Puraite
Start a PilotBook a live demo

AI Systematic Review SoftwareSystematic reviews in days, every decision auditable.

Explainable AI for the life sciences, making medical evidence available in real time.

Book a live demoWatch demo video
Projects/Title & Abstract ScreeningDashboardMy QueueAI ScreeningResults

Audit Trail12 Nov 2026, 14:32AI Screening SystemScreened as Include

included · 2,271 excluded · 8 unclear

Screening Details

Physiotherapy-led group programme for back pain in primary care

Demo Primary Care Journal · 2022 · DOI 10.0000/demo.2022.0932

AI AnalysisAI DecisionUnclearAI Confidence58%

Overall Summary

A physiotherapist-led group exercise programme compared with usual care in primary care. The abstract states neither how long participants had pain nor how they were allocated. Eligibility depends on the full text.

Key Evidence

  • “weekly physiotherapist-led exercise classes”
  • “patients were allocated to the programme or usual care”

AI Reasoning 5 Satisfied0 Violated3 Unclear

  • Adults with chronic non-specific low back pain Population

    The abstract gives no duration of pain.

  • Randomised controlled trial Study design

    Patients were allocated to groups, the method is not stated.

  • Acute or post-surgical back pain Population

    Acute cases are not ruled out.

  • Supervised exercise therapy Intervention

    Group exercise sessions are led by physiotherapists.

  • Usual care, no treatment or another active treatment Comparator

    The comparison is usual care.

  • Pain intensity or disability reported Outcome

    Pain and disability are reported at six months.

  • Participants under 18 years Population

    All participants are adults.

  • Protocol or conference abstract without results Publication type

    Results are reported in full.

Audit TrailAI Screening SystemScreened as Unclear12 Nov 2026, 14:33

Title and abstract screening, results · demo data

<1 month

Draft systematic review with Puraite

16 months

Industry standard

The AI steps of a review run in days. With your reviewers checking the decisions, a full draft is ready in under a month. The industry standard is 16 months.

Supported by Europe's leading AI and life science organisations

eXISTRWTH InnovationHigh Tech NRW AcceleratorFounders FoundationGerman Acceleratorgarage33QuhrPaderborn Universitylife science factoryUniversity Hospital CologneGHA - German Health Alliance

Why Puraite

What sets Puraite apart from generic AI tools and older review platforms.

Every decision shows its reasons.

Each AI screening decision states which criteria it judged met, unmet or unclear. It quotes the passage behind a judgement where the text has one and gives the AI's own confidence from 0 to 100%.

Projects/Full-Text ScreeningManual ScreeningBatchExport

PDF Viewer

Methods

We conducted a systematic search of MEDLINE, Embase and Cochrane Central. Eligible trials enrolled adults (≥18 years) with moderate-to-severe rheumatoid arthritis (DAS28 ≥3.2) who received any approved IL-6 receptor inhibitor. Primary endpoint was ACR20 response at week 12.

AI citation: Population criterion

Eligibility Criteria

  • Adult RA patients (DAS28 ≥3.2)
  • IL-6 receptor inhibitor arm
  • RCT or controlled trial design
  • Min. 12-week follow-up
  • ACR20 primary endpoint

AI Recommendation: Include

Full-text screening with the highlighted source passages · demo data

Records a dossier team can check.

The PRISMA 2020 flow diagram fills itself from your screening decisions. Your assessors rate risk of bias with an AI pre-fill they accept or change and rate GRADE certainty outcome by outcome. Every judgement is in the audit log.

Projects/PRISMA Flow DiagramPRISMA 2020
PRISMA 2020 (default)AI transparency (PRISMA-trAIce)SVGPNGExcelPowerPointWord
IdentificationScreeningIncluded

Records from databases:

  • PubMed (n = 812)
  • Embase (n = 1,046)
  • Cochrane CENTRAL (n = 398)
  • Total (n = 2,256)

Records identified from:

  • Websites (n = 0)
  • Organisations (n = 0)
  • Citation searching (n = 0)

Records removed before screening:

  • Duplicate records removed (n = 684)
  • Records marked as ineligible by automation tools (n = 0)
  • Records removed for other reasons (n = 0)

Records screened

(n = 1,572)

AI-screened
1,572 (100%)
Human-screened
1,572 (100%)

Records excluded

(n = 1,498)

By AI
1,498
By human
1,492
AI agreement
97%

Reports sought for retrieval

(n = 74)

Reports not retrieved

(n = 3)

Reports assessed for eligibility

(n = 71)

AI-assessed
71
Human-assessed
71

Reports excluded

  • Wrong population (n = 18)
  • Wrong intervention (n = 14)
  • Wrong comparator (n = 9)
  • Wrong outcome (n = 11)
  • Wrong study design (n = 13)
  • Total (n = 65)
AI-excluded
62
Human-excluded
65

Studies included in review

(n = 6)

  • Quantitative synthesis (n = 6)
  • Qualitative synthesis (n = 0)
PRISMA 2020 flow diagram with the share of AI and human screening · demo data

A person has the last word.

