LATIDIA · Investigación

Modelos de lenguaje grandes aumentados con herramientas para un cálculo médico confiable a partir de las notas del paciente

arXiv: 2610.21477v1Tipo de anuncio: nuevo Resumen: Las calculadoras médicas traducen los resultados brutos de los pacientes en valores y puntuaciones clínicamente procesables. Sin embargo, aplicar estas calculadoras directamente a las notas libres del paciente

La noticia

arXiv:2610.21477v1 Announce Type: new Abstract: Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to free-form patient notes requires precise variable extraction combined with the exact execution of complex formulas, scoring rules, and output conventions. Relying solely on direct large language model (LLM) prompting is unreliable in this context, as rule recall, parameter extraction, arithmetic reasoning, and formatting become entangled within a single generative step. To address these limitations, we propose a tool-augmented LLM framework for reliable medical calculation from patient notes. The framework retrieves and structures calculator specifications, generates reusable executable tools, and uses a constrained extractor to map each patient