{"ID":2861303,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01671","arxiv_id":"2510.01671","title":"A Locally Executable AI System for Improving Preoperative Patient Communication: A Multi-Domain Clinical Evaluation","abstract":"Patients awaiting invasive procedures often have unanswered pre-procedural questions; however, time-pressured workflows and privacy constraints limit personalized counseling. We present LENOHA (Low Energy, No Hallucination, Leave No One Behind Architecture), a safety-first, local-first system that routes inputs with a high-precision sentence-transformer classifier and returns verbatim answers from a clinician-curated FAQ for clinical queries, eliminating free-text generation in the clinical path. We evaluated two domains (tooth extraction and gastroscopy) using expert-reviewed validation sets (n=400/domain) for thresholding and independent test sets (n=200/domain). Among the four encoders, E5-large-instruct (560M) achieved an overall accuracy of 0.983 (95% CI 0.964-0.991), AUC 0.996, and seven total errors, which were statistically indistinguishable from GPT-4o on this task; Gemini made no errors on this test set. Energy logging shows that the non-generative clinical path consumes ~1.0 mWh per input versus ~168 mWh per small-talk reply from a local 8B SLM, a ~170x difference, while maintaining ~0.10 s latency on a single on-prem GPU. These results indicate that near-frontier discrimination and generation-induced errors are structurally avoided in the clinical path by returning vetted FAQ answers verbatim, supporting privacy, sustainability, and equitable deployment in bandwidth-limited environments.","short_abstract":"Patients awaiting invasive procedures often have unanswered pre-procedural questions; however, time-pressured workflows and privacy constraints limit personalized counseling. We present LENOHA (Low Energy, No Hallucination, Leave No One Behind Architecture), a safety-first, local-first system that routes inputs with a...","url_abs":"https://arxiv.org/abs/2510.01671","url_pdf":"https://arxiv.org/pdf/2510.01671v1","authors":"[\"Motoki Sato\",\"Yuki Matsushita\",\"Hidekazu Takahashi\",\"Tomoaki Kakazu\",\"Sou Nagata\",\"Mizuho Ohnuma\",\"Atsushi Yoshikawa\",\"Masayuki Yamamura\"]","published":"2025-10-02T04:53:11Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.HC\"]","methods":"[\"Transformer\"]","has_code":false}