Click Any Answer, See the Exact Sentence in the PDF
Click an extracted answer and the PDF viewer opens the cited page with that quote highlighted. The same quotes are on the Excel Audit Trail sheet.
Read articleEvidence Table Builder
Research PDFs in. Defensible tables out.
Extract structured answers for systematic reviews, meta-analyses, and CERs with verbatim quotes, page locations, and review flags in every Excel export.
Create a free account: 3 PDFs free, no card required.
See the extraction workflow
Watch Evidence Table Builder turn research PDFs into structured, reviewable Excel outputs.
Click any answer. See the exact sentence in the PDF.
Four example answers from one open-access trial. The highlight is the sentence behind the answer.
Preview shows the sample-size sentence.
Starling et al., JAMA Network Open, 2024. Voice-Activated Cognitive Behavioral Therapy for Insomnia. DOI · CC BY 4.0. © 2024 Starling CM et al. Highlights added; answers paraphrased. Open the sample PDF.
Built for evidence work
Systematic reviewsMeta-analysesClinical evaluation reportsHTA submissionsHEOR evidence tablesRCTsObservational studiesSafety narrativesComparative effectivenessLiterature screening follow-ups
Literature screening follow-upsComparative effectivenessSafety narrativesObservational studiesRCTsHEOR evidence tablesHTA submissionsClinical evaluation reportsMeta-analysesSystematic reviews
From study PDFs to a review-ready table
A focused extraction path, not another chat-with-PDF toy. Define what you need once, then reuse it across your corpus.
- 01
Upload studies
Drop one PDF or a full batch. Keep moving while files process.
- 02
Define questions
Set the fields your evidence table needs—population, outcomes, follow-up, and more.
- 03
Export with proof
Receive structured Excel plus an Audit Trail sheet: quotes, locations, confidence, flags.
Batch intake
Upload multiple papers and extract against the same question set—ideal for screening follow-ups and living reviews.
Smith_2023_RCT.pdf
12 pages
Chen_2022_Cohort.pdf
18 pages
Garcia_2024_Meta.pdf
24 pages
- Mean age
- Sample size
- Intervention
- Comparator
- Primary endpoint
- Follow-up duration
- Inclusion criteria
- Adverse events
Analysis-ready Excel, not loose notes
Consistent columns for filtering and synthesis—plus a second sheet that keeps every answer accountable.
ResultsAudit Trail
Question
Answer
Flag
Mean age
64.5 yrs
Verified
Follow-up
24 mo
Verified
Endpoint
—
Not found
Every extracted answer keeps its source
Results and Audit Trail ship together - verbatim quotes, page locations, confidence scores, and review flags so the table stays defensible.
Evidence_Table_Export.xlsx
Two sheets · one export| Question | Verbatim | Location | Conf. | Flag |
|---|---|---|---|---|
| Mean age | "The mean age of the study population was 64.5 ± 8.2 years at baseline." | Results · Table 1 Page 4 | 98% | Verified |
| Follow-up duration | "Participants were followed for a median of 24 months (IQR 18–30)." | Methods · §2.3 Page 2 | 95% | Verified |
| Sample size | "A total of 412 patients met eligibility and were included." | Abstract Page 1 | 99% | Verified |
| Primary endpoint | "Outcome data not explicitly reported in Table 4." | Results · Table 4 Page 12 | N/A | Not found |
| Intervention | "Active treatment with an SGLT2 inhibitor compared with matched placebo." | Methods · Interventions Page 3 | 81% | Needs review |
| Comparator | "Control participants received matched placebo tablets." | Methods · §2.1 Page 3 | 96% | Verified |
| Adverse events | "Safety events were described narratively without a consistent severity scale." | Results · Safety Page 9 | 74% | Ambiguous |
Extraction without a paper trail is just a guess
Every cell can point back to the source language, the page it came from, and a status flag when the paper is silent or ambiguous.
- Verbatim quotes keep the exact wording behind each answer.
- Locations cite section, table, and page for rapid verification.
- Status flags surface not found, ambiguous, and needs-review answers before you publish.
- Human verification confirms or corrects each answer against the PDF. Highlighted quotes are AI-cited evidence; Verified means a person checked them.
Smith_2023_RCT.pdf
Page 4 · Results · Baseline characteristicsLinked to Excel · Mean age
Table 1 summarizes demographic and clinical characteristics. The mean age of the study population was 64.5 ± 8.2 years at baseline. Sixty-two percent of participants were male.
VerifiedConfidence 98%
Live audit signals
Latest from the blog
Guides on evidence tables, systematic reviews, and HEOR workflows.
Free Data Extraction Template for Systematic Reviews
Download a free data extraction template for systematic reviews: PICO, design, outcomes by timepoint, effect sizes, and risk-of-bias domains.
Read articleQuality Review Tool: Choose by Study Design
Match a quality review tool to the study design, then record RoB 2, ROBINS-I, NOS, QUADAS-2, AMSTAR 2, or CASP in the evidence table.
Read articlePyramid of Evidence: Study Pyramid and Levels
Pyramid of evidence (the study pyramid and level of evidence pyramid): the base, nursing Levels I–VII, and filtered vs unfiltered evidence.
Read articleData Extraction Tools for Systematic Reviews (Honest Comparison)
Compare data extraction tools for systematic reviews, including when a spreadsheet or another platform fits better.
Read articleMoving from Excel (or Covidence extraction) to Evidence Table Builder
Bring an Excel or Covidence extraction form into Builder: import the questions, check each quote on the page, then export Excel and Word.
Read article
Questions researchers ask first
Work with a professional
Need hands-on help with evidence tables, systematic reviews, or quality assessment? Request a consultation and we'll follow up within 24 hours.
Next step
Build your next evidence table with a paper trail
Upload studies, define your questions, and export Results plus Audit Trail in one pass.