Automatic international classification of disease coding method incorporating heterogeneous information

doi:10.11772/j.issn.1001-9081.2023081166

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (8): 2476-2482.DOI: 10.11772/j.issn.1001-9081.2023081166

• Data science and technology • Previous Articles

Automatic international classification of disease coding method incorporating heterogeneous information

Quanmei ZHANG¹, Runping HUANG¹, Fei TENG¹, Haibo ZHANG², Nan ZHOU¹()

^1.School of Computing and Artificial Intelligence，Southwest Jiaotong University，Chengdu Sichuan 611756，China
^2.Department of Computer Science，University of Otago，Otago 9040，New Zealand

Received:2023-09-13 Revised:2023-10-16 Accepted:2023-11-03 Online:2024-08-22 Published:2024-08-10
Contact: Nan ZHOU
About author:ZHANG Quanmei， born in 1998， M.S. candidate. Her research interests include natural language processing， automatic ICD coding.
HUANG Runping， born in 2000， M. S. candidate. Her research interests include natural language processing， text classification.
TENG Fei， born in 1984， Ph. D.， professor. Her research interests include natural language processing， medical informatics.
ZHANG Haibo， born in 1982， Ph. D.， associate professor. His research interests include medical informatics， high-performance computing.
Supported by:
National Natural Science Foundation of China(62272398);Major Science and Technology Project of Sichuan Province(2023jdr0183)

融合异构信息的自动国际疾病分类编码方法

张全梅¹, 黄润萍¹, 滕飞¹, 张海波², 周南¹()

^1.西南交通大学计算机与人工智能学院，成都 611756
^2.奥塔哥大学计算机科学系，新西兰奥塔哥 9040

通讯作者: 周南
作者简介:张全梅（1998—），女，湖南吉首人，硕士研究生，CCF会员，主要研究方向：自然语言处理、自动ICD编码
黄润萍（2000—），女，四川泸州人，硕士研究生，CCF会员，主要研究方向：自然语言处理、文本分类
滕飞（1984—），女，山东泰安人，教授，博士，CCF高级会员，主要研究方向：自然语言处理、医学信息学
张海波（1982—），男，山东济南人，副教授，博士，CCF会员，主要研究方向：医学信息学、高性能计算
周南（1966—），女，浙江杭州人，教授，博士，主要研究方向：教育学、科研管理、产学研创新 nzhou@swjtu.edu.cn。
基金资助:
国家自然科学基金资助项目(62272398);四川省重大科技专项(2023jdr0183)

Abstract

Abstract:

Concerning the structural diversity of medical Electronic Health Record （EHR） and the complicated correlation between coding in the automatic International Classification of Disease （ICD） coding task， an Automatic ICD Coding method integrating Heterogeneous Information （AIC-HI） was proposed. Firstly， various feature extractors were designed based on the distinctive characteristics of structured coding， semi-structured description， and unstructured medical text in the coding task. At the same time， the coding knowledge graph was constructed to fit the hierarchical relationship of coding， and the association relationships between different branches were transformed into triples containing head and tail coding. Then representation learning was used to fuse encoding and description information to calculate label features. Finally， the attention mechanism was used to extract the most relevant feature representation in unstructured documents. The experimental results show that， compared with the suboptimal baseline model MARN （Multitask bAlanced and Recalibrated Network）， the microscopic F1-score of the model AIC-HI on the real clinical dataset MIMIC-Ⅲ is increased by 4.3 percentage points.

Key words: medical code prediction, automatic International Classification of Disease (ICD) coding, hierarchical structure, heterogeneous information, Natural Language Processing (NLP)

摘要：

针对自动国际疾病分类（ICD）编码中医学电子健康记录（EHR）的结构多样性以及编码间复杂的关联关系等特点，提出一种融合异构信息的自动ICD编码方法AIC-HI（Automatic ICD Coding integrating Heterogeneous Information）。首先，针对编码任务中结构化编码、半结构化描述、非结构化医学文本这3种异构数据的不同特性设计了多种特征提取器；其次，构建编码知识图谱拟合编码的层次结构关系，将不同分支间关联关系转化为包含头尾编码的三元组；再次，运用表征学习融合编码和描述信息计算标签特征；最后，通过注意力机制提取在非结构化文档中与编码标签最为相关的特征表示。实验结果表明，与次优的基线模型MARN（Multitask bAlanced and Recalibrated Network）相比，AIC-HI在真实临床数据集MIMIC-Ⅲ上所有编码的微观F1值提升了4.3个百分点。

