These pages explain how LitSynth supports screening, data extraction, and appraisal—and the limits that belong in a Methods section, a library procurement packet, or a review protocol.
Last reviewed 2026-09-24. Feature pages still exist for discovery. These pages exist for citation, teaching, and institutional review.
The sequence
Do not appraise bias on a title. Do not extract papers you have not screened. Do not report RoB 2 because a limitations field exists. The tutorial keeps those jobs in order so a methods committee can follow the trail.
Complete methods tutorial
A review is not a search box plus a draft. It is a sequence of decisions: which records enter, which fields are extracted, and which validity limits you are willing to report. This tutorial walks that sequence in the order a methods committee expects to see it.
Screening methods
Screening is the first decision that changes the evidence base. The method is not “the AI ranked papers.” The method is pre-specified criteria, a documented first pass on titles and abstracts, and a human who can reverse every recommendation.
Extraction methods
Extraction is where included studies become comparable. If a field cannot be traced to a paper, it does not belong in the synthesis. The method is structured cards, retained failures, and a human pass before drafting.
Appraisal methods
RoB is the stage institutions ask about and vendors most often overclaim. Appraisal judges whether an extracted study can support a causal or clinical inference. It is not a relevance score, and it is not a limitations bullet copied into a RoB 2 badge.
People searching “how to screen titles and abstracts” or “risk of bias after extraction” should find a method, not a pricing grid.
Each page includes paste-ready Methods language and a checklist of claims you still have to earn outside the tool.
Libraries and methods committees can see what LitSynth records, what it does not do (RoB 2, dual screening, GRADE), and where the human remains responsible.