Using classification models for the generation of disease-specific medications from biomedical literature and clinical data repository.
Using classification models for the generation of disease-specific medications from biomedical literature and clinical data repository.
复制标题
DOI：
10.1016/j.jbi.2017.04.014
复制
发表时间：
2017-05
影响因子：
4.5
通讯作者：
Del Fiol G
中科院分区：
文献类型：
--
作者：
Wang L;Haug PJ;Del Fiol G
从现有知识资源中挖掘特定于疾病的关联对于构建特定于疾病的本体和支持基于知识的应用程序非常有用。许多关联挖掘技术已经被利用。然而，当这些提取的关联包含大量噪声时，挑战仍然存在。简单地在多个相关性分数上设置任意的分界点来确定关联的相关性是不可靠的；而且，让人类专家手动审查大量的关联是非常昂贵的。我们提出基于机器学习的分类可以用来从噪声中分离信号，并提供一种可行的方法来创建和维护特定疾病的词汇表。为了简单起见，我们最初专注于疾病与药物的关联。对于感兴趣的疾病，我们从生物医学文献引用和本地临床数据库中提取了可能与治疗相关的药物概念。每个概念都与多个相关性度量（即特征）相关联，例如出现频率。为了机器学习的目的，我们针对三种疾病形成了九个数据集，每个疾病有两个单源数据集，一个来自前两个数据集的组合。所有数据集均使用现有参考标准进行标记。此后，我们进行了两个实验：1)测试添加临床数据存储库中的特征是否会提高仅使用生物医学文献中的特征进行分类的性能；2)确定使用已知药物疾病数据集训练的分类器是否可以推广到新疾病。简单逻辑回归和LogitBoost分类器分别被确定为生物医学文献数据集和组合数据集的首选模型。与单独使用生物医学文献特征相比，使用组合特征的分类性能有显著提高（p值<0.001）。从已知疾病构建的分类器来预测新疾病的相关概念的性能与使用新疾病数据集构建和测试的分类器的性能没有显著差异。使用分类方法自动预测一个概念与感兴趣的疾病的相关性是可行的。结合来自不同来源的特征来完成分类任务是很有用的。从已知疾病建立的分类器可推广到新疾病。
Mining disease-specific associations from existing knowledge resources can be useful for building disease-specific ontologies and supporting knowledge-based applications. Many association mining techniques have been exploited. However, the challenge remains when those extracted associations contained much noise. It is unreliable to determine the relevance of the association by simply setting up arbitrary cut-off points on multiple scores of relevance; and it would be expensive to ask human experts to manually review a large number of associations. We propose that machine-learning-based classification can be used to separate the signal from the noise, and to provide a feasible approach to create and maintain disease-specific vocabularies. We initially focused on disease-medication associations for the purpose of simplicity. For a disease of interest, we extracted potentially treatment-related drug concepts from biomedical literature citations and from a local clinical data repository. Each concept was associated with multiple measures of relevance (i.e., features) such as frequency of occurrence. For the machine purpose of learning, we formed nine datasets for three diseases with each disease having two single-source datasets and one from the combination of previous two datasets. All the datasets were labeled using existing reference standards. Thereafter, we conducted two experiments: 1) to test if adding features from the clinical data repository would improve the performance of classification achieved using features from the biomedical literature only, and 2) to determine if classifier(s) trained with known medication-disease data sets would be generalizable to new disease(s). Simple logistic regression and LogitBoost were two classifiers identified as the preferred models separately for the biomedical-literature datasets and combined datasets. The performance of the classification using combined features provided significant improvement beyond that using biomedical-literature features alone (p-value<0.001). The performance of the classifier built from known diseases to predict associated concepts for new diseases showed no significant difference from the performance of the classifier built and tested using the new disease’s dataset. It is feasible to use classification approaches to automatically predict the relevance of a concept to a disease of interest. It is useful to combine features from disparate sources for the task of classification. Classifiers built from known diseases were generalizable to new diseases.
登录
查看更多内容
影响因子：
8.9
作者：
Huang, J;Ling, CX
通讯作者：
Ling, CX
影响因子：
7.5
作者：
Landwehr, N;Hall, M;Frank, E
通讯作者：
Frank, E
使用中心性在文献挖掘的基因互动网络上识别基因 - 疾病的关联。
DOI：
10.1093/bioinformatics/btn182
发表时间：
2008-07-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Ozgür A;Vu T;Erkan G;Radev DR
通讯作者：
Radev DR
影响因子：
8
作者：
Bradley, AP
通讯作者：
Bradley, AP
影响因子：
4.5
作者：
Cao, Hui;Hripcsak, George;Markatou, Marianthi
通讯作者：
Markatou, Marianthi