RobotReviewer vs SWIFT-Review

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.

SWIFT-Review is a desktop workbench for formulating systematic reviews and prioritizing literature for screening. Statistical text mining and machine learning identify over-represented topics and rank documents for manual review. Users can search, categorize, prioritize, visualize, and extract information from large citation sets. The ranking workflow requires an initial training seed, and the software does not estimate how many relevant articles remain above a threshold. It can import PubMed IDs or XML, RIS files, and previously saved SWIFT Text-mining Project files; PMID imports retrieve citation data through NLM’s Entrez e-Utilities interface. Exports include Excel, RIS, and plain tab-delimited text. The free desktop software is available for Windows and Mac, with downloads through Sciome’s applications portal after signing in or creating a free account. Installation requires administrative access. The guide lists 64-bit Windows 7, 8, or 10 and 64-bit Mac OS X 10.8 or later, and recommends 8 GB RAM; very large projects may need more. Minor updates usually happen automatically, while major updates may require administrator privileges.