國家衛生研究院 NHRI:Item 3990099045/13629
English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 12145/12927 (94%)
造訪人次 : 854824      線上人數 : 846
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧：
  • 您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料
    •  進階搜尋
    主頁 ‧ 登入 ‧ 上傳 ‧ 說明 ‧ 關於NHRI ‧ 管理 到手機版


    請使用永久網址來引用或連結此文件: http://ir.nhri.org.tw/handle/3990099045/13629


    題名: Cancer registry coding via hybrid neural symbolic systems in the cross-hospital setting
    作者: Dai, HJ;Yang, YH;Wang, TH;Lin, YJ;Lu, PJ;Wu, CY;Chang, YC;Lee, YQ;Zhang, YC;Hsu, YC;Wu, HH;Ke, CR;Huang, CJ;Wang, YT;Yang, SF;Hsiao, KC;Liu, KJ;Chen, LT;Chang, IS;Chao, KSC;Liu, TW
    貢獻者: National Institute of Cancer Research;Institute of Population Health Sciences
    摘要: Cancer registries are critical databases for cancer research whose maintenance requires various types of domain knowledge with labor-intensive data curation. In order to facilitate the curation process with high quality in a timely manner, we developed a hybrid neural symbolic system for cancer registry coding. Unlike previous works which mainly worked on the dataset collected from one hospital or formulated the task as text classification problems, we collaborated with two medical centers in Taiwan to compile a cross-hospital corpus and applied neural networks to extract cancer registry variables described in unstructured pathology reports along with expert systems for generating registry coding. We conducted experiments to study the feasibility of the proposed hybrid for the task of cancer registry coding and compare its performance with state-of-the-art non-hybrid approaches. Furthermore, cross-hospital experiments were performed to study the advantages and limitations of transfer learning for processing reports from different sources. The experiment results demonstrated that the proposed hybrid neural symbolic system is a robust approach which works well across hospitals and outperformed classification-based baselines by F-scores of 0.13 similar to 0.27. Compared to the baseline models, the F-scores of the proposed approaches are apparently higher when fewer training instances were used. All methods benefited from the transferred parameters learned from the source dataset, but the results suggest that it is a better strategy to transfer the learned knowledge through the concept recognition task followed by the symbolic expert system to address the task of cancer registry coding.
    日期: 2021-07-26
    關聯: IEEE Access. 2021 Jul 26;9:112081-112096.
    Link to: http://dx.doi.org/10.1109/ACCESS.2021.3099175
    JIF/Ranking 2023: http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=NHRI&SrcApp=NHRI_IR&KeyISSN=2169-3536&DestApp=IC2JCR
    Cited Times(WOS): https://www.webofscience.com/wos/woscc/full-record/WOS:000685881100001
    Cited Times(Scopus): https://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85112647212
    顯示於類別:[其他] 期刊論文
    [張憶壽] 期刊論文
    [陳立宗] 期刊論文
    [劉柯俊] 期刊論文
    [楊奕馨] 期刊論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    ISI000685881100001.pdf2649KbAdobe PDF244檢視/開啟


    在NHRI中所有的資料項目都受到原著作權保護.

    TAIR相關文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