Previously submitted to: Journal of Medical Internet Research (no longer under consideration since Jun 11, 2026)
Date Submitted: Apr 1, 2026
Open Peer Review Period: Apr 1, 2026 - May 27, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Externalized Living Memory: Structuring Clinical Knowledge for the Age of AI Agents
ABSTRACT
As AI agents become increasingly capable of autonomous action in health care, a prerequisite remains underaddressed: the persistent, structured memory that makes such action contextually meaningful. Clinicians face cognitive overload not from any single task but from the erosion of decision context over time. Existing tools—personal knowledge management frameworks, LLM built-in memory, and autonomous agents—each address parts of this problem but leave gaps in auditability, portability, or contextual persistence. This Viewpoint argues that memory should precede action: before AI agents can act meaningfully, they need persistent, human-controlled context. We describe externalized living memory—a structured knowledge base that both human and AI can read and write—as it emerged from the first author's practice as a cardiovascular radiologist and division chief. The approach is organized as a layered architecture with a routing table for scalable context loading and a governance hierarchy for sustainable maintenance. We illustrate the approach through clinical vignettes, compare it with existing solutions, and discuss limitations including the small-team evidence base and maintenance costs. An open-source implementation with templates and setup instructions accompanies this paper.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.