Table 1.

Summary of Methods Proposed for Aiding in Systematic Review

Ref #	Title	Year	Machine-Learning Algorithm(s) Used	Comments
1	Text categorization models for high-quality article retrieval in internal medicine	2005	Naïve Bayes, Adaboost, SVM	First known method
2	A comparison of citation metrics to machine-learning filters for the identification of high-quality MEDLINE documents	2006	Support Vector Machines (SVM)
3	Reducing workload in systematic review preparation using automated citation classification	2006	Perceptron based voting
4	Optimizing feature representation for automated systematic review work prioritization	2008	SVM	Extensive research on Machine-learning features
5	Cross-topic learning for work prioritization in systematic review creation and update	2009	SVM
6	A new algorithm for reducing the workload of experts in performing systematic reviews	2010	Factorized version of Complement Naïve Bayes (FCNB)
7	Semi-automated screening of biomedical citations for systematic reviews	2010	ensemble of SVMs	Uses active learning
8	Toward automating the initial screening phase of a systematic review	2010	Evolutionary SVM
9	Exploiting the systematic review protocol for classification of medical abstracts	2011	FCNB

Ref #: the citation in the References section (1-,9 respectively, correspond to Aphinyanaphongs et al, 2006; Aphinyanaphongs et al, 2005; Bekhuis and Demner-Fushman, 2010; A.M. Cohen et al, 2006; A.M. Cohen, 2008; A.M. Cohen et al, 2009; Frunza et al, 2011; Matwin et al, 2010; Wallace et al, 2010); Title: title of the paper; Year: the year in which the article is published.