About this document
Evaluating LLMs for Italian EHRs by contactgreenbhumi is a document available to read on EtoBox.
This document explores the zero-shot multilingual capabilities of Large Language Models (LLMs) in extracting information from Italian Electronic Health Records (EHRs) within the healthcare sector. It evaluates the performance of various open-source LLMs against traditional regular expression methods for extracting comorbidities, revealing that while some LLMs perform well, others struggle with generalization across diseases. The study emphasizes the importance of accurate data annotation and the challenges
- Author
- contactgreenbhumi
- Language
- EN