RobotReviewer vs Silvi

RobotReviewer analyzes clinical trial reports by annotating PDFs with PICO characteristics and likely bias assessments using the Cochrane Risk of Bias tool. Uploading PDFs on the website extracts key data and presents a summary table. Its REST API can process groups of clinical trial reports to synthesize results across trials. The project is open source under GNU GPL version 3.0 and is free to use. It can run locally as Docker services, with a web app and API server exposed on local ports. The self-hosted processing setup uses Grobid, RabbitMQ, Celery, and SciBERT through bert-as-a-service. Docker instructions cover GPU use, and the worker can also run CPU-only. Manual setup calls for Python 3.6, TensorFlow 1.12.0, and the associated processing services. Installation is documented as tested on Ubuntu and Mac OS; Windows works with substantial installation difficulty. Maintainers ask users to cite the 2017 ACL paper and invite questions by email, including requests for help integrating RobotReviewer into other software.

Silvi is a web tool for organizing scientific literature into structured evidence. Its review workflow covers collecting studies, screening them, extracting data and analyzing results, including systematic reviews, meta-analyses and network meta-analyses. Reviewers can include or exclude studies individually or in bulk, with AI screening suggestions available. Data extraction can use PDF text highlights, which Silvi stores alongside the extracted information, or AI; users can check and correct AI results. Extracted data can be organized in tables, plotted and exported. Teams can assign tasks, require multiple reviewers and blind decisions. Silvi lists imports from PubMed, OpenAlex, Web of Science, ERIC, Zotero, Mendeley and EndNote. Its Web of Science RIS workflow allows up to 1,000 records per export. Open-access papers can be retrieved automatically; paywalled papers must be obtained through a university library. Plans include a free option and paid options from €19/mo.