Currently submitted to: Journal of Medical Internet Research
Date Submitted: Jun 10, 2026
Open Peer Review Period: Jun 11, 2026 - Aug 6, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited.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.
Characterizing Patient Portal Usage and Implications: A Data-driven Analysis on a Rural Population
ABSTRACT
Background:
Patient portals have become a primary channel for asynchronous patient–provider communication, yet rural-specific communication patterns remain underexplored.
Objective:
This study characterizes portal communication patterns in a rural-serving academic medical center over 5 years and links messaging behaviors to markers of care burden.
Methods:
We analyzed 370,498 patient messages and 256,295 provider responses from 10,206 patients at Dartmouth Hitchcock Medical Center (2020-2024). We also analyze the linked structured electronic health record (EHR) data for each patient. We used validated large language model (LLM)–based classifiers for thematic analysis and message authorship identification at scale.
Results:
Female patients and older adults generated disproportionately high message volumes. Anxiety (47.0%), hypertension (36.1%), and lipid disorders (33.7%) were the most prevalent conditions. Information seeking dominated portal communication (33.4%). The median response time to a patient messages was 10.6 hours, with patients who had dementia or cerebrovascular conditions waiting for the longest. Care partner-authored messages were substantially elevated among patients with Alzheimer disease and dementia (approximately 55%-60%) vs 5% for those without.
Conclusions:
Rural portal communication reflects systematic disparities linked to age, sex, and clinical complexity. LLM-based analysis enables scalable characterization of thematic patterns and clarity failures that may inform AI-assisted triage.
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.