A person settles every conflict and can override any AI decision. Every override is in the audit log.

Title & Abstract Screening/Audit TrailRead-only

Supervised exercise versus usual care in chronic low back pain: a randomised trial

  1. AI Screening SystemIncluded, confidence 94%Decision with rationale and source quotes stored
  2. R. Okafor · Reviewer 1IncludedAdopted the AI decision after reading the abstract
  3. L. Brandt · Reviewer 2ExcludedReason given: comparator is another exercise programme
  4. SystemConflict openedTwo human decisions differ, record leaves the queue
  5. M. Sato · Project ManagerConflict resolved: IncludedComparator criterion I3 allows another active treatment
  6. SystemSent to full-text retrievalPRISMA count updated
Audit trail of one record · demo data

From protocol to report or one step of it.

Run the review from protocol to PRISMA report in one audited workspace. Studies screened in another tool can start at data extraction.

Demo organisation/Projects

Start your evidence project

Recommended

Guided Review

Step by step through a complete, audit-ready review.

Best for most reviews

or start another way

Data extraction onlyStandalone statistical analysis

Studies already chosen? Start at data extraction and skip search and screening.

Start screen of a new evidence project · demo data

No Training on Your Content

We do not use your content to train or fine-tune AI models. Our AI providers keep inputs for limited periods set out in our data processing agreement. You can export or delete your data; section 14 of the Terms of Use sets the steps and periods.

Security and data handling

From Protocol to Evidence in Six Phases

The complete systematic review workflow, powered by explainable AI.

Planning & Protocol

Answer a guided questionnaire or let the AI draft the protocol from your research question.

  1. Define Research Question (PICO)
  2. Conduct Scoping Search
  3. Draft the Protocol
  4. Register Protocol (optional)
Projects/ProtocolProtocolCriteria BoardSearchScreeningExtraction

Research Protocol

A systematic review to evaluate the efficacy of IL-6 inhibitors in patients with moderate-to-severe rheumatoid arthritis, comparing treatment outcomes versus placebo or standard of care.

Extract Criteria

Criteria Board

P
Population
Adults with moderate-to-severe RA
I
Intervention
IL-6 receptor inhibitors
C
Comparison
Placebo or standard of care
O
Outcome
ACR20 response at week 12
Protocol and criteria board · demo data

Search & Management

Search the open databases from inside the project and import everything else by file.

  1. Develop Search Strategy
  2. Execute Database Searches
  3. Search Grey Literature
  4. Deduplicate Records
Projects/Search & ImportFile ImportDatabase SearchDeduplication

SourcePubMed

Drop your .ris or .nbib file hereor click to browse
TitleSourceYearStatus
Efficacy of IL-6 inhibitors in RA...PubMed2024Imported
A randomized controlled trial...PubMed2023Imported
Meta-analysis of biologic therapy...PubMed2022Imported
Search and record import · demo data

Study Selection

Screen manually, with the AI as second reviewer or AI-first. Resolve conflicts in place.

  1. Title/Abstract Screening
  2. Resolve TIAB Conflicts
  3. Full-Text Retrieval
  4. Full-Text Screening
  5. Resolve Full-Text Conflicts
Projects/Title & Abstract ScreeningManualBatch AISettings
18 / 40 reviewed86% AI confidence

Efficacy of IL-6 receptor inhibitors in rheumatoid arthritis: a systematic review and network meta-analysis

Demo Journal of Rheumatology · 2024 · 1,847 participants

AI Rationale

Population matches adult RA patients (P criterion met). Intervention aligns with IL-6 inhibitor protocol (I criterion met). Primary outcomes reported at week 12 (O criterion met).

ExcludeInclude
Title and abstract screening, one record at a time · demo data

Extraction & Quality

Dual extraction and risk of bias with the tool that fits the study design.

