Skip to content
AI-powered meta-analysis

Publish faster. Stay audit-ready.

AI-assisted meta-analysis from question to manuscript. Axelium combines intelligent screening and extraction with reproducible statistics — so your team delivers rigorous reviews in days, not months.

10x
Faster than manual review
100%
Audit trail coverage
11
End-to-end workflow stages
Reproduced a peer-reviewed meta-analysis in 2 days →
www.axelium.aiLive
QuestionScreenExtractAnalyseNetworkReportUpdateValidate
Forest Plot — Primary OutcomeRE Model
Smith 2023
0.72 [0.58, 0.89]
Chen 2022
0.81 [0.64, 1.02]
Patel 2024
0.65 [0.51, 0.83]
Garcia 2023
0.78 [0.60, 1.01]
Overall
0.74 [0.63, 0.87]
How buyers scan it

Four modules first. Eleven stages when you need detail.

A review team does not need to parse every stage on first pass. Axelium reads as four connected modules, with the full audit-ready workflow underneath for evaluators and methods teams.

01

Find evidence

Build searches, import references, de-duplicate records, and keep the source trail visible from the start.

02

Screen and extract

Move from title/abstract decisions to full-text review and source-linked extraction without switching tools.

03

Analyze and grade

Run pairwise or network synthesis, inspect diagnostics, and connect certainty review to the underlying evidence.

04

Report and keep current

Export review artefacts, preserve sign-off, and turn completed reviews into living evidence workflows.

Detailed workflow

The full 11-stage pipeline. One living loop.

Eleven stages from research question to published manuscript, with sign-off gates at the milestones that matter and a living-review loop wrapped around the whole pipeline. Everything on one platform — no stitched-together exports, no copy-paste between tools.

END-TO-END PIPELINE · ONE PLATFORMLIVING LOOP
DISCOVERY
01
Protocol
02
Search
03
Screen
04
Full-text
SYNTHESIS
05
Extract
06
RoB 2.0
07
GRADE
ANALYSIS
08
Stats
09
NMA
10
Report
11
Living
SIGN-OFF GATELIVING-REVIEW LOOP
End-to-end platform

Every stage, integrated. Then kept current.

From research question to published manuscript to a living evidence base — every stage integrated, auditable, and designed for teams that demand rigour.

www.axelium.ai
01 · PROTOCOL CONFIGURATION

Chat with the AI to define your PICO or PEO framework. Axelium automatically generates and tests optimized PubMed and CT.gov query strings.

Seen enough? — free tier runs the full pipeline on one real review, end to end.

Audit trail · PRISMA 2020

Every search becomes a PRISMA flow.

The diagram updates itself as records move through the pipeline. Identification, screening, eligibility, included — with every exclusion category linked to the studies it removed. Export as Word, PDF, or a publication-ready figure with one click.

  • Counts trace to the underlying studies — every number in the diagram is a live link in the app.
  • Conforms to PRISMA 2020. Every reviewer decision is timestamped and reproducible.
  • Living reviews keep the diagram current — the version in your manuscript matches the one in the app.
PRISMA 2020 · FLOW OF INFORMATIONauto-generated · live
01
Identification
Records identified from databases
PubMed · ClinicalTrials.gov · EuropePMC · Cochrane CENTRAL
287
RECORDS
02
Screening
Records screened (title & abstract)
After de-duplication
287
RECORDS
03
Eligibility
Reports assessed for eligibility
Full-text retrieved and reviewed
41
RECORDS
04
Included
Studies included in synthesis
Trials contributing to the primary outcome pool
8
RECORDS
EXCLUDED WITH REASONS
−246Excluded at title & abstract screening
−33Excluded at full-text review

Each exclusion category traces to the studies it removed. Click any number in the live app to see the underlying list.

Publication bias · small-study effects

Detect publication bias at a glance.

A funnel plot puts every included study on a single chart — precision on the vertical axis, effect size on the horizontal. Asymmetry is the visual fingerprint of missing small negative trials. The plot is paired with Egger's and Begg's tests so a reviewer can quote both the picture and the number.

  • HTA submissions require a publication-bias appraisal whenever ten or more studies are pooled — the funnel plot is the expected first artefact.
  • Contour-enhanced and trim-and-fill variants are one click away, with the statistical tests and a plain-language interpretation alongside the figure.
  • Every plot is regenerated when new evidence arrives — the figure in your dossier matches the live evidence base on the day you submit.
Funnel plot · small-study effectsEgger's test · p = 0.04
Effect size (log scale)pooled 0.78
n = 15 studies · mild left-asymmetry
Network meta-analysis

Compare every intervention in one connected workflow.

Axelium connects review evidence to advanced synthesis: teams can prepare treatment networks, review assumptions, inspect network outputs, and keep certainty review tied to the extracted data that produced the model.

  • Prepare treatment nodes before interpreting a connected evidence network.
  • Inspect network graphs, league tables, rankings, and diagnostics in the same workspace as extraction.
  • Keep rankings separate from certainty, with reviewer checkpoints before conclusions move into a report.
Treatment network · primary outcomeranking ≠ certainty
64532AStandard careBTreatment ACTreatment BDCombination
Network graph
connected evidence
League table
relative effects
Certainty review
reviewer-owned
Standards we implement

Every reviewer-facing tool implements a published methodological standard. The references below are the ones our automation answers to — not in spirit, in code.

PRISMA 20202021

The PRISMA 2020 statement: an updated guideline for reporting systematic reviews

Page MJ, McKenzie JE, Bossuyt PM, et al.

BMJ 2021;372:n71

Cochrane Handbook2024

Cochrane Handbook for Systematic Reviews of Interventions

Higgins JPT, Thomas J, Chandler J, et al.

Version 6.5, Cochrane

RoB 2.02019

RoB 2: a revised tool for assessing risk of bias in randomised trials

Sterne JAC, Savović J, Page MJ, et al.

BMJ 2019;366:l4898

Risk of biasRead the reference
GRADE2008

GRADE: an emerging consensus on rating quality of evidence and strength of recommendations

Guyatt GH, Oxman AD, Vist GE, et al.

BMJ 2008;336:924

Plays well with your stack

Drops into your existing review workflow.

Bring your references in, send your manuscript out — Axelium connects to the databases, reference managers, and authoring tools you already use.

01 · REFERENCE MANAGERS

Import RIS or BibTeX from EndNote, Zotero, Mendeley, Embase, and Web of Science.

02 · COCHRANE HANDOFF

Export to RevMan 5 (.rm5) for risk-of-bias and final authoring.

03 · DATABASES

PubMed, ClinicalTrials.gov, EuropePMC, OpenAlex, CENTRAL, MAUDE, ERIC.

04 · CITATION GRAPH

Walk references, citers, and recommendations via Semantic Scholar.

05 · WORK ACCOUNTS

Sign in with Google or Microsoft — no extra password to manage.

FAQ

Common questions

A

Ready to streamline your systematic reviews?