Before using this in research
The goal is not to adopt another tool. The goal is to reduce verified research time without weakening the evidence trail.
Biomedical, medical, clinical, public health, and academic researchers who need to identify relevant studies, trace evidence, explore related papers, and support structured literature reviews.
Start by defining your research question, key concepts, inclusion criteria, and target databases or evidence sources before choosing a tool.
A safer workflow
- 1Use biomedical databases and scholarly search tools to identify core studies, systematic reviews, guidelines, and recent papers related to your question.
- 2Use evidence discovery tools such as Elicit or Consensus to screen abstracts, surface study-level information, and generate candidate papers for further review.
- 3Use Semantic Scholar, ResearchRabbit, Connected Papers, or similar citation tools to trace influential papers, related work, backward citations, and forward citations.
- 4Verify all candidate evidence in the original publications, export citations where possible, and document search terms, dates, tools used, and screening decisions.
Watch-outs
- Do not rely on AI-generated summaries or rankings as evidence without checking the original article, methods, population, outcomes, and limitations.
- Coverage varies across tools; some may miss biomedical indexing details, preprints, non-English studies, or recently published articles.
- Citation networks can reinforce highly cited literature and may overlook newer, negative, or less visible studies.
Evidence checks
- Confirm whether each source is peer-reviewed, a preprint, a guideline, a systematic review, or a primary study.
- Check study design, sample size, population, intervention or exposure, comparator, outcomes, bias risk, and conflicts of interest.
- Cross-check important findings in PubMed, publisher pages, clinical trial registries, systematic reviews, or guideline repositories when appropriate.
Need the complete current version?
Open the full detail page
This English version is a curated decision page. The full current detail page remains available while the English library is being expanded.
Open current full topic