  1. Design Extraction Form
  2. Extract Data (Dual)
  3. Risk of Bias Assessment
  4. Resolve Conflicts
  5. Contact Authors
Projects/Data ExtractionPanel ViewTable ViewExport

Source Document

...enrolled 342 patients across 14 sites. ACR20 response was achieved in 68.4% of patients in the treatment arm vs 28.1% in the placebo arm (p<0.001). Mean DAS28 reduction of 2.1 points

3 fields linked to this passage

Extraction Form

Sample size
342 patients
ACR20 (treatment)
68.4%
ACR20 (placebo)
28.1%
p-value
< 0.001
DAS28 reduction
2.1 points
Data extraction linked to its source passage · demo data

Synthesis & Grading

Meta-analysis with forest plots, GRADE and Summary of Findings tables.

  1. Meta-Analysis
  2. Qualitative Synthesis
  3. GRADE Assessment
  4. Summary of Findings Tables
Projects/GRADE AssessmentEvidence ProfileSummary of Findings
  • High
  • Moderate
  • Low
  • Very low
HTMLExport

Summary of Findings4/7

OutcomeStudiesParticipantsEffect Estimate (CI)CertaintyRisk with comparatorAbsolute effectPlain Language Summary
ACR20 response at week 1252,068RR 2.32 (95% CI 1.94 to 2.77)Moderate281 per 1,000371 more per 1,000 (from 264 more to 497 more)The intervention probably increases ACR20 response at week 12.
DAS28 remission at week 2441,656RR 5.02 (95% CI 3.41 to 7.39)Moderate54 per 1,000217 more per 1,000 (from 130 more to 345 more)The intervention probably increases DAS28 remission at week 24.
Serious adverse events62,678RR 1.23 (95% CI 0.89 to 1.70)Low52 per 1,00012 more per 1,000 (from 6 fewer to 36 more)The intervention may result in little to no difference in serious adverse events.
Withdrawal due to adverse events62,678RR 1.58 (95% CI 1.04 to 2.40)Moderate31 per 1,00018 more per 1,000 (from 1 more to 43 more)The intervention probably increases withdrawal due to adverse events.
GRADE summary of findings · demo data

Reporting & Maintenance

PRISMA manuscript draft, flow diagram and checklist.

  1. PRISMA Manuscript Draft
  2. PRISMA Flow Diagram
  3. PRISMA Checklist
  4. Living Review Dashboard
Projects/PRISMA Flow DiagramPRISMA 2020
PRISMA 2020 (default)AI transparency (PRISMA-trAIce)SVGPNGExcelPowerPointWord
IdentificationScreeningIncluded

Records from databases:

  • PubMed (n = 812)
  • Embase (n = 1,046)
  • Cochrane CENTRAL (n = 398)
  • Total (n = 2,256)

Records identified from:

  • Websites (n = 0)
  • Organisations (n = 0)
  • Citation searching (n = 0)

Records removed before screening:

  • Duplicate records removed (n = 684)
  • Records marked as ineligible by automation tools (n = 0)
  • Records removed for other reasons (n = 0)

Records screened

(n = 1,572)

AI-screened
1,572 (100%)
Human-screened
1,572 (100%)

Records excluded

(n = 1,498)

By AI
1,498
By human
1,492
AI agreement
97%

Reports sought for retrieval

(n = 74)

Reports not retrieved

(n = 3)

Reports assessed for eligibility

(n = 71)

AI-assessed
71
Human-assessed
71

Reports excluded

  • Wrong population (n = 18)
  • Wrong intervention (n = 14)
  • Wrong comparator (n = 9)
  • Wrong outcome (n = 11)
  • Wrong study design (n = 13)
  • Total (n = 65)
AI-excluded
62
Human-excluded
65

Studies included in review

(n = 6)

  • Quantitative synthesis (n = 6)
  • Qualitative synthesis (n = 0)
PRISMA 2020 flow diagram with the share of AI and human screening · demo data

See the whole product

Choose the AI's role for each phase

From switched off to screening alone.

The AI cannot run on this phase. Your reviewers screen and resolve conflicts.

The AI screens alongside your team for comparison. Its verdict never raises a conflict or changes an outcome.

The AI re-checks what your reviewers excluded. An AI include counts only on a record no reviewer included. An AI exclude never counts.

The AI holds one reviewer seat next to your reviewers. Its vote counts exactly like a human reviewer's.

The AI decides every record and no human votes. A Project Manager or an Information Manager can override any AI decision.

