Using Semi-Supervised Learning for the Creation of Medical Systematic Review: An Exploratory Analysis

In this research, we explore semi-supervised learning based classifiers to identify articles that can be included when creating medical systematic reviews (SRs). Specifically, we perform comparative study of various semi-supervised learning algorithm, and identify the best technique that is suited for SRs creation. We also aim to identify whether semisupervised learning technique with few labeled samples produce meaningful work saving for SRs creation. Through an empirical study, we demonstrate that semi-supervised classifiers are viable for selecting articles for systematic reviews and situations when only a few numbers of training samples are available.

[1]  Chengwei Huang,et al.  A Semi-Supervised Learning Algorithm Based on Modified Self-training SVM , 2011, J. Comput..

[2]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[3]  J. McGowan,et al.  Systematic reviews need systematic searchers. , 2005, Journal of the Medical Library Association : JMLA.

[4]  Juan Jose García Adeva,et al.  Automatic text classification to support systematic reviews in medicine , 2014, Expert Syst. Appl..

[5]  Stephen E. Robertson,et al.  Understanding inverse document frequency: on theoretical arguments for IDF , 2004, J. Documentation.

[6]  Klaus Linde,et al.  Updating systematic reviews. , 2006, Explore.

[7]  Aaron M. Cohen,et al.  Research Paper: Cross-Topic Learning for Work Prioritization in Systematic Review Creation and Update , 2009, J. Am. Medical Informatics Assoc..

[8]  Xiaojin Zhu,et al.  Semi-Supervised Learning , 2010, Encyclopedia of Machine Learning.

[9]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[10]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[11]  William R. Hersh,et al.  Reducing workload in systematic review preparation using automated citation classification. , 2006, Journal of the American Medical Informatics Association : JAMIA.

[12]  Zoubin Ghahramani,et al.  Learning from labeled and unlabeled data with label propagation , 2002 .

[13]  Dina Demner-Fushman,et al.  Screening nonrandomized studies for medical systematic reviews: A comparative study of classifiers , 2012, Artif. Intell. Medicine.

[14]  Jeff Shrager,et al.  Observation of Phase Transitions in Spreading Activation Networks , 1987, Science.

[15]  Min Song,et al.  Combining active learning and semi-supervised learning techniques to extract protein interaction sentences , 2011, BMC Bioinformatics.

[16]  Yi Mao,et al.  The Locally Weighted Bag of Words Framework for Document Representation , 2007, J. Mach. Learn. Res..

[17]  Stan Matwin,et al.  Building Systematic Reviews Using Automatic Text Classification Techniques , 2010, COLING.

[18]  Elizabeth Eckstrom,et al.  Screening for Cognitive Impairment in Older Adults: A Systematic Review for the U.S. Preventive Services Task Force , 2013, Annals of Internal Medicine.

[19]  Hongfang Liu,et al.  Research Paper: Automatic Resolution of Ambiguous Terms Based on Machine Learning and Conceptual Relations in the UMLS , 2002, J. Am. Medical Informatics Assoc..

[20]  Sophia Ananiadou,et al.  Supporting Systematic Reviews Using Text Mining , 2009 .

[21]  Benjamin Naumann.  The Architecture Of Cognition , 2016 .

[22]  David Ogilvie,et al.  Pinpointing needles in giant haystacks: use of text mining to reduce impractical screening workload in extremely large scoping reviews , 2014, Research synthesis methods.

[23]  G. Antes,et al.  Five Steps to Conducting a Systematic Review , 2003, Journal of the Royal Society of Medicine.

[24]  Matthias Seeger,et al.  Learning from Labeled and Unlabeled Data , 2010, Encyclopedia of Machine Learning.

[25]  J. Higgins.  Cochrane handbook for systematic reviews of interventions. Version 5.1.0 [updated March 2011]. The Cochrane Collaboration , 2011 .