EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

System Architecture of a Local Hybrid AI for Secure Patient Communication: Implementation on Consumer Hardware

Motoki Sato, Yuki Matsushita, Hidekazu Takahashi, Tomoaki Kakazu, Sou Nagata, Mizuho Ohnuma, Atsushi Yoshikawa, Masayuki Yamamura

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260228 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Motoki Sato und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Skeletal Development and Regenerative Biology, Nagasaki University, Graduate School of Biomedical Sciences, Nagasaki, Japan. Hauptthemen laut MEDLINE: Computer Security, Artificial Intelligence, Communication. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We constructed a system that explicitly separates clinically oriented queries from low-risk casual conversation using a sentence-transformer classifier. Clinical inputs are routed to a non-generative, expert vetted Frequently Asked Questions (FAQ) retrieval module that returns predefined answers verbatim, while non-clinical inputs are handled by a locally hosted small language model (SLM) restricted to brief, empathic small talk. Performance tests on a standard laptop GPU demonstrated that the routing module achieved over 98% accuracy (AUC 0.996) across two domains (tooth extraction and gastroscopy), with decision thresholds calibrated by Youden’s index. Within the FAQ-based clinical pathway, all test utterances mapped to pre-authored question–answer pairs, so clinical replies remained deterministic and expert-approved rather than being generated. System profiling revealed that the non-generative FAQ pathway reduced energy consumption by approximately 75x (2.23 mWh vs. 168 mWh per request) and achieved substantially lower latency (∼0.10 s vs. ∼8.51 s) compared to the generative SLM pathway. These findings support the feasibility of deploying a privacy-preserving, energy-efficient hybrid architecture for preoperative patient communication that operates entirely offline, and they provide an implementation-focused complement to our broader research on the clinical and ethical aspects of such systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computer SecurityArtificial IntelligenceCommunicationHumansConfidentiality

Stichwörter der Autor:innen

Local AIPatient CommunicationPrivacyTrustworthy AI

Autor:innen und Institutionen

  • Department of Skeletal Development and Regenerative Biology, Nagasaki University, Graduate School of Biomedical Sciences, Nagasaki, Japan.
  • Boston Medical Sciences, Inc., Japan.
  • Digestive Disease Center, Showa Medical University Koto Toyosu Hospital, Japan.
  • Department of Oral and Maxillofacial Surgery, Nagasaki University Graduate School of Biomedical Sciences, Japan.
  • College of Science and Engineering, Kanto Gakuin University, Japan.
  • Department of Computer Science, Tokyo Institute of Technology, Japan.

Zitieren

APA

Sato, M., Matsushita, Y., Takahashi, H., Kakazu, T., Nagata, S., Ohnuma, M., Yoshikawa, A., & Yamamura, M. (2026). System Architecture of a Local Hybrid AI for Secure Patient Communication: Implementation on Consumer Hardware. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260228

Vancouver

Sato M, Matsushita Y, Takahashi H, Kakazu T, Nagata S, Ohnuma M, et al. System Architecture of a Local Hybrid AI for Secure Patient Communication: Implementation on Consumer Hardware. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260228

BibTeX
@article{Sato2026,
  author = {Sato, Motoki and Matsushita, Yuki and Takahashi, Hidekazu and Kakazu, Tomoaki and Nagata, Sou and Ohnuma, Mizuho and Yoshikawa, Atsushi and Yamamura, Masayuki},
  title = {System Architecture of a Local Hybrid AI for Secure Patient Communication: Implementation on Consumer Hardware},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260228}
}
Kostenlos starten →