EUVIMEDOpdag EUVIMED
Open access

A Locally Executable AI System for Improving Preoperative Patient Communication: Multidomain Clinical Evaluation

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

JMIR Medical Informatics · 2026-07-21 · 14 · e89173-e89173

DOI: 10.2196/89173 ↗

At a glance

Journal article in JMIR Medical Informatics, published online on 2026-07-21. Written by Motoki Sato and 7 co-authors. Institution: Department of Skeletal Development and Regenerative Biology, Graduate School of Biomedical Sciences, Nagasaki University, 3F Building for Basic Denta…. Major MEDLINE topics: Artificial Intelligence, Communication, Preoperative Period. Cited 1 times so far (Crossref); 35 references. The full text is freely available in PubMed Central.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Patients undergoing invasive procedures frequently experience anxiety and often have unanswered questions regarding the procedure. Although large language models show considerable promise for supporting patient communication in many cases, their deployment in health care is limited by the risk of hallucinations, data-privacy constraints, and high energy costs—factors that impede equitable access in resource-limited settings.

Objective

This study aims to develop and evaluate LENOHA (Low Energy, No Hallucination, Leave No One Behind Architecture), a locally executable dialog system for safe, equitable, and sustainable preprocedural communication.

Methods

We built expert-curated FAQ (frequently asked question) databases and independent test sets for 2 domains (tooth extraction and gastroscopy; 200 utterances per domain: 100 clinical questions and 100 casual). A sentence-transformer classifier routed inputs: clinical questions were answered verbatim from the vetted FAQs (nongenerative path), while casual conversation was handled by a locally hosted 8-billion-parameter small language model (Swallow-8B). We evaluated 4 sentence-transformer models (including E5-large-instruct) against cloud large language models (ChatGPT [GPT-4o] and Gemini Advanced) using accuracy, F 1 -score, and area under the receiver operating characteristic curve, and measured the on-device inference energy on a consumer graphics processing unit (RTX 3080).

Results

Across both domains (N=400), E5-large-instruct achieved an accuracy of 98.3% (393/400; 95% CI 96.4%‐99.1%) and an area under the curve of 0.996, with only 7 out of 400 (1.8%) misclassifications. This performance was not statistically different from that of ChatGPT (GPT-4o), which had 6 out of 400 (1.5%) errors (McNemar test with Holm adjustment; P >.99). Sustainability measurements showed approximately 2.23 mWh per request (latency≈0.10 s; video RAM≈2.2 GiB average, ≈2.5 GiB peak) for the nongenerative clinical path vs approximately 168.27 mWh (latency≈8.51 s; video RAM≈13.3 GiB average, ≈14.0 GiB peak) for small language model small talk—approximately a 75-fold higher energy footprint per reply for the generative path.

Conclusions

High-precision, nongenerative clinical support is feasible using local, low-cost hardware without cloud dependence. By decoupling clinical information retrieval from generative chitchat, LENOHA enhances safety, preserves privacy, and markedly reduces energy use, offering a practical blueprint for sustainable and equitable medical AI deployment across diverse care settings.

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceCommunicationPreoperative PeriodHumansLarge Language Models

Author keywords

AIartificial intelligencedoctor-patient communicationenergy metabolismimplementation sciencelarge language modelsnatural language processingprivacy

Authors and institutions

  • Department of Skeletal Development and Regenerative Biology, Graduate School of Biomedical Sciences, Nagasaki University, 3F Building for Basic Dental Science, 1-7-1 Sakamoto, Nagasaki, Japan, 81 95-819-7633, 81 95-819-…
  • Boston Medical Sciences, Inc., Tokyo, Japan.
  • Digestive Diseases Center, Showa University Koto Toyosu Hospital, Tokyo, Japan.
  • Department of Computer Science, School of Computing, Institute of Science Tokyo, Tokyo, Japan.
  • College of Informatics, Kanto Gakuen University, Yokohama, Kanagawa, Japan.

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

Cite

APA

Sato, M., Nagata, S., Ohnuma, M., Takahashi, H., Kakazu, T., Yamamura, M., Yoshikawa, A., & Matsushita, Y. (2026). A Locally Executable AI System for Improving Preoperative Patient Communication: Multidomain Clinical Evaluation. JMIR Medical Informatics, 14, e89173-e89173. https://doi.org/10.2196/89173

Vancouver

Sato M, Nagata S, Ohnuma M, Takahashi H, Kakazu T, Yamamura M, et al. A Locally Executable AI System for Improving Preoperative Patient Communication: Multidomain Clinical Evaluation. JMIR Medical Informatics. 2026;14:e89173-e89173. doi:10.2196/89173

BibTeX
@article{Sato2026,
  author = {Sato, Motoki and Nagata, Sou and Ohnuma, Mizuho and Takahashi, Hidekazu and Kakazu, Tomoaki and Yamamura, Masayuki and Yoshikawa, Atsushi and Matsushita, Yuki},
  title = {A Locally Executable AI System for Improving Preoperative Patient Communication: Multidomain Clinical Evaluation},
  journal = {JMIR Medical Informatics},
  year = {2026},
  volume = {14},
  pages = {e89173--e89173},
  doi = {10.2196/89173}
}
Start for free →