Practical notes on AI literature review, screening, synthesis, and citation audit.
Data extraction is reducing included records to inspectable fields. It is not a results section, not a meta-analysis, and not something you complete from a title when full text is missing.
A research gap is not “more studies are needed.” It is a missing population, comparator, endpoint, follow-up, or design implied by included evidence. Here is how to turn a literature review into the next study.
Appraisal judges whether an extracted study can support an inference. LitSynth does not implement Cochrane RoB 2, ROBINS-I, or GRADE. Report the order, use the table as a worksheet, and do not mint Low/High badges.
Screening is not “the AI ranked papers.” It is pre-specified eligibility, an inspectable first pass on titles and abstracts, and a human who can reverse every recommendation.
ChatGPT and other LLMs frequently generate citations that look real but do not exist. Here is why hallucinated references happen, how to detect them, and safer workflows for AI-assisted literature reviews.
Learn how to automate your literature review using AI tools without sacrificing academic rigor. We cover finding papers, extracting data, and synthesizing findings safely.