-2068 |
[1] | Jiawei ZHANG, Guandong GAO, Ke XIAO, Shengzun SONG. Violent crime hierarchy algorithm by joint modeling of improved hierarchical attention network and TextCNN [J]. Journal of Computer Applications, 2024, 44(2): 403-410. |
[2] | Chenghao FENG, Zhenping XIE, Bowen DING. Selective generation method of test cases for Chinese text error correction software [J]. Journal of Computer Applications, 2024, 44(1): 101-112. |
[3] | Hanxiao SHI, Leichun WANG. Short-term power load forecasting by graph convolutional network combining LSTM and self-attention mechanism [J]. Journal of Computer Applications, 2024, 44(1): 311-317. |
[4] | Xinyue ZHANG, Rong LIU, Chiyu WEI, Ke FANG. Aspect-based sentiment analysis method with integrating prompt knowledge [J]. Journal of Computer Applications, 2023, 43(9): 2753-2759. |
[5] | Bihui YU, Xingye CAI, Jingxuan WEI. Few-shot text classification method based on prompt learning [J]. Journal of Computer Applications, 2023, 43(9): 2735-2740. |
[6] | Xiaomin ZHOU, Fei TENG, Yi ZHANG. Automatic international classification of diseases coding model based on meta-network [J]. Journal of Computer Applications, 2023, 43(9): 2721-2726. |
[7] | Guoshuai MA, Yuhua QIAN, Yayu ZHANG, Junxia LI, Guoqing LIU. Scientific collaboration potential prediction based on dynamic heterogeneous information fusion [J]. Journal of Computer Applications, 2023, 43(9): 2775-2783. |
[8] | Yumeng CUI, Jingya WANG, Xiaowen LIU, Shangyi YAN, Zhizhong TAO. General text classification model combining attention and cropping mechanism [J]. Journal of Computer Applications, 2023, 43(8): 2396-2405. |
[9] | Zexi JIN, Lei LI, Ji LIU. Transfer learning model based on improved domain separation network [J]. Journal of Computer Applications, 2023, 43(8): 2382-2389. |
[10] | Yuan WEI, Yan LIN, Shengnan GUO, Youfang LIN, Huaiyu WAN. Prediction of taxi demands between urban regions by fusing origin-destination spatial-temporal correlation [J]. Journal of Computer Applications, 2023, 43(7): 2100-2106. |
[11] | Yi ZHANG, Gangsheng CAI, Zhenmei WANG. Long non-coding RNA-disease association prediction model based on semantic and global dual attention mechanism [J]. Journal of Computer Applications, 2023, 43(7): 2125-2132. |
[12] | Yao LIU, Xin TONG, Yifeng CHEN. Algorithm path self-assembling model for business requirements [J]. Journal of Computer Applications, 2023, 43(6): 1768-1778. |
[13] | Kejun JIN, Hongtao YU, Yiteng WU, Shaomei LI, Jianpeng ZHANG, Honghao ZHENG. Improved defense method for graph convolutional network based on singular value decomposition [J]. Journal of Computer Applications, 2023, 43(5): 1511-1517. |
[14] | Senqi YANG, Xuliang DUAN, Zhan XIAO, Songsong LANG, Zhiyong LI. Text classification of agricultural news based on ERNIE+DPCNN+BiGRU [J]. Journal of Computer Applications, 2023, 43(5): 1461-1466. |
[15] | Xu ZHANG, Long SHENG, Haifang ZHANG, Feng TIAN, Wei WANG. Pre-hospital emergency text classification model based on label confusion [J]. Journal of Computer Applications, 2023, 43(4): 1050-1055. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||