Kahubi for medicine

From clinical question to submitted manuscript, with the process documented

Medical publishing has the strictest process requirements in research: registered questions, PRISMA flows, reporting checklists, Vancouver references, and data handling an ethics committee will interrogate. Kahubi is built around exactly that discipline — and takes the mechanical work out of it.

Free plan included. No credit card required.

Where Kahubi fits your work

Systematic review

The review pipeline, end to end

Question, search strategy, dual-pass screening against your criteria with AI-suggested calls you confirm, and a written synthesis following PRISMA or Cochrane conventions — with the audit trail intact.

Library chat

Interrogate the trial literature

Ask what endpoints the trials in your library used, where effect estimates conflict, or which populations were excluded — answers cite the papers so claims can be checked.

Statistics

Analysis with the write-up attached

Group comparisons, correlations, regression and more on your data, reported with effect sizes and confidence intervals in journal-ready form.

Writing voice

Vancouver by default, your register

References render in Vancouver (or APA and four others) from a managed library, and drafts follow a style profile learned from your own publications.

Transcription

Qualitative health research, compliant

Patient and clinician interviews transcribed on an EU endpoint with speaker labels, coded against COREQ-friendly documentation.

Monitor

Your specialty, monitored

Follow journals, authors, and topics; get a digest when new trials and reviews land — before the journal club does.

AI chat

Chat with your library, not a generic chatbot

Kahubi answers from the papers, drafts, datasets, and transcripts you actually have. Type @ to pull any source into the conversation; the agent reads it, searches your library, and cites what it used.

  • @-mention papers, drafts, datasets, interviews, and files
  • Select text in any PDF to explain, summarize, or translate it
  • Agent searches OpenAlex and the web, and imports papers for you
Kahubi's AI chat answering from the user's library, with a tool chip and cited references
Writing

Write accurate manuscripts, grounded in your sources

Draft in a clean editor and let the AI help — it writes in your voice, learned from your own publications, and every paragraph stays anchored to the papers, data, and notes you actually have, never invented. Read it as a formatted PDF, edit it like a Word document, or drop into LaTeX when you want fine control.

  • Writes in your voice: a style profile learned from your published work, not a generic chatbot register
  • Grounded in your library: the AI writes from your real papers and data, and cites what it used
  • One click to a compiled PDF, plus Word (.docx) export and full version history
A manuscript compiled to a typeset PDF in Kahubi

What changes

  • PRISMA 2020-aligned screening logs and flow-diagram numbers generated from the actual process
  • Reporting standards at hand: CONSORT, STROBE, PRISMA, COREQ
  • Vancouver/ICMJE-style referencing with abbreviation-friendly BibTeX export
  • EU audio processing and documented subprocessors — answers for the ethics committee
  • No training on your content, ever

Common questions

Can Kahubi run a full systematic review for a medical journal?
It runs the pipeline with you in control: search strategy generation, screening with documented include/exclude decisions, and a drafted synthesis following PRISMA or Cochrane conventions. Registration (PROSPERO), dual independent screening, and clinical judgment remain yours — the tool documents them rather than replacing them.
Does it search MEDLINE/PubMed?
Kahubi searches OpenAlex (250M+ works, which indexes the PubMed corpus among others) enriched with Semantic Scholar. For a formal review you should still run and document venue-required databases per your protocol - Kahubi generates the search strategy you can port.
How does Kahubi handle sensitive health data?
Content is not used for model training, transcription runs on an EU endpoint, subprocessors are documented publicly, and deletion is available on request. De-identification per your protocol remains the researcher’s responsibility before upload.

Reviews and manuscripts with the audit trail built in

PRISMA, Vancouver, EU data handling — and the mechanical work compressed. Free to start.

Kahubi for other roles