JournalsAll issuesFor AuthorsAbout usPublisher: Malikian Evidence Review
First Contact
Open Journal of Clinical AI and Primary Care Evidence Synthesis
ISSN: pending · Monthly · Open Access · Volume 1, 2026 · Palmdale, California, USA
Latest issue
First Contact
Open Journal of Clinical AI and Primary Care Evidence Synthesis
Volume 1, Issue 2
November 2026
  • LLM clinical summaries: errors per summary
  • Unsafe advice from patient-facing chatbots
  • High-dose vitamin C in cancer
  • Loss of taste in viral infection
  • Synthetic patients and Synthea
  • Multi-agent peer review — methods
7 articles · pp. 78–438 · Browse this issue

Latest articles

  1. Review · Systematic Review & Meta-analysisClinically Significant Errors in Large Language Model-Generated Clinical Summaries: A Systematic Review and Meta-analysis of Omissions, Inaccuracies and Fabrications per Summary

    Raphael Malikian

    First Contact 2026;1(2):78–117 · November 2026

    How often do LLM-generated clinical summaries omit, distort or fabricate — counted per summary, across the published evaluation literature.

  2. Review · Systematic Review & Meta-analysisUnsafe or potentially unsafe advice from patient-facing large language model chatbots in bench evaluations of primary-care question sets: a systematic review and meta-analysis

    Raphael Malikian

    First Contact 2026;1(2):118–147 · November 2026

    A pooled look at bench evaluations of patient-facing chatbots answering primary-care questions — and how often the advice was judged unsafe.

  3. Review · Systematic Review & Meta-analysisHigh-dose vitamin C in people with cancer: a Cochrane-level systematic review and meta-analysis of oral and intravenous ascorbate for treatment outcomes, quality of life and harms

    Raphael Malikian

    First Contact 2026;1(2):148–166 · November 2026 · DOI: 10.5281/zenodo.24213997

    Decades of claims for high-dose ascorbate in cancer, tested against the trial evidence for outcomes, quality of life and harms.

  4. Research · Retrospective AnalysisSynthetic Patients and What They Can and Cannot Teach: A Retrospective Analysis of Open-Source Contributions to Synthea

    Raphael Malikian

    First Contact 2026;1(2):266–281 · November 2026 · DOI: 10.5281/zenodo.23964017

    What building for the Synthea synthetic-patient ecosystem shows about what synthetic data can — and cannot — teach clinical AI.

  5. Review · Systematic Review & Meta-analysisAmbient artificial intelligence scribes for clinical documentation: effects on documentation time, after-hours work, clinician burnout, note quality and note errors — A systematic review and meta-analysis

    Raphael Malikian

    First Contact 2026;1(1):1–43 · October 2026 · DOI: 10.5281/zenodo.23565499

    Do ambient AI scribes actually save time and reduce burnout — and what do they do to the quality and accuracy of the note?

  6. Review · Systematic Review & Meta-analysisFabricated and inaccurate citations generated by large language models for biomedical topics: a systematic review and meta-analysis

    Raphael Malikian

    First Contact 2026;1(1):44–77 · October 2026 · DOI: 10.5281/zenodo.23585717

    How often do LLMs invent or corrupt the biomedical references they cite — a meta-analysis of the verification studies.

  7. Research · Retrospective AnalysisWhen Agent Plumbing Fails Quietly: A Retrospective Analysis of Open-Source Contributions to LLM Tooling and Agent Infrastructure

    Raphael Malikian

    First Contact 2026;1(1):253–265 · October 2026 · DOI: 10.5281/zenodo.23741622

    The failures that don't crash — silent defects in LLM tooling and agent infrastructure, found by contributing to the code itself.

  8. CommentEighty-Three Percent Growth, Thirty-Eight Papers: Direct Primary Care and the Outcomes Accounting It Owes

    Raphael Malikian

    First Contact 2026;1(1) · October 2026 · DOI: 10.5281/zenodo.23562906

    Direct primary care is growing fast; its published outcomes evidence is not keeping pace. A commentary on the accounting owed.

See the full current issue → · Browse the archive →

Current Issue — Volume 1, Issue 2, November 2026

  1. Chapter 1 · Systematic Review & Meta-analysisClinically Significant Errors in Large Language Model-Generated Clinical Summaries: A Systematic Review and Meta-analysis of Omissions, Inaccuracies and Fabrications per SummaryRaphael Malikian · First Contact. 2026;1(2):78–117 · Read article · GitHub
  2. Chapter 2 · Systematic Review & Meta-analysisUnsafe or potentially unsafe advice from patient-facing large language model chatbots in bench evaluations of primary-care question sets: a systematic review and meta-analysisRaphael Malikian · First Contact. 2026;1(2):118–147 · Read article · GitHub
  3. Chapter 3 · Systematic Review & Meta-analysisHigh-dose vitamin C in people with cancer: a Cochrane-level systematic review and meta-analysis of oral and intravenous ascorbate for treatment outcomes, quality of life and harmsRaphael Malikian · First Contact. 2026;1(2):148–166 · Read article · GitHub
  4. Chapter 4 · Systematic Review & Meta-analysisLoss of taste in possible viral infection: etiologies, pathogenesis, and the evidence for treatmentsRaphael Malikian · First Contact. 2026;1(2):326–438 · Read article · GitHub
  5. Chapter 5 · Retrospective AnalysisSynthetic Patients and What They Can and Cannot Teach: A Retrospective Analysis of Open-Source Contributions to SyntheaRaphael Malikian · First Contact. 2026;1(2):266–281 · Read article · GitHub
  6. Chapter 6 · Methods PaperMulti-Agent Peer Review System for Clinical AI, Medical Research and Health Technology Papers: persona-based AI reviewers and looped editorial gates before preprint submissionRaphael Malikian · First Contact. 2026;1(2):318–325 · Read article · GitHub
  7. Chapter 7 · Methods PaperMulti-Agent Cochrane-Level Review Process (Robust Standard v2)Raphael Malikian · First Contact. 2026;1(2):312–317 · Read article · GitHub