Project Settings/Screening setupTitle/abstract
Reviewers per record2 human reviewers2 human reviewers + AI shadow (informative only)2 human reviewers + AI check of excludes1 human reviewer + 1 AI reviewerAI only · no human reviewers
RecordHuman 1Human 2AI · not countedAI ConfidenceResult
Supervised exercise versus usual care in chronic low back pain: a randomised trialIncludeIncludeInclude94%Included
Lumbar fusion outcomes after ten years: a registry analysisExcludeExcludeExclude97%Excluded
Physiotherapy-led group programme for back pain in primary careIncludeExcludeUnclear58%ConflictIncludedUnclear · advances
Yoga versus stretching for adults with persistent back painExcludeExcludeInclude91%ExcludedConflictIncluded
Core stability training in adolescent athletes with acute strainExcludeExcludeExclude88%Excluded
What the AI's role does to each record in title and abstract screening · demo data

Built For Review Teams

Roles, assignments and an audit trail for every decision.

Project Manager
Configures the protocol, assigns reviewers, follows progress.
Information Manager
Manages publications, the extraction form and the AI runs.
Collaborator
Screens, extracts, comments and resolves conflicts where assigned.
Viewer
Reads the project without changing decisions.

Who Puraite Is Made For

Regulated industries where the speed, auditability, and reproducibility of evidence synthesis directly determine commercial and regulatory outcomes.

Pharmaceuticals

Regulatory AffairsMarket Access & HEOR

Medical Devices

Regulatory AffairsClinical & Market Access

CRO & Market Access Consultancies

Evidence Synthesis TeamsClinical Operations

Insurance & Payers

Coverage DecisionsHealth Economics

Chemistry

Regulatory SafetyProduct Compliance

Food & Nutrition

Regulatory SafetyProduct Compliance

Cosmetics

Safety AssessmentClaims & Dossiers

Academic Network

Research groups working with Puraite

Universities and public research institutes run their systematic reviews on Puraite. Academic access is free, with no time limit. Run as many reviews as you need. No plan limits the number of reviews.

  • All India Institute of Speech and Hearing, MysuruIndia
  • Harvard UniversityUnited States
  • National Research and Innovation Agency (BRIN)Indonesia
  • Universidad de AntioquiaColombia
  • Università degli Studi della Campania Luigi VanvitelliItaly
  • University of AberdeenUnited Kingdom
  • University of OxfordUnited Kingdom
  • Wayne State UniversityUnited States

See the Academic Network

Puraite's end-to-end systematic review platform has allowed us to maintain a high level of research momentum without compromising human control. It has streamlined our evidence synthesis workflow, allowing our team to process and manage over 10,000 records in an auditable, highly efficient workspace.

Researchers at over 150 institutions in over 40 countries

Puraite is built in Bielefeld and Paderborn, Germany. Research teams on every inhabited continent use it.

BielefeldHeadquartersPaderbornPaderborn University
Countries where researchers use Puraite · as of November 2026

What your reviews cost in researcher time

Set your own numbers. The starting values come from a published cost study.

Your reviews
5
5
11
Assumptions
15 h
EUR 40
70%

Researcher time saved per year

EUR 500,480

12,512 researcher hours

Researcher hours per year

Today
17,875 h
With Puraite
5,363 h

The starting values follow Michelson and Reuter (Contemporary Clinical Trials Communications, 2019): five co-authors working 15 hours a week for 11 months, about USD 141,000 of researcher time per review. The share of time the AI takes over is your assumption. The Puraite licence is not included.

Engineering Rigor

How we build, validate and deploy AI for regulated evidence synthesis.

Methodology and explainability

How we test screening

We test the AI screening against the decisions of published Cochrane reviews. Joint evaluations with independent academic research groups are under way. We link the publications when they appear. A hall of fame of the papers conducted on Puraite is coming!

Selecting the right model for each task

We benchmark leading foundation models at every pipeline stage: retrieval, screening, extraction and synthesis. A model that excels at eligibility classification may underperform at data extraction. Each step runs on the model that does it best at the lowest cost and energy use.

Works with the tools your team already uses

Search eight sources from inside the project. Licensed databases come in by file. Your results leave in the formats your team works with.

Searched inside Puraite

  • PubMed (MEDLINE)
  • OpenAlex
  • Semantic Scholar
  • Europe PMCwith medRxiv and bioRxiv
  • ClinicalTrials.gov
  • DOAJ
  • FDA FAERS
  • FDA MAUDE

By fileSearch string written for you

  • Embase
  • Cochrane CENTRAL
  • CINAHL
  • PsycInfo
  • EconLit

From your reference managerRIS, NBIB, BibTeX

  • EndNote
  • Zotero
  • Mendeley

Your results leave as

  • WordManuscript draft, PRISMA checklist
  • ExcelExtraction tables
  • R scriptThe R code that reproduces each analysis
  • PowerPoint, SVG and PNGPRISMA flow diagram
  • RIS, BibTeX, EndNote XML and CSL-JSONReferences back to your reference manager

Move in mid-review.

