Score: 0

Evaluating Prompting Strategies with MedGemma for Medical Order Extraction

Published: November 13, 2025 | arXiv ID: 2511.10583v1

By: Abhinand Balachandran , Bavana Durgapraveen , Gowsikkan Sikkan Sudhagar and more

Potential Business Impact:

Helps doctors quickly get important patient notes.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

The accurate extraction of medical orders from doctor-patient conversations is a critical task for reducing clinical documentation burdens and ensuring patient safety. This paper details our team submission to the MEDIQA-OE-2025 Shared Task. We investigate the performance of MedGemma, a new domain-specific open-source language model, for structured order extraction. We systematically evaluate three distinct prompting paradigms: a straightforward one-Shot approach, a reasoning-focused ReAct framework, and a multi-step agentic workflow. Our experiments reveal that while more complex frameworks like ReAct and agentic flows are powerful, the simpler one-shot prompting method achieved the highest performance on the official validation set. We posit that on manually annotated transcripts, complex reasoning chains can lead to "overthinking" and introduce noise, making a direct approach more robust and efficient. Our work provides valuable insights into selecting appropriate prompting strategies for clinical information extraction in varied data conditions.

Page Count
7 pages

Category
Computer Science:
Computation and Language