关键词: 医学代码预测, 自动国际疾病分类编码, 层次结构, 异构信息, 自然语言处理

CLC Number:

TP391.4

Quanmei ZHANG, Runping HUANG, Fei TENG, Haibo ZHANG, Nan ZHOU. Automatic international classification of disease coding method incorporating heterogeneous information[J]. Journal of Computer Applications, 2024, 44(8): 2476-2482.

张全梅, 黄润萍, 滕飞, 张海波, 周南. 融合异构信息的自动国际疾病分类编码方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2476-2482.

Figures/Tables 8

References 25

1	COWIE M R， BLOMSTER J I， CURTIS L H. Electronic health records to facilitate clinical research ［J］. Clinical Research in Cardiology， 2017，106： 1-9.
2	KAUR R， GINIGE J A. Analysing effectiveness of multi-label classification in clinical coding ［C］// Proceedings of the 2019 Australasian Computer Science Week Multiconference. New York： ACM， 2019： 24.
3	殷希，初菁菁，金雯，等. 实施疾病诊断相关分组预付费制度对医疗服务质量影响的文献分析［J］. 中华医院管理杂志， 2020， 36（6）： 490-495.
	YIN X， CHU J J， JIN W， et al. Literature analysis on the impact of implementing the diagnosis-related groups prospective payment system on the quality of medical services ［J］. Chinese Journal of Hospital Administration， 2020， 36（6）： 490-495.
4	李小丹，梁嘉诚，邝倩仪，等. 病案首页ICD编码的准确率对DRGs付费影响［J］. 广州医药， 2022， 53（6）： 96-99.
	LI X D， LIANG J C， KUANG Q Y， et al. The impact of the accuracy of ICD coding on the first page of medical records on the payment of DRGs ［J］. Guangzhou Medical Journal， 2022， 53（6）： 96-99.
5	邱小娟，张丽丽，朱琳. 600份住院病案首页ICD-10编码质量分析［J］. 中国病案， 2022， 23（7）： 27-29.
	QIU X J， ZHANG L L， ZHU L. Analysis of ICD-10 code quality on the front pages of 600inpatient medical records［J］. Chinese Medical Record， 2022， 23（7）： 27-29.
6	YAN C， FU X， LIU X， et al. A survey of automated ICD coding： development， challenges， and applications ［J］. Intelligent Medicine， 2022， 2（3）： 161-173.
7	SHE Y， SONG P. Quality analysis on international classification of disease coding in a 3A hospital ［J］. Chinese Medical Record： English Edition， 2013， 1（10）： 423-426.
8	KRAWCZYK P， ŚWIĘCICKI Ł. ICD-11 vs ICD-10： a review of updates and novelties introduced in the latest version of the WHO International Classification of Diseases ［J］. Psychiatria Polska， 2020， 54（1）： 7-20.
9	LIU S， WANG X， HOU Y， et al. Multimodal data matters： Language model pre-training over structured and unstructured electronic health records ［J］. IEEE Journal of Biomedical and Health Informatics， 2023， 27（1）： 504-514.
10	LI Y， MAMOUEI M， SALIMI-KHORSHIDI G， et al. Hi-BEHRT： hierarchical transformer-based model for accurate prediction of clinical events using multimodal longitudinal electronic health records ［J］. IEEE Journal of Biomedical and Health Informatics， 2023， 27（2）： 1106-1117.
11	PEROTTE A， PIVOVAROV R， NATARAJAN Ket al. Diagnosis code assignment： models and evaluation metrics ［J］. Journal of the American Medical Informatics Association， 2014， 21（2）： 231-237.
12	MULLENBACH J， WIEGREFFE S， DUKE Jet al. Explainable prediction of medical codes from clinical text ［C］// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics. Stroudsburg： ACL， 2018： 1101-1111.
13	LI F， YU H. ICD coding from clinical text using multi-filter residual convolutional neural network ［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2020， 34（5）： 8180-8187.
14	CATLING F， SPITHOURAKIS G P， RIEDEL S， et al. Towards automated clinical coding ［J］. International Journal of Medical Informatics， 2018， 120： 50-61.
15	YUAN Z， TAN C， HUANG S. Code synonyms do matter： multiple synonyms matching network for automatic ICD coding ［EB/OL］. （2022-03-03）［2023-10-14］. .
16	WU Y， CHEN Z， YAO X， et al. JAN： Joint attention networks for automatic ICD coding ［J］. IEEE Journal of Biomedical and Health Informatics， 2022， 26（10）： 5235-5246.
17	ZHANG N， JANKOWSKI M. Hierarchical BERT for medical document understanding ［EB/OL］. （2022-03-11）［2023-10-14］. .
18	CAO P， CHEN Y， LIU K， et al. Hypercore： hyperbolic and co-graph representation for automatic ICD coding ［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2020， 3105-3114.
19	ZHOU T， CAO P， CHEN Y， et al. Automatic ICD coding via interactive shared representation networks with self-distillation mechanism ［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Conference on Natural Language Processing. Stroudsburg： ACL，2021， 5948-5957.
20	VU T， NGUYEN D Q， NGUYEN A. A label attention model for ICD coding from clinical text ［EB/OL］. （2020-07-13）［2023-10-14］. .
21	YU Y， DUAN J， JIANG H， et al. Automatic ICD coding based on multi-granularity feature fusion ［C］// Proceedings of the 18th International Symposium on the Bioinformatics Research and Applications. Cham： Springer， 2023： 19-29.
22	周晓敏，滕飞，张艺. 基于元网络的自动国际疾病分类编码模型［J］. 计算机应用， 2023， 43（9）： 2721-2726.
	ZHOU X M， TENG F， ZHANG Y. Automatic international classification of diseases coding model based on meta-network ［J］. Journal of Computer Applications， 2023， 43（9）： 2721-2726.
23	BORDES A， USUNIER N， GARCIA-DURÁN D. Translating embeddings for modeling multi-relational data ［C］// Proceedings of the 26th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2013： 2787-2795.
24	WU H， MENG L， XU S， et al. Joint modeling of document and label with clause interaction hypergraph for ICD medical code assignment ［C］// Proceedings of the 2022 International Joint Conference on Neural Networks. Piscataway： IEEE， 2022： 1-8.
25	SUN W， JI S， CAMBRIA E， et al. Multitask balanced and recalibrated network for medical code prediction ［J］. ACM Transactions on Intelligent Systems and Technology， 2022， 14（1）： 17.

