跳到主要內容

臺灣博碩士論文加值系統

(44.201.99.222) 您好!臺灣時間:2022/12/10 11:02
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:昌珮祺
研究生(外文):CHANG, PEI-CHI
論文名稱:基於深度學習之國際疾病碼多標籤分類
論文名稱(外文):Multi-label Classification of ICD Coding Using Deep Learning
指導教授:許中川許中川引用關係
指導教授(外文):HSU, CHUNG-CHIAN
口試委員:許中川張榮昇蔡鴻旭
口試委員(外文):HSU, CHUNG-CHIANCHANG, ARTHURTSAI, HUNG-HSU
口試日期:2020-06-15
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:資訊管理系
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:38
中文關鍵詞:國際疾病碼編碼多標籤分類自然語言處理深度學習
外文關鍵詞:ICD codingMulti-label classificationNatural language processingDeep learning
相關次數:
  • 被引用被引用:0
  • 點閱點閱:157
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本研究使用深度學習方法來解決國際疾病碼編碼中的多標籤分類問題。本研究利用支援向量機和多個深度學習框架比較,並和不同的分類組合實驗來進行任務。採用MIMIC-III數據集的出院紀錄來進行文本預處理、標籤預處理和深度學習模型訓練。具體而言,本研究嘗試了按照章節分類和常見標籤的分類的方法,以期為醫生的每次診斷找到最佳的國際疾病碼代碼推薦。實驗結果顯示,透過F1-micro績效衡量指標,卷積類神經網路在標籤到章節中的最佳績效為76%。廣泛的實驗結果還顯示,在前50個和前100個常見標籤中,卷積類神經網路的性能優於其他方法。
This study uses deep learning approach to tackle the multi-label classification problem in ICD coding. We use support vector machine to compare with multiple deep learning techniques along with different classification combinations to perform our tasks. The discharge summaries on MIMIC-III dataset are adopted to explore the training methods of text preprocessing, label preprocessing, and model training. Specifically, the methods of label-to-chapter and common label classification are experimented, in order to find the best recommendations of ICD codes for each diagnosis to the physicians. The result showed that CNN has the best performance 76% by micro F1-measure in label-to-chapter. Extensive experiments results also showed that CNN outperforms the other methods in top-50 and top-100 popular labels.
摘要 i
Abstract ii
目錄 iii
表目錄 iv
圖目錄 v
壹、緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究目的 2
貳、文獻探討 4
2.1 詞向量 4
2.1.1 Word2Vec 4
2.1.2 FastText 6
2.1.3 Doc2Vec 6
2.2 自動編碼 7
參、方法 9
3.1 文字前處理 9
3.2 標籤處理 14
3.2.1 疾病分類碼之章節 14
3.2.2 分類最常見的疾病代碼 15
3.3 分類器 16
3.3.1 卷積神經網路 16
3.3.2 遞歸神經網絡 17
3.4 評估 18
肆、實驗 20
4.1 MIMIC 資料集 20
4.2 實驗設計 20
4.3 實驗結果 21
4.3.1 廣泛嘗試不同的分類器 21
4.3.2 小資料集參數調整 24
4.3.3 MIMIC-III實驗結果 27
伍、結論 29
參考文獻 30
1. Atutxa, A., de Ilarraza, A. D., Gojenola, K., Oronoz, M., & Perez-de-Viñaspre, O. (2019). Interpretable deep learning to map diagnostic texts to ICD-10 codes. International Journal of Medical Informatics, 129, 49-59.
2. Atutxa, A., Pérez, A., & Casillas, A. (2018). Machine Learning Approaches on Diagnostic Term Encoding With the ICD for Clinical Documentation. IEEE Journal of Biomedical and Health Informatics, 22(4), 1323-1329. doi:10.1109/JBHI.2017.2743824
3. Bai, T., & Vucetic, S. (2019). Improving Medical Code Prediction from Clinical Text via Incorporating Online Knowledge Sources. Paper presented at the The World Wide Web Conference.
4. Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017). Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics, 5, 135-146. doi:10.1162/tacl_a_00051
5. Chen, D., Zhang, R., & Qiu, R. G. (2019). Leveraging semantics in WordNet to facilitate the computer-assisted coding of ICD-11. IEEE journal of biomedical and health informatics.
6. Chen, Y., & Ren, J. (2019). Automatic ICD code assignment utilizing textual descriptions and hierarchical structure of ICD code. Paper presented at the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).
7. Chen, Y., & Wang, Z. (2010, 16-18 Oct. 2010). A semantic method for coding of ICD diagnoses. Paper presented at the 2010 3rd International Conference on Biomedical Engineering and Informatics.
8. Elman, J. L. (1990). Finding structure in time. Cognitive science, 14(2), 179-211.
9. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
10. Huang, J., Osorio, C., & Sy, L. W. (2019). An empirical evaluation of deep learning for ICD-9 code assignment using MIMIC-III clinical notes. Computer methods and programs in biomedicine, 177, 141-153.
11. Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2016). Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759.
12. Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882.
13. Le, Q., & Mikolov, T. (2014). Distributed representations of sentences and documents. Paper presented at the International conference on machine learning.
14. Li, L., Niu, C., Pu, D., & Jin, X. (2018, 19-21 Oct. 2018). Electronic Medical Data Analysis Based on Word Vector and Deep Learning Model. Paper presented at the 2018 9th International Conference on Information Technology in Medicine and Education (ITME).
15. Li, M., Fei, Z., Zeng, M., Wu, F., Li, Y., Pan, Y., & Wang, J. (2018). Automated ICD-9 coding via a deep learning approach. IEEE/ACM transactions on computational biology and bioinformatics.
16. Li, Y., Chen, W., Liu, D., Zhang, Z., Wu, S., & Liu, C. (2019). IFFLC: An Integrated Framework of Feature Learning and Classification for Multiple Diagnosis Codes Assignment. Ieee Access, 7, 36810-36818.
17. Liu, P., Qiu, X., & Huang, X. (2016). Recurrent neural network for text classification with multi-task learning. arXiv preprint arXiv:1605.05101.
18. Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
19. Mikolov, T., Yih, W.-t., & Zweig, G. (2013). Linguistic regularities in continuous space word representations. Paper presented at the Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
20. Sutskever, I., Vinyals, O., & Le, Q. (2014). Sequence to sequence learning with neural networks. Advances in NIPS.
21. Xu, K., Lam, M., Pang, J., Gao, X., Band, C., Xie, P., & Xing, E. (2018). Multimodal Machine Learning for Automated ICD Coding. arXiv preprint arXiv:1810.13348.
22. Yin, W., Kann, K., Yu, M., & Schütze, H. (2017). Comparative study of CNN and RNN for natural language processing. arXiv preprint arXiv:1702.01923.
23. Yu, Y., Li, M., Liu, L., Wu, F.-X., & Wang, J. (2019). Tentative diagnosis prediction via deep understanding of patient narratives. Paper presented at the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).
24. Zhang, X., Zhao, J., & LeCun, Y. (2015). Character-level convolutional networks for text classification. Paper presented at the Advances in neural information processing systems.
25. Understanding LSTM Networks (http://colah.github.io/posts/2015-08-Understanding-LSTMs/).
26. 衛生福利部統計處(2013)。「國際疾病分類使用指引」。取自https://dep.mohw.gov.tw/DOS/lp-2490-113.html



電子全文 電子全文(網際網路公開日期:20250624)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