# A Locally Executable AI System for Improving Preoperative Patient Communication: A Multi-Domain Clinical Evaluation

arXiv: https://arxiv.org/abs/2510.01671 · HTML: https://mlsanity.com/paper/2510.01671/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 45 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Measuring the Carbon Intensity of AI in Cloud Instances](https://mlsanity.com/paper/2206.05229/) (2022)
- [Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities](https://mlsanity.com/paper/2404.17790/) (2024)
- [ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?](https://mlsanity.com/paper/2411.06469/) (2024)
- [Measuring the environmental impact of delivering AI at Google Scale](https://mlsanity.com/paper/2508.15734/) (2025)
- [Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks](https://mlsanity.com/paper/2404.00376/) (2024)
- [Clinical knowledge in LLMs does not translate to human interactions](https://mlsanity.com/paper/2504.18919/) (2025)
- [Global Performance Disparities Between English-Language Accents in Automatic Speech Recognition](https://mlsanity.com/paper/2208.01157/) (2022)
- [Generating Explanations in Medical Question-Answering by Expectation Maximization Inference over Evidence](https://mlsanity.com/paper/2310.01299/) (2023)
- [The Multicultural Medical Assistant: Can LLMs Improve Medical ASR Errors Across Borders?](https://mlsanity.com/paper/2501.15310/) (2025)

## Abstract (arXiv)

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.