数据集	类别	样本数	平均单词数	总标签数	唯一标签数	平均标签数
MIMIC⁃Ⅲ⁃Top50	训练集	8 066	1 529.69	45 919	50	918.38
	验证集	1 573	1 799.67	9 283	50	185.66
	测试集	1 729	1 825.45	10 477	50	209.54
MIMIC⁃Ⅲ⁃full	训练集	47 723	1 484.54	758 216	8 686	87.29
	验证集	1 631	1 784.71	28 897	3 009	9.60
	测试集	3 372	1 792.33	61 579	4 075	15.11

数据集	类别	样本数	平均单词数	总标签数	唯一标签数	平均标签数
MIMIC⁃Ⅲ⁃Top50	训练集	8 066	1 529.69	45 919	50	918.38
	验证集	1 573	1 799.67	9 283	50	185.66
	测试集	1 729	1 825.45	10 477	50	209.54
MIMIC⁃Ⅲ⁃full	训练集	47 723	1 484.54	758 216	8 686	87.29
	验证集	1 631	1 784.71	28 897	3 009	9.60
	测试集	3 372	1 792.33	61 579	4 075	15.11

模型	MIMIC⁃Ⅲ⁃Full数据集					MIMIC⁃Ⅲ⁃Top50数据集
模型	Macro⁃AUC	Micro⁃AUC	Macro⁃F1	Micro⁃F1	P@8	Macro⁃AUC	Micro⁃AUC	Macro⁃F1	Micro⁃F1	P@5
CAML	0.820	0.966	0.048	0.442	0.523	0.875	0.909	0.532	0.614	0.609
DR⁃CAML	0.826	0.966	0.049	0.457	0.515	0.884	0.916	0.576	0.633	0.618
MultiResCNN	0.910	0.986	0.085	0.552	0.734	0.899	0.928	0.606	0.670	0.641
MDBERT	0.925	0.989	0.101	0.555	0.727	0.918	0.936	0.659	0.692	0.654
MNIC	0.907	0.982	0.104	0.576	—	0.914	0.937	0.615	0.658	—
MARN	0.913	0.988	0.116	0.584	0.754	0.927	0.947	0.682	0.718	0.673
AIC⁃HI	0.923	0.989	0.094	0.627	0.762	0.931	0.951	0.679	0.729	0.678

