Semi-automated title-abstract screening using natural language processing and machine learning

Abstract

Background: Title-abstract screening in the preparation of a systematic review is a time-consuming task. Modern techniques of natural language processing and machine learning might allow partly automatization of title-abstract screening. In particular, clear guidance on how to proceed with these techniques in practice is of high relevance. Methods: This paper presents an entire pipeline how to use natural language processing techniques to make the titles and abstracts usable for machine learning and how to apply machine learning algorithms to adequately predict whether or not a publication should be forwarded to full text screening. Guidance for the practical use of the methodology is given. Results: The appealing performance of the approach is demonstrated by means of two real-world systematic reviews with meta analysis. Conclusions: Natural language processing and machine learning can help to semi-automatize title-abstract screening. Different project-specific considerations have to be made for applying them in practice.