Turn collections of academic PDFs into structured datasets using the extraction questions that matter to your review.
Provide your papers and your extraction framework, and receive an Excel workbook with an answer and a short reasoning note for every question, ready for you to check.
Academic PDFs
Extraction questions
Structured extraction
Excel output
Researcher review
Data extraction for a systematic review usually means locating the same types of information (study design, sample size, outcomes) across dozens or hundreds of papers, one at a time.
Systematically Reviewed lets you define your extraction framework once, in a spreadsheet, and applies it to your full set of papers. Instead of a blank table to fill in, you start from a completed one to check and correct.
Your extraction questions, applied consistently across your papers.
The template workbook has two sheets, paper_level_data and variable_level_data. You decide whether to use one or both.
Paper level (one row per paper)
Questions asked once about the whole paper. If this is all you need, fill in this sheet alone.
e.g. “What study design was used?”
Variable level (one row per item)
Use this sheet when a paper reports several models, treatments, or exposures and you want a row for each. Leave it empty to keep one row per paper.
e.g. “What sample size was used for {variable_name}?”
Supply your papers as PDF files. Extraction covers the main text as well as tables and figures, and records only information explicitly stated in each paper.
You receive a single Excel workbook with one row per paper, or one row per item when you use variable-level questions. Each question appears as a column paired with a reasoning column explaining where the answer was found.
Use the provided cross-checking application to review results one paper at a time. Edit extracted values, view reasoning notes, with the source PDF side by side, and mark each field as correct or incorrect before export.
Each question becomes a column in your workbook, paired with a reasoning note.
Both layouts come from the same template: paper-level questions alone, or with variable-level questions added so that each model, treatment, or exposure has its own row.
Showing 2 rows.
| pdf_name | study_design | variable_abstraction |
|---|---|---|
| Rodriguez_2026 | Retrospective cohort (target trial emulation) | ADM trial; AOM trial; MAUD-T2D trial; MAUD-obesity trial |
| Chen_2024 | Propensity-score matched cohort | Semaglutide; Tirzepatide |
The variable_abstraction question returns a semicolon-separated list, and each listed item becomes its own row with the paper-level answers repeated. Every question is paired with a reasoning column; one is shown here.
Extraction is AI-assisted, the program allows you to easily verify and update results before relying on them.
After delivery, you review results in a web application. You will receive an email with a link to the application with your results. Load the Excel workbook, work through one paper at a time, with the matching source PDF side by side. Each extracted field shows the value alongside a read-only reasoning note from the extraction, and shortcut to see exactly where the answer was found.
Edit any value, mark fields as correct or incorrect, and export your reviewed data with a parallel correctness grid. All processing happens locally in your browser; nothing is uploaded during verification.
Review one paper at a time, edit cells, mark each field correct or incorrect, then export.
Rodriguez_2026
Correct: 1 · Incorrect: 0 · Pending: 1 · Rows complete: 0/2
1 / 2 variables reviewed
Viewing: Rodriguez_2026.pdf
Source PDF opens alongside extracted fields on larger screens.
Variable-level data
hazard_ratio
Reasoning
outcome_of_interest
Reasoning
I'm Jackson, I am a medical doctor halfway through Australian physicians training currently completing a PhD in population health at the University of Oxford. I built this tool as I was doing my own systematic review because I thought it should exist, but just couldn't find it available anywhere on the internet.
My main aim for this tool is to assist in reproducible, reliable data extraction from academic papers. The tool uses both traditional and AI methods to extract data from PDF documents, including tables and figures, which are the passed through a harnsed LLM to generate results. It has helped speed up my own and my colleagues research, without compromising on quality.
I genuinely want this tool to produce as high quality results as possible. Whilst I have iterated and tried to consider edge cases, there are almost certainly failure modes or design flaws I have missed. As such, if you choose to use this tool and would either be willing to share your final checked data extraction table, or meaningful feedback on your experience with the tool, I will give you a 50% refund on the initial payment.
I see this as part of a broader project in reducing residual time spent in research on repetitive and automatable tasks. I ramble on my blog here if you'd like to read more. Thanks for supporting the project.
I offer a no questions asked full refund if for any reason the tool does not meet expectations.
Apply the same extraction framework across every paper in your review, with the same question definitions and answer formats throughout.
Define questions relevant to your specific review: text, numbers, categories from your own list, or lists of items extracted per paper.
Inspect and amend every extracted value before analysis. Reasoning notes help you locate answers in the source paper.
Receive a structured Excel workbook that fits existing evidence-synthesis workflows, with an export path for reviewed results and correctness labels.
Select the package that best matches your review. After payment, you will be directed to submit your papers and extraction framework.
Up to 10 papers
£25
For small reviews, pilot projects or testing the workflow.
Up to 30 papers
£50
For typical systematic review extraction projects.
Up to 60 papers
£75
For larger systematic reviews and evidence-synthesis projects.
Contact us to discuss projects that fall outside the standard packages.
Contact UsComplete checkout through Stripe. You will receive a confirmation with next steps.
After payment, you are directed to a submission page. Upload your PDF papers and your completed extraction framework workbook. If you have not filled in the template yet, download it here.
Download the template workbook (.xlsx)We process your papers and deliver a structured Excel workbook. Use the cross-checking application to review, edit, and export your verified results.
Choose a package and turn your extraction framework into structured, reviewable results.
View Pricing