Identifying reports of randomized controlled trials (RCTs) via a hybrid machine learning and crowdsourcing approach

Journal of the American Medical Informatics Association

Volumn 24, Issue 6, 2017, Pages 1165-1168

  Wallace, Byron C ^a   Noel Storr, Anna ^b   Marshall, Iain J ^c   Cohen, Aaron M ^d   Smalheiser, Neil R ^e   Thomas, James ^f  

^a Northeastern University   (United States)

^b UNIVERSITY OF OXFORD   (United Kingdom)

^c KING'S COLLEGE LONDON   (United Kingdom)

^d OREGON HEALTH AND SCIENCE UNIVERSITY   (United States)

^e UNIVERSITY OF ILLINOIS   (United States)

^f UNIVERSITY COLLEGE LONDON   (United Kingdom)

Author keywords

Crowdsourcing; Evidence based medicine; Human computation; Machine learning; Natural language processing

Indexed keywords

CLASSIFIER; CONTROLLED STUDY; CROWDSOURCING; HUMAN; MEDICINE; NATURAL LANGUAGE PROCESSING; RANDOMIZED CONTROLLED TRIAL; RECALL; BIBLIOGRAPHIC DATABASE; INFORMATION RETRIEVAL; LITERATURE; MACHINE LEARNING; MEDICAL RESEARCH; PROCEDURES; RANDOMIZED CONTROLLED TRIAL (TOPIC); RECEIVER OPERATING CHARACTERISTIC; SUPPORT VECTOR MACHINE;

BIOMEDICAL RESEARCH; CROWDSOURCING; DATABASES, BIBLIOGRAPHIC; INFORMATION STORAGE AND RETRIEVAL; MACHINE LEARNING; NATURAL LANGUAGE PROCESSING; RANDOMIZED CONTROLLED TRIALS AS TOPIC; REVIEW LITERATURE AS TOPIC; ROC CURVE; SUPPORT VECTOR MACHINE;

EID: 85028670339     PISSN: 10675027     EISSN: 1527974X     Source Type: Journal    
DOI: 10.1093/jamia/ocx053     Document Type: Article

References (10)

1. Chalmers I. The Cochrane collaboration: preparing, maintaining, and disseminating systematic reviews of the effects of health care. Ann NY Acad Sci. 1993;703(1):156-65.
2. Cohen AM, Smalheiser NR, McDonagh MS, et al. Automated confidence ranked classification of randomized controlled trial articles: an aid to evidence-based medicine. J Am Med Inform Assoc. 2015;22(3):707-17.
3. McKibbon KA, Wilczynskil NL, Haynes RB. Retrieving randomized controlled trials from Medline: a comparison of 38 published search filters. Health Info Libr J. 2009;26(3):187-202.
4. Wieland LS, Robinson KA, Dickersin K. Understanding why evidence from randomised clinical trials may not be retrieved from Medline: comparison of indexed and non-indexed records. Brit Med J. 2012;344:2008-12.
5. Bastian H, Glaszio P, Chalmers I. Seventy-five trials and eleven systematic reviews a day: how will we ever keep up? PLoS Med. 2010;7(9):1-6.
6. Wallace BC, Trikalinos TA, Lau J, Brodley C, Schmid CH. Semi-automated screening of biomedical citations for systematic reviews. BMC Bioninformatics. 2010;11(1):55.
7. Cohen AM, Hersh WR, Peterson K, Yen P-Y. Reducing workload in systematic review preparation using automated citation classification. J Am Med Inform Assoc. 2006;13(2):206-19.
8. Joachims T. Text categorization with support vector machines: learning with many relevant features. In European Conference on Machine Learning (ECML). Berlin: Springer; 1998.
9. Wallace BC, Small K, Brodley CE, Trikalinos TA. Who should label what? Instance allocation in multiple expert active learning. In SIAM International Conference on Data Mining. Phoenix, AZ: Society for Industrial and Applied Mathematics; 2011.
10. Nguyen AT, Wallace BC, Lease M. Combining crowd and expert labels using decision theoretic active learning. In Human Computation and Crowdsourcing (HCOMP). San Diego, CA: Association for the Advancement of Artificial Intelligence (AAAI); 2015.