Bring your records, your protocol and your full texts in bulk and continue where you stopped. Studies you screened elsewhere start at data extraction and count as screened externally in the PRISMA flow.

End to end or one step.

Run the whole review in one workspace. Or use one step on its own, such as data extraction for studies screened elsewhere or the statistical analysis.

Frequently Asked Questions

Not sure where to start?

Answer a few short questions about your next review. You get a setup for your team and can request a pilot on the same page.

What is Puraite?

Puraite is the operating system for evidence synthesis in the life sciences. We help teams run systematic literature reviews and other review types faster, with the reasoning behind every AI decision on record.

What is a systematic literature review?

A systematic literature review (SLR) is a structured research methodology for identifying, appraising and synthesizing all relevant evidence on a specific research question. It follows predefined protocols to minimize bias and ensure comprehensiveness.

Who is Puraite for?

Puraite serves pharmaceutical companies, contract research organizations (CROs), health technology assessment (HTA) bodies, academic researchers and anyone conducting evidence synthesis in regulated environments.

What makes Puraite different?

Puraite's AI is built to support dual screening, not to replace it. Every AI decision shows its reasoning and can be overridden by a reviewer. The platform is PRISMA compliant and covers the review from protocol to report in one auditable workspace.

Is Puraite scientifically validated?

We evaluate Puraite's AI screening against the decisions of published Cochrane reviews. Joint evaluations with academic research groups are under way; we will link the publications when they appear.

How does human-AI collaboration work?

AI augments human reviewers by automating screening, extraction and synthesis tasks. Every AI decision is reviewable and overridable. Human experts maintain full control with approve, override, comment and second review capabilities.

What review types are supported?

Systematic reviews, scoping reviews, rapid reviews, living reviews, umbrella reviews, targeted reviews and meta-analyses. The platform adapts its workflow to each review type's specific methodology requirements.

How secure is your data?

Research data and uploaded files are stored in the EU, in Paris. Connections are encrypted with TLS and uploaded files are encrypted at rest. Project roles and organisation permissions control access. Audit trail entries cannot be edited. We test the platform's security internally on a regular basis. Our hosting provider is certified to ISO/IEC 27001. ISO 27001 and SOC 2 certification for Puraite are on our roadmap.

What export formats are available?

References as RIS, BibTeX, CSV, CSL-JSON and EndNote XML. The manuscript draft as Word or PDF, extraction tables as Excel or CSV and the PRISMA flow diagram as SVG, PNG, Word, PowerPoint or Excel. The audit log exports as CSV or JSON.

How long does it take to complete a review with Puraite?

Depending on the scope and complexity, Puraite can reduce a typical 6-24 month systematic review to days or weeks. The exact timeline depends on the number of records, review type and level of human oversight required.

What databases does Puraite search?

Puraite searches PubMed (MEDLINE), OpenAlex, Semantic Scholar, Europe PMC including medRxiv and bioRxiv, ClinicalTrials.gov, DOAJ, FDA FAERS and FDA MAUDE from inside your project. For databases that need their own licence, such as Embase, Cochrane CENTRAL, CINAHL and PsycInfo, Puraite writes the search string in the database's syntax and you import the result file. Direct connections to further databases are planned.

Can multiple reviewers collaborate on the same project?

Yes. Puraite supports multi-reviewer projects with PM/reviewer roles, task assignment, conflict resolution, audit trails and real-time collaboration features. Advanced workspace analytics and richer consensus tooling are on the roadmap.

How does Puraite handle full-text PDF retrieval?

Puraite retrieves full texts from open-access sources such as Unpaywall, PubMed Central and Europe PMC. Articles it cannot find there are uploaded by your team, one file at a time or in bulk.

Is training required to use Puraite?

Puraite is designed to be intuitive for researchers familiar with systematic review methodology. We provide onboarding sessions, video tutorials and dedicated customer success support for all enterprise accounts.

Can Puraite handle non-English language publications?

The vast majority of biomedical evidence is published in English, which Puraite handles natively. Multi-language screening and extraction capabilities for major European and Asian languages are on our development roadmap and will be available in a future release.

Ready to Accelerate Your Evidence Workflow?

Book a live demo
Funded by the German Federal Ministry for Economic Affairs and Energy and the European Union through the European Social Fund Plus (ESF Plus). Implemented by Projektträger Jülich as part of the EXIST programme.