ASReview

Uses

How it works

Comparisons

Evidence quality

Highlighted claims

• The protocol uses ASReview, an open-source AI tool based on natural language processing. — Long-term infection risks in haematological cancer survivors compared with individuals with no cancer history: protocol for a systematic review aided by artificial intelligence-based methods
• ASReview learns from inclusion and exclusion decisions and prioritises abstracts by predicted relevance. — Long-term infection risks in haematological cancer survivors compared with individuals with no cancer history: protocol for a systematic review aided by artificial intelligence-based methods
• The AI-assisted screening approach must be internally validated against manual screening before use in the main review process. — Long-term infection risks in haematological cancer survivors compared with individuals with no cancer history: protocol for a systematic review aided by artificial intelligence-based methods
• The ASReview validation set stops after 200 consecutive abstracts without an inclusion or after all 1000 abstracts are screened. — Long-term infection risks in haematological cancer survivors compared with individuals with no cancer history: protocol for a systematic review aided by artificial intelligence-based methods
• If validation fails, the team will assess other NLP-assisted methods or consider a fully manual review. — Long-term infection risks in haematological cancer survivors compared with individuals with no cancer history: protocol for a systematic review aided by artificial intelligence-based methods