上海交通大学学报（英文版） ›› 2012, Vol. 17 ›› Issue (4): 494-499.doi: 10.1007/s12204-012-1311-z

• 论文 • 上一篇    下一篇

Web-Based Biomedical Literature Mining

AN Jian-fu1,4 (安建福), XUE Hui-ping2 (薛惠平), CHEN ying1 (陈瑛), WU Jian-guo3 (吴建国), ZHANG Lu1 (章鲁)   

  1. (1. Department of Biomedical Engineering, Basic Medical College, Shanghai Jiaotong University School of Medicine, Shanghai 200025, China; 2. Division of Gastroenterology and Hepatology, Renji Hospital, Shanghai Jiaotong University School of Medicine, Shanghai 200001, China; 3. Department of Nuclear Medicine, Renji Hospital, Shanghai Jiaotong University School of Medicine, Shanghai 200001, China; 4. Information and Resource Center, Shanghai Jiaotong University School of Medicine, Shanghai 200025, China)
  • 出版日期:2012-08-30 发布日期:2012-11-16
  • 通讯作者: ZHANG Lu1 (章鲁) E-mail:zhanglu614@126.com

Web-Based Biomedical Literature Mining

AN Jian-fu1,4 (安建福), XUE Hui-ping2 (薛惠平), CHEN ying1 (陈瑛), WU Jian-guo3 (吴建国), ZHANG Lu1 (章鲁)   

  1. (1. Department of Biomedical Engineering, Basic Medical College, Shanghai Jiaotong University School of Medicine, Shanghai 200025, China; 2. Division of Gastroenterology and Hepatology, Renji Hospital, Shanghai Jiaotong University School of Medicine, Shanghai 200001, China; 3. Department of Nuclear Medicine, Renji Hospital, Shanghai Jiaotong University School of Medicine, Shanghai 200001, China; 4. Information and Resource Center, Shanghai Jiaotong University School of Medicine, Shanghai 200025, China)
  • Online:2012-08-30 Published:2012-11-16
  • Contact: ZHANG Lu1 (章鲁) E-mail:zhanglu614@126.com

摘要： With an upsurge in biomedical literature, using data-mining method to search new knowledge from literature has drawing more attention of scholars. In this study, taking the mining of non-coding gene literature from the network database of PubMed as an example, we first preprocessed the abstract data, next applied the term occurrence frequency (TF) and inverse document frequency (IDF) (TF-IDF) method to select features, and then established a biomedical literature data-mining model based on Bayesian algorithm. Finally, we assessed the model through area under the receiver operating characteristic curve (AUC), accuracy, specificity, sensitivity, precision rate and recall rate. When 1 000 features are selected, AUC, specificity, sensitivity, accuracy rate, precision rate and recall rate are 0.868 3, 84.63%, 89.02%, 86.83%, 89.02% and 98.14%, respectively. These results indicate that our method can identify the targeted literature related to a particular topic effectively.

关键词: Bayesian algorithm, term occurrence frequency (TF) and inverse document frequency (IDF) (TFIDF), data-mining

Abstract: With an upsurge in biomedical literature, using data-mining method to search new knowledge from literature has drawing more attention of scholars. In this study, taking the mining of non-coding gene literature from the network database of PubMed as an example, we first preprocessed the abstract data, next applied the term occurrence frequency (TF) and inverse document frequency (IDF) (TF-IDF) method to select features, and then established a biomedical literature data-mining model based on Bayesian algorithm. Finally, we assessed the model through area under the receiver operating characteristic curve (AUC), accuracy, specificity, sensitivity, precision rate and recall rate. When 1 000 features are selected, AUC, specificity, sensitivity, accuracy rate, precision rate and recall rate are 0.868 3, 84.63%, 89.02%, 86.83%, 89.02% and 98.14%, respectively. These results indicate that our method can identify the targeted literature related to a particular topic effectively.

Key words: Bayesian algorithm, term occurrence frequency (TF) and inverse document frequency (IDF) (TFIDF), data-mining

中图分类号: