Salvato in:
Dettagli Bibliografici
Autori principali: Kumar, Niranjan, Seifi, Farid, Conte, Marisa, Flynn, Allen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.17550
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909547799511040
author Kumar, Niranjan
Seifi, Farid
Conte, Marisa
Flynn, Allen
author_facet Kumar, Niranjan
Seifi, Farid
Conte, Marisa
Flynn, Allen
contents Clinical calculators are widely used, and large language models (LLMs) make it possible to engage them using natural language. We demonstrate a purpose-built chatbot that leverages software implementations of verifiable clinical calculators via LLM tools and metadata about these calculators via retrieval augmented generation (RAG). We compare the chatbot's response accuracy to an unassisted off-the-shelf LLM on four natural language conversation workloads. Our chatbot achieves 100% accuracy on queries interrogating calculator metadata content and shows a significant increase in clinical calculation accuracy vs. the off-the-shelf LLM when prompted with complete sentences (86.4% vs. 61.8%) or with medical shorthand (79.2% vs. 62.0%). It eliminates calculation errors when prompted with complete sentences (0% vs. 16.8%) and greatly reduces them when prompted with medical shorthand (2.4% vs. 18%). While our chatbot is not ready for clinical use, these results show progress in minimizing incorrect calculation results.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17550
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An LLM-Powered Clinical Calculator Chatbot Backed by Verifiable Clinical Calculators and their Metadata
Kumar, Niranjan
Seifi, Farid
Conte, Marisa
Flynn, Allen
Quantitative Methods
Clinical calculators are widely used, and large language models (LLMs) make it possible to engage them using natural language. We demonstrate a purpose-built chatbot that leverages software implementations of verifiable clinical calculators via LLM tools and metadata about these calculators via retrieval augmented generation (RAG). We compare the chatbot's response accuracy to an unassisted off-the-shelf LLM on four natural language conversation workloads. Our chatbot achieves 100% accuracy on queries interrogating calculator metadata content and shows a significant increase in clinical calculation accuracy vs. the off-the-shelf LLM when prompted with complete sentences (86.4% vs. 61.8%) or with medical shorthand (79.2% vs. 62.0%). It eliminates calculation errors when prompted with complete sentences (0% vs. 16.8%) and greatly reduces them when prompted with medical shorthand (2.4% vs. 18%). While our chatbot is not ready for clinical use, these results show progress in minimizing incorrect calculation results.
title An LLM-Powered Clinical Calculator Chatbot Backed by Verifiable Clinical Calculators and their Metadata
topic Quantitative Methods
url https://arxiv.org/abs/2503.17550