OPEN Health
Artificial Intelligence in Systematic Literature Reviews
Pages
1
Time to read
6 mins
Publication
Language
English
Pages
1
Time to read
6 mins
Publication
Language
English
This technical report assesses the effectiveness of artificial intelligence (AI) in replacing human reviewers for literature screening and selection in systematic literature reviews (SLRs). The study specifically examines the use of Evidence Prime's Laser AI platform in a comprehensive SLR concerning biologic treatments for Crohn's disease, which involved eight updates. The report documents the accuracy of AI in identifying relevant studies, noting that the AI achieved a sensitivity of 95.8% and a specificity of 88.5% across the updates. It outlines the workload savings associated with AI, indicating an average reduction of 45.4% in human screening effort compared to traditional methods. The report emphasizes that while AI can effectively assist in the screening phase, achieving high sensitivity may lead to an increase in the number of studies requiring full-text review. The findings suggest that AI tools can significantly enhance the efficiency of SLRs while maintaining control for human reviewers.