EXL Health AI Lab at MEDIQA-OE 2025: Evaluating Prompting Strategies with MedGemma for Medical Order Extraction

Abhinand Balachandran, Bavana Durgapraveen, Gowsikkan Sikkan Sudhagar, Vidhya Varshany J S, Sriram Rajkumar


Abstract
The accurate extraction of medical orders fromdoctor-patient conversations is a critical taskfor reducing clinical documentation burdensand ensuring patient safety. This paper detailsour team’s submission to the MEDIQA-OE-2025Shared Task. We investigate the performanceof MedGemma, a new domain-specific opensource language model, for structured order extraction. We systematically evaluate three distinct prompting paradigms: a straightforwardone-shot approach, a reasoning-focused ReActframework, and a multi-step agentic workflow.Our experiments reveal that while more complex frameworks like ReAct and agentic flowsare powerful, the simpler one-shot promptingmethod achieved the highest performance onthe official validation set. We posit that on manually annotated transcripts, complex reasoningchains can lead to “overthinking” and introduce noise, making a direct approach more robust and efficient. Our work provides valuableinsights into selecting appropriate promptingstrategies for clinical information extraction invaried data conditions.
Anthology ID:
2025.clinicalnlp-1.8
Volume:
Proceedings of the 7th Clinical Natural Language Processing Workshop
Month:
October
Year:
2025
Address:
Virtual
Editors:
Asma Ben Abacha, Steven Bethard, Danielle Bitterman, Tristan Naumann, Kirk Roberts
Venues:
ClinicalNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
68–74
Language:
URL:
https://aclanthology.org/2025.clinicalnlp-1.8/
DOI:
Bibkey:
Cite (ACL):
Abhinand Balachandran, Bavana Durgapraveen, Gowsikkan Sikkan Sudhagar, Vidhya Varshany J S, and Sriram Rajkumar. 2025. EXL Health AI Lab at MEDIQA-OE 2025: Evaluating Prompting Strategies with MedGemma for Medical Order Extraction. In Proceedings of the 7th Clinical Natural Language Processing Workshop, pages 68–74, Virtual. Association for Computational Linguistics.
Cite (Informal):
EXL Health AI Lab at MEDIQA-OE 2025: Evaluating Prompting Strategies with MedGemma for Medical Order Extraction (Balachandran et al., ClinicalNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.clinicalnlp-1.8.pdf