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.
@article{arxiv.2511.10583,
title = {Evaluating Prompting Strategies with MedGemma for Medical Order Extraction},
author = {Abhinand Balachandran and Bavana Durgapraveen and Gowsikkan Sikkan Sudhagar and Vidhya Varshany J S and Sriram Rajkumar},
journal= {arXiv preprint arXiv:2511.10583},
year = {2025}
}