- Home
- Systematic Review Software
- ReviewAid
ReviewAid
What it is
ReviewAid is a free, open-source AI tool for full-text screening and data extraction in systematic reviews. Researchers can provide PICO inclusion and exclusion criteria for classifying papers, then define the fields they want extracted. The tool reports confidence scores and flags low-confidence results for human review; its maker describes it as supplementary to, not a replacement for, manual screening or extraction. Results can be downloaded as CSV, XLSX or DOCX files. ReviewAid supports OpenAI, Anthropic, DeepSeek, Cohere, Z.ai and local Ollama. With a cloud provider, paper text is sent there for the run; with Ollama, inference takes place locally and the text stays on the machine. The maker says API keys are not stored. Use the browser-based Streamlit app or run it locally with Python 3.12 or later and Streamlit on Windows, macOS or Linux. Submission guidance limits full-text screening to 10 articles and extraction to 20 per submission. The hosted app may take about 30 seconds to initialize. ReviewAid is licensed under Apache 2.0.
For and against
For
- Classifies full-text papers against user-provided PICO criteria.
- Users define the extraction fields they need.
- Exports results as CSV, XLSX or DOCX.
- Ollama keeps paper text on the local machine.
Against
- Full-text screening submissions are limited to 10 articles.
- Extraction submissions are limited to 20 articles.
- Hosted app may take about 30 seconds to initialize.
The verdict
ReviewAid provides screening and extraction assistance with confidence flags and downloadable results, while leaving manual review important. Choose local Ollama if you want paper text to stay on your machine.
Who it suits
ReviewAid is intended for researchers, particularly those working on evidence synthesis, who want assistance with systematic-review screening or extraction while retaining manual oversight.
Plans and prices
Free
Open source · Apache 2.0
Read 7 Oct 2026 · reviewaid.github.io
On the record
- AI providers
- The maker lists OpenAI, Anthropic, DeepSeek, Cohere, Z.ai, and local Ollama as supported providers.reviewaid.github.io · read 7 Oct 2026
- API key privacy
- The maker says API keys are not stored.reviewaid.github.io · read 7 Oct 2026
- Batch limits
- The README says to limit each submission to 20 articles for data extraction and 10 for full-text screening.github.com · read 7 Oct 2026
- Batch processing
- The site lists batch processing of up to 20 papers, while the repository instructions limit extraction submissions to 20 articles and screener submissions to 10.github.com · read 7 Oct 2026
- Cloud processing
- When a cloud provider is selected, the repository documentation says paper text is sent to that provider for the run.aurumz-rgb.github.io · read 7 Oct 2026
- Confidence scoring
- ReviewAid assigns confidence scores and flags low-confidence or unreliable results for manual review.aurumz-rgb.github.io · read 7 Oct 2026
- Custom extraction
- Users can define the data fields they want extracted from research papers.github.com · read 7 Oct 2026
- Exports
- Screening and extraction results can be downloaded as CSV, XLSX, or DOCX.aurumz-rgb.github.io · read 7 Oct 2026
- Hosted service limitation
- The maker notes that the Streamlit-hosted web app may have cold starts, including waits of about 30 seconds while it initializes.github.com · read 7 Oct 2026
- Human oversight
- The maker says ReviewAid is a supplementary reviewer and is not intended to replace manual screening or data extraction.reviewaid.github.io · read 7 Oct 2026
- Intended users
- The maker says ReviewAid was built to assist researchers, especially those involved in evidence synthesis.aurumz-rgb.github.io · read 7 Oct 2026
- License
- ReviewAid is licensed under Apache 2.0.reviewaid.github.io · read 7 Oct 2026
- Local inference
- With Ollama, inference runs locally and the maker says paper text is not sent to external servers.aurumz-rgb.github.io · read 7 Oct 2026
- Local installation
- The repository instructions describe running ReviewAid locally with Python 3.12 or later and Streamlit on Windows, macOS, or Linux.github.com · read 7 Oct 2026
- Local use
- ReviewAid can be run locally with Streamlit, and its Ollama option runs inference on the local machine without an external API key.github.com · read 7 Oct 2026
- Maintainer
- The maker page credits Vihaan Sahu; the journal author page identifies him as lead developer at Georgian National University SEU.reference-global.com · read 7 Oct 2026
- Online access
- The app is available as a browser-based Streamlit web app without installation.aurumz-rgb.github.io · read 7 Oct 2026
- PICO screening
- It classifies full-text papers against user-provided PICO inclusion and exclusion criteria.github.com · read 7 Oct 2026
