← Back to home

About TrialReviewer

TrialReviewer is an evidence-appraisal tool for the medical literature. It doesn't just recap a paper — it appraises the evidence like a clinical epidemiologist: recomputing absolute benefit (ARR / NNT), surfacing methodology flaws, grading certainty in the spirit of GRADE, and giving an A/B/C/D appraisal-confidence rating with a one-line bottom line.

What it does

It covers randomized controlled trials (RCT), meta-analyses, and observational studies. Expert mode is for clinicians and reviewers; Teaching mode is for medical and graduate students. Every threshold judgment carries an inline [Author Year] citation and is grounded in established evidence-appraisal methods and core references — not the model's intuition.

Privacy

The paper text you paste is sent to Anthropic's model API to generate the appraisal; PDFs you upload are parsed for text locally in your browser and the file itself is not uploaded. When signed in, your analyses (study type, mode, report, timestamp) are stored in Supabase, tied only to your account, and only you can access them; authentication is provided by Clerk. We do not sell your data.

Who made it

TrialReviewer is built by an independent developer for medical education and evidence-appraisal research.

TrialReviewer appraises evidence quality to inform professional judgment; it is not medical advice, and clinical decisions are made by the clinician.