Axelium vs RobotReviewer

Axelium is an AI-assisted platform for systematic reviews and meta-analyses, spanning evidence search, screening, analysis, reporting, and living reviews. Its 11 stages include protocol, search, screening, full-text review, extraction, RoB 2.0, GRADE, statistics, network meta-analysis, reporting, and living reviews. The maker says AI extracts structured values while deterministic code calculates statistics, and data points link to snippets in original PDFs. Listed methods include pairwise and network synthesis, Cochrane RoB 2.0, GRADE certainty ratings, CERQual, and PRISMA-style reporting. It imports references from tools and databases including EndNote, Zotero, PubMed, ClinicalTrials.gov, and Web of Science; exports include DOCX, XLSX, RIS, BibTeX, and RevMan. Team controls include roles, comments, dual-person sign-off, conflict adjudication, and versioned audit snapshots. A free plan includes one lifetime review and one seat; Researcher costs $29 a month. Human validation is needed for screening suggestions, extracted values, risk-of-bias assessments, and draft reports. Recurring statistical refresh for living-review network meta-analysis is paused, though scheduled cycles can import, screen, and extract new evidence.

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.