From research papers to reviewed evidence.
Collect studies, extract structured data with AI, resolve reviewer disagreements, assess risk of bias, and build your synthesis in one workspace.
AI assists. Your team reviews and decides.
Developed within Penn Dental MedicineWe enrolled 124 patients aged 3–6 years from four community clinics and randomised them to 38% SDF or placebo varnish. Allocation was concealed using sequentially numbered opaque envelopes prepared by a statistician not involved in recruitment.
Children were eligible if they presented with at least one active carious lesion in a primary tooth.
“We enrolled 124 patients aged 3–6 years from four community clinics and randomised them to 38% SDF or placebo varnish.”
Independent reviews. One recorded decision.
Reviewers enter values independently. Where they differ, the adjudicator sees every entry with its evidence, a majority suggestion when two agree, and records one decision.
Assess risk of bias with the evidence in view.
Reviewers work through RoB 2 domains for parallel-group randomized trials with the supporting evidence visible, and resolve differences into a recorded assessment.
Reviewed evidence becomes synthesis.
Map fields to outcomes and comparisons, confirm eligible studies, then pool with a forest plot and diagnostics, or synthesize without pooling when pooling is not appropriate.
One workspace for the review team.
Project owners define the scope and assign reviewer seats. Each reviewer sees the studies waiting on them; leads see progress across extraction, consensus and appraisal.
- P
- Children 3–6 with active caries
- I
- Silver diamine fluoride 38%
- C
- Placebo varnish
- O
- Caries arrest at 12 months
Bring evidence in. Take reviewed work out.
Records arrive from the sources review teams already use. What leaves carries the review with it: values with their source pages, judgements with their evidence, and plots with the study-level data behind them.
- Collect & configure48/48
- Extract44/48
- Review31/48
- Assess · RoB 218/48
- Synthesize—
Questions teams ask first.
- Where does AI fit into the review?
- AI can assist with extraction and suggestions. Reviewers inspect the evidence and make the recorded decisions.
- What can I import?
- PDFs, RIS and EndNote files, DOIs, and records found through PubMed and ClinicalTrials.gov search.
- Which risk-of-bias tool is supported?
- RoB 2 for parallel-group randomized trials.
- Do I have to pool studies?
- No. When pooling is not appropriate, eviStreams can retain the reported results and their sources for structured synthesis without a pooled estimate.