Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2510.01671 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915530663788544 |
|---|---|
| author | Sato, Motoki Matsushita, Yuki Takahashi, Hidekazu Kakazu, Tomoaki Nagata, Sou Ohnuma, Mizuho Yoshikawa, Atsushi Yamamura, Masayuki |
| author_facet | Sato, Motoki Matsushita, Yuki Takahashi, Hidekazu Kakazu, Tomoaki Nagata, Sou Ohnuma, Mizuho Yoshikawa, Atsushi Yamamura, Masayuki |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Locally Executable AI System for Improving Preoperative Patient Communication: A Multi-Domain Clinical Evaluation Sato, Motoki Matsushita, Yuki Takahashi, Hidekazu Kakazu, Tomoaki Nagata, Sou Ohnuma, Mizuho Yoshikawa, Atsushi Yamamura, Masayuki Artificial Intelligence Human-Computer Interaction 68T01 J.3 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. |
| title | A Locally Executable AI System for Improving Preoperative Patient Communication: A Multi-Domain Clinical Evaluation |
| topic | Artificial Intelligence Human-Computer Interaction 68T01 J.3 |
| url | https://arxiv.org/abs/2510.01671 |