BRIEF RESEARCH REPORT article
Front. Digit. Health
Sec. Health Technology Implementation
Volume 7 - 2025 | doi: 10.3389/fdgth.2025.1655154
This article is part of the Research TopicDigital Medicine and Artificial IntelligenceView all 8 articles
Artificial Intelligence and Health Empowerment in Rural Communities and Landslide-or Avalanche-Isolated Contexts: Real case at a fictitious location
Provisionally accepted
Rune Johan Krumsvik*
Vegard Slettvoll- University of Bergen, Bergen, Norway
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Rural Norwegian communities periodically lose primary-care access when avalanches or landslides sever roads and over-stretch general-practitioner (GP) rosters. We evaluated whether inexpensive point-of-care (POC) diagnostics combined with large-language-model (LLM) reasoning can maintain guideline-concordant care under such constraints. An authentic single-patient episode—presented with a fictitious location for anonymity—serves as the test case. A previously healthy 16-year-old male developed high-grade fever (39.5 °C), exudative tonsillitis, odynophagia, and tender cervical nodes. Home POC tests yielded C-reactive protein (CRP) 130 mg/L (finger-stick analyser), blood pressure 112/68 mmHg, pulse 58 bpm, oxygen saturation 98 %, and normal mobile ECG. These data were entered into a chain-of-thought prompt for the OpenAI o3 reasoning model, with cross-checks in GPT-4. The LLM prioritised acute bacterial tonsillitis, highlighted peritonsillar abscess as a red-flag differential, and advised clinician review within 24 h. A licensed physician in the family network clinically confirmed the diagnosis and prescribed phenoxymethylpenicillin 660 mg four times daily. Follow-up at 72 h showed afebrile status and CRP reduction to 23 mg/L, indicating successful therapy. The case demonstrates that a “virtual waiting-room” comprising finger-stick biomarkers, wearable sensor feeds, and guideline-trained LLM prompts can safely bridge a five-day gap in GP availability, provided human oversight is preserved. Implementation requires reliable broadband or satellite links, affordable consumables, and compliance with GDPR special-category data rules, the EU Artificial Intelligence Act (Regulation 2024/1689), and MDR software classification. With these safeguards, AI-augmented self-care pathways could strengthen health empowerment and disaster preparedness in landslide- and avalanche-isolated regions.
Keywords: artificial intelligence, landslide, Avalanches, Isolated villages, Rural Healthcare, health empowerment, simulated rural setting, brief case report
Received: 27 Jun 2025; Accepted: 08 Aug 2025.
Copyright: © 2025 Krumsvik and Slettvoll. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Rune Johan Krumsvik, University of Bergen, Bergen, Norway
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.