A probabilistic automated tagger to identify human-related publications.
A probabilistic automated tagger to identify human-related publications.
复制标题
DOI：
10.1093/database/bay079
复制
发表时间：
2018-01-01
期刊：
影响因子：
--
通讯作者：
Smalheiser NR
中科院分区：
文献类型：
--
作者：
Cohen AM;Dunivin ZO;Smalheiser NR
医学主题标题“人类”是手动管理的，表示MEDLINE中的人类相关研究。然而，新发表的MEDLINE文章可能需要数月才能编入索引，而非MEDLINE文章缺乏一致的、透明的索引。因此，对于最新和广泛的文献检索，需要一个独立的自动化系统来识别给定的出版物是否与人类相关，特别是当它们缺乏医学主题词时。随机选择了1987-2014年发表的一百万条MEDLINE记录。从题名、摘要、作者姓名和期刊字段中提取基于文本的特征。对线性支持向量机进行了训练，以估计给定文章应被索引为人类的概率，并对2015年至2016年的记录进行了评价。总体准确度较高：受试者工作曲线下面积= 0.976，F1 = 95%（相对于MeSH指数）。手动审查与MEDLINE极端不一致的病例显示，与自动预测的一致率为73.5%。我们已经用预测分数标记了PubMed中索引的所有文章，并在http://arrowsmith.psych.uic.edu/evidence_based_medicine/index.html上公开了这些信息。我们还提供了一个基于网络的界面，允许用户获得非MEDLINE文章的预测评分。这将有助于临床证据的分类，以撰写系统综述。
The Medical Subject Heading ‘Humans’ is manually curated and indicates human-related studies within MEDLINE. However, newly published MEDLINE articles may take months to be indexed and non-MEDLINE articles lack consistent, transparent indexing of this feature. Therefore, for up to date and broad literature searches, there is a need for an independent automated system to identify whether a given publication is human-related, particularly when they lack Medical Subject Headings. One million MEDLINE records published in 1987–2014 were randomly selected. Text-based features from the title, abstract, author name and journal fields were extracted. A linear support vector machine was trained to estimate the probability that a given article should be indexed as Humans and was evaluated on records from 2015 to 2016. Overall accuracy was high: area under the receiver operating curve = 0.976, F1 = 95% relative to MeSH indexing. Manual review of cases of extreme disagreement with MEDLINE showed 73.5% agreement with the automated prediction. We have tagged all articles indexed in PubMed with predictive scores and have made the information publicly available at http://arrowsmith.psych.uic.edu/evidence_based_medicine/index.html. We have also made available a web-based interface to allow users to obtain predictive scores for non-MEDLINE articles. This will assist in the triage of clinical evidence for writing systematic reviews.
登录
查看更多内容
影响因子：
3
作者：
Tsatsaronis G;Balikas G;Malakasiotis P;Partalas I;Zschunke M;Alvers MR;Weissenborn D;Krithara A;Petridis S;Polychronopoulos D;Almirantis Y;Pavlopoulos J;Baskiotis N;Gallinari P;Artiéres T;Ngomo AC;Heino N;Gaussier E;Barrio-Alvers L;Schroeder M;Androutsopoulos I;Paliouras G
通讯作者：
Paliouras G
影响因子：
105.7
作者：
Susan, L.;Robinson, Karen A.;Dickersin, Kay
通讯作者：
Dickersin, Kay
影响因子：
6
作者：
Smalheiser NR;Lin C;Jia L;Jiang Y;Cohen AM;Yu C;Davis JM;Adams CE;McDonagh MS;Meng W
通讯作者：
Meng W
MeSHLabeler：通过整合不同证据提高大规模 MeSH 索引的准确性
DOI：
10.1093/bioinformatics/btv237
发表时间：
2015-06-15
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Liu K;Peng S;Wu J;Zhai C;Mamitsuka H;Zhu S
通讯作者：
Zhu S
DOI：
10.1093/jamia/ocu025
发表时间：
2015-05
期刊：
Journal of the American Medical Informatics Association : JAMIA
影响因子：
--
作者：
Cohen AM;Smalheiser NR;McDonagh MS;Yu C;Adams CE;Davis JM;Yu PS
通讯作者：
Yu PS