Systematic reviews in minutes to hours using artificial intelligence

Abstract Systematic reviews are used in academia, biotechnology, pharmaceutical companies and government to synthesise and appraise large numbers of publications. The current (largely manual) workflow takes an average of 9-18 months 1 , at a cost of $100,000+ per review 2 . We built a platform, ScholaraAI, that leverages artificial intelligence to cut this to < 0.1% of the time, without compromising quality. ScholaraAI facilitates end-to-end systematic reviews; search, screening, data extraction, and analysis. The workflow is transparent, and the researcher is in the loop. Our approach is compliant with the PRISMA and RAISE frameworks. Compared to a benchmarking set of published systematic reviews, ScholaraAI’s sensitivity for correctly included studies is 100% ± 0%, its specificity for correctly excluded studies is 90.8 ± 8.6%, and its accuracy for data extraction is 98.0 ± 3.5%. The time taken per review was 3.67 hours ± 1.26. We used ScholaraAI to produce a novel, up-to-date systematic review and meta-analysis, which is presented here. ScholaraAI is free to try at app.scholara.ai .