Dataset Information

A semi-supervised approach using label propagation to support citation screening.

ABSTRACT: Citation screening, an integral process within systematic reviews that identifies citations relevant to the underlying research question, is a time-consuming and resource-intensive task. During the screening task, analysts manually assign a label to each citation, to designate whether a citation is eligible for inclusion in the review. Recently, several studies have explored the use of active learning in text classification to reduce the human workload involved in the screening task. However, existing approaches require a significant amount of manually labelled citations for the text classification to achieve a robust performance. In this paper, we propose a semi-supervised method that identifies relevant citations as early as possible in the screening process by exploiting the pairwise similarities between labelled and unlabelled citations to improve the classification performance without additional manual labelling effort. Our approach is based on the hypothesis that similar citations share the same label (e.g., if one citation should be included, then other similar citations should be included also). To calculate the similarity between labelled and unlabelled citations we investigate two different feature spaces, namely a bag-of-words and a spectral embedding based on the bag-of-words. The semi-supervised method propagates the classification codes of manually labelled citations to neighbouring unlabelled citations in the feature space. The automatically labelled citations are combined with the manually labelled citations to form an augmented training set. For evaluation purposes, we apply our method to reviews from clinical and public health. The results show that our semi-supervised method with label propagation achieves statistically significant improvements over two state-of-the-art active learning approaches across both clinical and public health reviews.

SUBMITTER: Kontonatsios G

PROVIDER: S-EPMC5726085 | biostudies-other | 2017 Aug

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

A semi-supervised approach using label propagation to support citation screening.

Kontonatsios Georgios G Brockmeier Austin J AJ Przybyła Piotr P McNaught John J Mu Tingting T Goulermas John Y JY Ananiadou Sophia S

Journal of biomedical informatics 20170623

Citation screening, an integral process within systematic reviews that identifies citations relevant to the underlying research question, is a time-consuming and resource-intensive task. During the screening task, analysts manually assign a label to each citation, to designate whether a citation is eligible for inclusion in the review. Recently, several studies have explored the use of active learning in text classification to reduce the human workload involved in the screening task. However, ex ...[more]

PMID: 28648605

Similar Datasets

Project description:BackgroundClinically, behavior, cognitive, and mental functions are affected during the neurodegenerative disease progression. To date, the molecular pathogenesis of these complex disease is still unclear. With the rapid development of sequencing technologies, it is possible to delicately decode the molecular mechanisms corresponding to different clinical phenotypes at the genome-wide transcriptomic level using computational methods. Our previous studies have shown that it is difficult to distinguish disease genes from non-disease genes. Therefore, to precisely explore the molecular pathogenesis under complex clinical phenotypes, it is better to identify biomarkers corresponding to different disease stages or clinical phenotypes. So, in this study, we designed a label propagation-based semi-supervised feature selection approach (LPFS) to prioritize disease-associated genes corresponding to different disease stages or clinical phenotypes.MethodsIn this study, we pioneering put label propagation clustering and feature selection into one framework and proposed label propagation-based semi-supervised feature selection approach. LPFS prioritizes disease genes related to different disease stages or phenotypes through the alternative iteration of label propagation clustering based on sample network and feature selection with gene expression profiles. Then the GO and KEGG pathway enrichment analysis were carried as well as the gene functional analysis to explore molecular mechanisms of specific disease phenotypes, thus to decode the changes in individual behavioral and mental characteristics during neurodegenerative disease progression.ResultsLarge amounts of experiments were conducted to verify the performance of LPFS with Huntington's gene expression data. Experimental results shown that LPFS performs better in comparison with the-state-of-art methods. GO and KEGG enrichment analysis of key gene sets shown that TGF-beta signaling pathway, cytokine-cytokine receptor interaction, immune response, and inflammatory response were gradually affected during the Huntington's disease progression. In addition, we found that the expression of SLC4A11, ZFP474, AMBP, TOP2A, PBK, CCDC33, APSL, DLGAP5, and Al662270 changed seriously by the development of the disease.ConclusionsIn this study, we designed a label propagation-based semi-supervised feature selection model to precisely selected key genes of different disease phenotypes. We conducted experiments using the model with Huntington's disease mice gene expression data to decode the mechanisms of it. We found many cell types, including astrocyte, microglia, and GABAergic neuron, could be involved in the pathological process.

Project description:BackgroundModern molecular profiling techniques are yielding vast amounts of data from patient samples that could be utilized with machine learning methods to provide important biological insights and improvements in patient outcomes. Unsupervised methods have been successfully used to identify molecularly-defined disease subtypes. However, these approaches do not take advantage of potential additional clinical outcome information. Supervised methods can be implemented when training classes are apparent (e.g., responders or non-responders to treatment). However, training classes can be difficult to define when assessing relative benefit of one therapy over another using gold standard clinical endpoints, since it is often not clear how much benefit each individual patient receives.ResultsWe introduce an iterative approach to binary classification tasks based on the simultaneous refinement of training class labels and classifiers towards self-consistency. As training labels are refined during the process, the method is well suited to cases where training class definitions are not obvious or noisy. Clinical data, including time-to-event endpoints, can be incorporated into the approach to enable the iterative refinement to identify molecular phenotypes associated with a particular clinical variable. Using synthetic data, we show how this approach can be used to increase the accuracy of identification of outcome-related phenotypes and their associated molecular attributes. Further, we demonstrate that the advantages of the method persist in real world genomic datasets, allowing the reliable identification of molecular phenotypes and estimation of their association with outcome that generalizes to validation datasets. We show that at convergence of the iterative refinement, there is a consistent incorporation of the molecular data into the classifier yielding the molecular phenotype and that this allows a robust identification of associated attributes and the underlying biological processes.ConclusionsThe consistent incorporation of the structure of the molecular data into the classifier helps to minimize overfitting and facilitates not only good generalization of classification and molecular phenotypes, but also reliable identification of biologically relevant features and elucidation of underlying biological processes.

Dataset Information

A semi-supervised approach using label propagation to support citation screening.

Publications

A semi-supervised approach using label propagation to support citation screening.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets