Concepts · pipeline

How Axelium works

Axelium turns a review protocol into a transparent evidence workflow: find candidate studies, screen them, obtain full text, extract evidence, run the right synthesis, review the outputs, and generate a report.

The public workflow: every stage remains reviewable before it becomes part of the final report.

NOTE · User-visible workflow, not implementation detail

This page explains what reviewers see and what they need to check. Internal engineering mechanisms are intentionally not documented in the public docs.

Search, import, and study linking

Add records manually, import RIS/BibTeX libraries, generate a search strategy from your protocol, or use citation chasing to find related papers. Axelium deduplicates records and links trial registrations, publications, and companion papers where possible.

Search results enter the review as candidates, usually pending screening.
Optional source coverage can broaden recall beyond the primary clinical indexes.
Known-relevant papers can improve recall as pearls or citation-chasing seeds.
Source coverage is retained for transparent PRISMA reporting.

Search workflow — Fig 1Search, import, and Discover help reviewers assemble candidate records before screening.

Screening and eligibility

Screening applies the protocol to every candidate record. AI suggestions can provide a starting point, but reviewer decisions, exclusion reasons, dual-review modes, and conflict adjudication are the source of truth for formal reviews.

Included records continue to full text and extraction.
Excluded records keep their reason for PRISMA reporting.
Unsure records need reviewer attention or adjudication.

Full text, supplements, and manual upload

Full-text retrieval collects PDFs, supplements, and other source documents needed for extraction or qualitative coding. Open-access retrieval is attempted first; when a document remains unavailable, users can upload it manually or capture it with the browser companion if they have lawful access.

Supplements can include appendices, spreadsheets, and Word documents.
Parsed documents become available for source-backed extraction.
Blocked or missing documents stay visible so reviewers can resolve them.

Learn moreBrowser companion

Extraction, coding, and reviewer checks

Quantitative reviews extract structured values such as events, totals, means, standard deviations, time-to-event estimates, or prevalence data. Qualitative reviews code passages, appraise studies, and develop themes. In both cases, outputs should stay connected to source evidence and reviewer decisions.

Low-confidence or conflicting values should be reviewed before synthesis.
Qualitative themes and CERQual ratings are proposals until a reviewer finalises them.
Risk-of-bias and certainty judgements remain reviewer-owned.

Extraction workspace — Fig 2Extraction presents proposed values with source evidence and review status.

Synthesis and statistical analysis

The Analysis tab supports pairwise meta-analysis, common sensitivity checks, publication-bias views, qualitative synthesis outputs, and controlled-rollout advanced workflows such as network meta-analysis and ecology/evolution synthesis. The app surfaces plots, tables, and diagnostics; reviewers interpret them against the protocol and the quality of the underlying evidence.

Statistical analysis Network meta-analysis Ecology meta-analysis Qualitative synthesis

Review automation and approval checkpoints

Automated review can flag missing data, stale appraisals, inconsistent units, or protocol-level questions. Data-level repairs still need review before they become trusted evidence, and protocol-level changes pause for explicit approval.

WARN · Nothing protocol-level changes silently

If a suggested change would alter the protocol or included evidence set, treat it as a reviewer decision. Approve, reject, or document the rationale before reporting results.

Living reviews

Living reviews monitor for new studies and evidence changes after a review is established. New evidence returns through screening, full-text retrieval, extraction, analysis, and reviewer approval. One-off NMA preparation is supported separately from recurring living NMA refresh.

Reports and Evidence Board

The Evidence Board lets reviewers pin plots, tables, notes, and decisions that should support a report. Generated drafts use selected evidence as a starting point; they should be edited, checked, and approved before sharing.

Report creation — Fig 3Reports are generated from selected evidence and remain editable.

Teams and collaboration

Team reviews add roles, invitations, assignments, comments, notifications, dual-review modes, conflict adjudication, and milestone sign-off. Use collaboration features when a review needs independent judgements, workload splitting, or accountable approval.

Learn moreCollaboration guide

Data provenance and audit

Axelium is designed so reviewers can trace results back to studies, source documents, extracted values, reviewer decisions, and report evidence. This does not remove the need for manual verification; it makes verification easier to perform and explain.

Lineage panel — Fig 4Lineage views help trace results back to supporting studies and source evidence.

FAQ

Can I trust AI outputs without review? No. Suggestions, extracted values, appraisals, and report drafts should be checked against the protocol and source evidence before they become part of a formal review.

Where should implementation details live? Public docs describe reviewer-visible behavior. Internal engineering docs should cover architecture, safeguards, and operational mechanics.

Edge cases and limitations

Complex PDFs, sparse evidence networks, unusual measures, incompatible study designs, and ambiguous qualitative material still require methodological judgement. Use the validation guide before relying on outputs in a manuscript, regulatory package, HTA dossier, or guideline process.

Learn moreValidation & limitations

Quickstart

Getting Started

Key concepts

Getting Started