Archive — Volume 1, Issue 1, October 2026

  1. Chapter 1 · Retrospective AnalysisGuarding the Clinical Narrative: A Practitioner-Contributor's Retrospective Analysis of Open-Source Contributions to Clinical Natural Language Processing and Health-Data De-identification (2025-2026)Raphael Malikian · First Contact. 2026;1(1):167–187 · Read article · GitHub
  2. Chapter 2 · Retrospective AnalysisSilent Failures in the Imaging Stack: A Retrospective Analysis of Open-Source Contributions to Medical Imaging Software: DICOM Geometry, Warnings Discipline, and Pipeline Reliability (2025-2026)Raphael Malikian · First Contact. 2026;1(1):188–206 · Read article · GitHub
  3. Chapter 3 · Retrospective AnalysisRetrieval Is the New Record System: A Retrospective Analysis of Open-Source Contributions to Vector Databases and Embedding Infrastructure Underpinning Clinical AI (2025-2026)Raphael Malikian · First Contact. 2026;1(1):207–229 · Read article · GitHub
  4. Chapter 4 · Retrospective AnalysisThe Plumbing Layer: A Retrospective Analysis of Open-Source Contributions to FHIR Servers, Synthetic Patient Data, and Federated Research Infrastructure (2025-2026)Raphael Malikian · First Contact. 2026;1(1):230–252 · Read article · GitHub
  5. Chapter 5 · Retrospective AnalysisWhen Agent Plumbing Fails Quietly: A Retrospective Analysis of Open-Source Contributions to LLM Tooling and Agent InfrastructureRaphael Malikian · First Contact. 2026;1(1):253–265 · Read article · GitHub
  6. Chapter 6 · CommentaryEighty-Three Percent Growth, Thirty-Eight Papers: Direct Primary Care and the Outcomes Accounting It OwesRaphael Malikian · First Contact. 2026;1(1):282–293 · Read article · GitHub
  7. Chapter 7 · CommentaryWhen a Warning Advertises: The Boomerang Effect in Anti-Drug Campaigns and the Case of Concentrated 7-HydroxymitragynineRaphael Malikian · First Contact. 2026;1(1):294–311 · Read article · GitHub
  8. Chapter 8 · Systematic Review & Meta-analysisAmbient artificial intelligence scribes for clinical documentation: effects on documentation time, after-hours work, clinician burnout, note quality and note errors — A systematic review and meta-analysisRaphael Malikian · First Contact. 2026;1(1):1–43 · Read article · GitHub
  9. Chapter 9 · Systematic Review & Meta-analysisFabricated and inaccurate citations generated by large language models for biomedical topics: a systematic review and meta-analysisRaphael Malikian · First Contact. 2026;1(1):44–77 · Read article · GitHub

All issues — Volume 1 (2026)

Volume 1 · Issue 2
November 2026 — Current Issue

7 articles: three systematic reviews, the viral taste-loss review, Synthea retrospective, and two methods papers. pp. 78–438.

View issue contents →

Volume 1 · Issue 1
October 2026

9 articles: five retrospective analyses of open-source clinical AI infrastructure, two commentaries, and two systematic reviews. pp. 1–311.

View issue contents →

About / Aims & Scope

First Contact is a monthly, open-access journal publishing evidence synthesis and methods work at the intersection of clinical artificial intelligence, family medicine and primary care. It publishes Cochrane-level systematic reviews and meta-analyses, retrospective analyses of open-source contributions to clinical AI infrastructure, commentaries on primary care evidence and policy, and methods papers on how this research is produced and reviewed.

Every article is published in the open: the full text, data and analysis code are public in the article's GitHub repository, and each article carries a Zenodo DOI. New issues appear monthly; Volume 1 began in October 2026.

Article types

Editorial and peer review

Editor: Raphael Malikian. Before publication, every manuscript undergoes a structured multi-agent pre-submission peer review — a panel of persona-based reviewers, including a dedicated skeptic, working through fix-and-re-review loops until no blocker or major issue remains open — under the editor's sole accountability as author and editor. Review reports are published with the article's repository. This is pre-submission review conducted in the open; it is described honestly as such, and no article claims external journal peer review it has not had.

Citing articles in this journal

Malikian R. [Article title]. First Contact. 2026;1(1 or 2):[pages]. DOI: [the article's Zenodo DOI, as given on its landing page].

For Authors

First Contact currently publishes the editor's own programme of systematic reviews, retrospective analyses, commentaries and methods papers in clinical AI, family medicine and primary care. Every article is open access, carries a Zenodo DOI, and is published with its full text, data and code in a public GitHub repository. Manuscripts pass the journal's multi-agent pre-submission peer review — a reviewer panel with a dedicated skeptic, in looped editorial gates — before they appear. Enquiries: rtmalikian@gmail.com.