Harnessing Large Language Models for Medical Data Processing: Structured Information Extraction, Disease Classification, and RAG Integration 

Add to your list(s) Download to your calendar using vCal

• Cristian Cosentino (Università della Calabria)
• Monday 24 February 2025, 17:30-20:30
• Lecture Theatre 2, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Pietro Lio.

This talk will explore various applications of Large Language Models (LLMs) in the medical domain, focusing on three key topics: structured information extraction from free-text data, Alzheimer’s classification, and the integration of Retrieval-Augmented Generation (RAG) with medical information.

The session will cover how LLMs can be utilized to extract structured insights from unstructured clinical documents, improving the accessibility and usability of medical knowledge. Additionally, we will discuss their role in Alzheimer’s classification, evaluating the effectiveness of fine-tuned LLMs in processing multimodal clinical data for early diagnosis. Finally, we will delve into the integration of RAG to enhance medical information retrieval, reducing hallucinations and improving the reliability of AI-generated responses.

Through this discussion, we will highlight the challenges and opportunities associated with deploying LLMs in healthcare, examining how these models can be optimized for real-world medical applications. The talk will conclude with insights into future research directions and potential advancements in AI-driven medical analysis.

(Cambridge) Harnessing Large Language Models for Medical Data Processing: Structured Information Extraction, Disease Classification, and RAG

Google Meet Link: https://meet.google.com/cmn-gjvy-zuy

This talk is part of the Foundation AI series.

This talk is included in these lists:

• Lecture Theatre 2, Computer Laboratory, William Gates Building

Note that ex-directory lists are not shown.