Assessing the accuracy of machine-assisted abstract screening with DistillerAI: a user study

• Published in: Systematic reviews Vol. 8; no. 1; pp. 277 - 10
• Main Authors: Gartlehner, Gerald, Wagner, Gernot, Lux, Linda, Affengruber, Lisa, Dobrescu, Andreea, Kaminski-Hartenthaler, Angela, Viswanathan, Meera
• Format: Journal Article
• Language: English
• Published: England BioMed Central 15.11.2019; BMC
• Subjects: Accuracy; Artificial intelligence; Automation; Cost control; Machine learning; Methods study; Natural language processing; Rapid reviews; Software; Support vector machines; Systematic review; Systematic reviews; Workloads; United States > US; Systematic reviews; Methods study; Rapid reviews; Accuracy; Machine-learning

Web applications that employ natural language processing technologies to support systematic reviewers during abstract screening have become more common. The goal of our project was to conduct a case study to explore a screening approach that temporarily replaces a human screener with a semi-automate...