https://scholars.lib.ntu.edu.tw/handle/123456789/476477
標題: | PICO element detection in medical text without metadata: Are first sentences enough? | 作者: | Huang K.-C. Chiang I.-J. FU-REN XIAO Liao C.-C. Liu C.C.H. Wong J.-M. |
公開日期: | 2013 | 卷: | 46 | 期: | 5 | 起(迄)頁: | 940-946 | 來源出版物: | Journal of Biomedical Informatics | 摘要: | Efficient identification of patient, intervention, comparison, and outcome (PICO) components in medical articles is helpful in evidence-based medicine. The purpose of this study is to clarify whether first sentences of these components are good enough to train naive Bayes classifiers for sentence-level PICO element detection. We extracted 19,854 structured abstracts of randomized controlled trials with any P/I/O label from PubMed for naive Bayes classifiers training. Performances of classifiers trained by first sentences of each section ( CF) and those trained by all sentences ( CA) were compared using all sentences by ten-fold cross-validation. The results measured by recall, precision, and F-measures show that there are no significant differences in performance between CF and CA for detection of O-element ( F-measure. = 0.731. ±. 0.009 vs. 0.738. ±. 0.010, p= 0.123). However, CA perform better for I-elements, in terms of recall (0.752. ±. 0.012 vs. 0.620. ±. 0.007, p<. 0.001) and F-measures (0.728. ±. 0.006 vs. 0.662. ±. 0.007, p<. 0.001). For P-elements, CF have higher precision (0.714. ±. 0.009 vs. 0.665. ±. 0.010, p<. 0.001), but lower recall (0.766. ±. 0.013 vs. 0.811. ±. 0.012, p<. 0.001). CF are not always better than CA in sentence-level PICO element detection. Their performance varies in detecting different elements. ? 2013 Elsevier Inc. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84883806449&doi=10.1016%2fj.jbi.2013.07.009&partnerID=40&md5=bcd5f1ae42b7edf391c17a0bde39bbf0 https://scholars.lib.ntu.edu.tw/handle/123456789/476477 |
ISSN: | 1532-0464 | DOI: | 10.1016/j.jbi.2013.07.009 | SDG/關鍵字: | Cross validation; Evidence-based medicine; Naive Bayes classifiers; NAtural language processing; Question Answering; Randomized controlled trial; Structured abstract; Text mining; Data mining; Information retrieval; Patient treatment; Natural language processing systems; accuracy; article; Bayesian learning; bioinformatics; classifier; data mining; evidence based medicine; human; information retrieval; model; natural language processing; patient intervention comparison and outcome model; performance; priority journal; randomized controlled trial (topic); Evidence-based medicine; Information extraction; Information retrieval; Natural language processing; Question answering; Text mining; Algorithms; Bayes Theorem; Natural Language Processing |
顯示於: | 醫學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。