An open source machine learning framework for efficient and transparent systematic reviews

To address the inefficiency and error-proneness of manual screening in systematic reviews and meta-analyses, the authors developed ASReview, an open-source machine learning-aided pipeline employing active learning. Simulation studies demonstrate ASReview's superior efficiency and high-quality results compared to manual reviewing. The paper details ASReview's features, including various machine learning models, and presents user experience test results. The authors advocate for community contributions to enhance open-source tools for systematic reviewing.

Rens van de Schoot, Jonathan de Bruin, Raoul Schram, Parisa Zahedi, Jan de Boer, Felix Weijdema, Bianca Kramer, Martijn Huijts, Maarten Hoogerwerf, Gerbrich Ferdinands, Albert Harkema, Joukje Willemsen, Yongchao Ma, Qixiang Fang, Sybren Hindriks, Lars Tummers, Daniel L. Oberski