TY - JOUR AU - Del Fiol, Guilherme AU - Michelson, Matthew AU - Iorio, Alfonso AU - Cotoi, Chris AU - Haynes, R Brian PY - 2018 DA - 2018/06/25 TI -一种从生物医学文献中自动识别科学严谨临床研究报告的深度学习方法:比较分析研究JO - J Med Internet Res SP - e10281 VL - 20 IS - 6kw -信息检索KW -循证医学KW -深度学习KW -机器学习KW -文献数据库AB -背景:循证医学实践的一个主要障碍是有效地找到给定临床主题的科学合理的研究。目的:探讨一种从生物医学文献中检索科学合理的治疗研究的深度学习方法。方法:我们使用403216个PubMed引用的噪声数据集，以标题和摘要为特征，训练了一个卷积神经网络。深度学习模型与最先进的搜索过滤器进行了比较，例如PubMed的临床查询广泛治疗过滤器、McMaster的文本搜索策略(没有医学主题标题、MeSH、术语)和临床查询平衡治疗过滤器。使用先前注释的数据集(临床对冲)作为金标准。结果:深度学习模型的召回率明显低于临床查询广泛治疗过滤器(96.9% vs 98.4%;P <措施);与麦克马斯特文本搜索的召回率相当(96.9% vs 97.1%;P=.57)和临床询问平衡过滤器(96.9% vs 97.0%; P=.63). Deep learning obtained significantly higher precision than the Clinical Queries Broad filter (34.6% vs 22.4%; P<.001) and McMaster’s textword search (34.6% vs 11.8%; P<.001), but was significantly lower than the Clinical Queries Balanced filter (34.6% vs 40.9%; P<.001). Conclusions: Deep learning performed well compared to state-of-the-art search filters, especially when citations were not indexed. Unlike previous machine learning approaches, the proposed deep learning model does not require feature engineering, or time-sensitive or proprietary features, such as MeSH terms and bibliometrics. Deep learning is a promising approach to identifying reports of scientifically rigorous clinical research. Further work is needed to optimize the deep learning model and to assess generalizability to other areas, such as diagnosis, etiology, and prognosis. SN - 1438-8871 UR - //www.mybigtv.com/2018/6/e10281/ UR - https://doi.org/10.2196/10281 UR - http://www.ncbi.nlm.nih.gov/pubmed/29941415 DO - 10.2196/10281 ID - info:doi/10.2196/10281 ER -