Citation screening using crowdsourcing and machine learning produced accurate results: Evaluation of Cochrane's modified Screen4Me service

• Published in: Journal of clinical epidemiology Vol. 130; pp. 23 - 31
• Main Authors: Noel-Storr, Anna, Dooley, Gordon, Affengruber, Lisa, Gartlehner, Gerald
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.02.2021; Elsevier Limited
• Subjects: Accuracy; Agreement algorithm; Agreements; Algorithms; Classifiers; Crowdsourcing; Datasets; Decision making; Epidemiology; Human computation; Identification; Internal Medicine; Learning algorithms; Literature reviews; Literature screening; Machine learning; Medical research; Performance assessment; Screening; Sensitivity; Systematic review; Systematic reviews; Workflow; Crowdsourcing; Accuracy; Human computation; Agreement algorithm; Machine learning; Literature screening; Systematic reviews; agreement algorithm; crowdsourcing; human computation; accuracy; systematic reviews; machine learning; literature screening

To assess the feasibility of a modified workflow that uses machine learning and crowdsourcing to identify studies for potential inclusion in a systematic review. This was a substudy to a larger randomized study; the main study sought to assess the performance of single screening search results versu...