The ASReview Research Team continuously explores and investigates new ways to improve ASReview through simulation studies, use-cases, and more. The team doesn’t do this all alone, but often together with other organizations, research groups, and developers. The findings are published in peer-reviewed journals like Nature Machine Intelligence. By publishing data, scripts and underlying code, all work becomes fully transparent too.
The ASReview project was initiated at Utrecht University by Prof. dr Rens van de Schoot, dr. Daniel Oberski and Prof. dr. Lars Tummers in 2018. The award winning project has now grown into a full multidisciplinary research team that works hand in hand with the ASReview community. The team works according to the Open Science principles and invests in an inclusive community that contributes to the project.
In a time of exponential growth of new evidence supporting clinical decision making, combined with a labor-intensive process of selecting this evidence, there is a need for methods to speed up current processes in order to keep medical guidelines up-to-date.
We show that by using active learning, ASReview can lead to far more efficient reviewing than manual reviewing, while exhibiting adequate quality. Furthermore, the presented software is fully transparent and open source.
After manually screening 5050 studies, Smid et al included only 27 studies for their review. In the current study, both the Bayesian and logistic regression models found more than 80% of relevant publications after screening only 10% of all publications.
To determine the defaults we performed a simulation study and Naive Bayes + TF-IDF model performed the best.