模型	MIMIC⁃Ⅲ⁃Full数据集					MIMIC⁃Ⅲ⁃Top50数据集
模型	Macro⁃AUC	Micro⁃AUC	Macro⁃F1	Micro⁃F1	P@8	Macro⁃AUC	Micro⁃AUC	Macro⁃F1	Micro⁃F1	P@5
CAML	0.820	0.966	0.048	0.442	0.523	0.875	0.909	0.532	0.614	0.609
DR⁃CAML	0.826	0.966	0.049	0.457	0.515	0.884	0.916	0.576	0.633	0.618
MultiResCNN	0.910	0.986	0.085	0.552	0.734	0.899	0.928	0.606	0.670	0.641
MDBERT	0.925	0.989	0.101	0.555	0.727	0.918	0.936	0.659	0.692	0.654
MNIC	0.907	0.982	0.104	0.576	—	0.914	0.937	0.615	0.658	—
MARN	0.913	0.988	0.116	0.584	0.754	0.927	0.947	0.682	0.718	0.673
AIC⁃HI	0.923	0.989	0.094	0.627	0.762	0.931	0.951	0.679	0.729	0.678

模型	MIMIC-Ⅲ-Full数据集		MIMIC-Ⅲ-Top50数据集
模型	Macro-F1	Micro-F1	Macro-F1	Micro-F1
-fusion	0.062	0.493	0.571	0.645
-attention	0.081	0.619	0.630	0.718
AIC-HI	0.094	0.627	0.679	0.729

Automatic international classification of disease coding method incorporating heterogeneous information

融合异构信息的自动国际疾病分类编码方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 25

Related Articles 15

Recommended Articles

Metrics

[1]	Youren YU, Yangsen ZHANG, Yuru JIANG, Gaijuan HUANG. Chinese named entity recognition model incorporating multi-granularity linguistic knowledge and hierarchical information [J]. Journal of Computer Applications, 2024, 44(6): 1706-1712.
[2]	Lipeng ZHAO, Bing GUO. Blockchain consensus improvement algorithm based on BDLS [J]. Journal of Computer Applications, 2024, 44(4): 1139-1147.
[3]	Longtao GAO, Nana LI. Aspect sentiment triplet extraction based on aspect-aware attention enhancement [J]. Journal of Computer Applications, 2024, 44(4): 1049-1057.
[4]	Xianfeng YANG, Yilei TANG, Ziqiang LI. Aspect-level sentiment analysis model based on alternating‑attention mechanism and graph convolutional network [J]. Journal of Computer Applications, 2024, 44(4): 1058-1064.
[5]	Tao SUN, Zhangtian DUAN, Haonan ZHU, Peihao GUO, Heli SUN. Social event recommendation method based on unexpectedness metric [J]. Journal of Computer Applications, 2024, 44(3): 760-766.
[6]	Baoshan YANG, Zhi YANG, Xingyuan CHEN, Bing HAN, Xuehui DU. Analysis of consistency between sensitive behavior and privacy policy of Android applications [J]. Journal of Computer Applications, 2024, 44(3): 788-796.
[7]	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.
[8]	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.
[9]	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.
[10]	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.
[11]	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.
[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]	Xingbin LIAO, Xiaolin QIN, Siqi ZHANG, Yangge QIAN. Review of interactive machine translation [J]. Journal of Computer Applications, 2023, 43(2): 329-334.
[14]	Ming XU, Linhao LI, Qiaoling QI, Liqin WANG. Abductive reasoning model based on attention balance list [J]. Journal of Computer Applications, 2023, 43(2): 349-355.
[15]	Jianle CAO, Nana LI. Semantically enhanced sentiment classification model based on multi-level attention [J]. Journal of Computer Applications, 2023, 43(12): 3703-3710.