Evaluating Prompting Strategies with MedGemma for Medical Order Extraction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918200980013056 |
|---|---|
| author | Balachandran, Abhinand Durgapraveen, Bavana Sudhagar, Gowsikkan Sikkan S, Vidhya Varshany J Rajkumar, Sriram |
| author_facet | Balachandran, Abhinand Durgapraveen, Bavana Sudhagar, Gowsikkan Sikkan S, Vidhya Varshany J Rajkumar, Sriram |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10583 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating Prompting Strategies with MedGemma for Medical Order Extraction Balachandran, Abhinand Durgapraveen, Bavana Sudhagar, Gowsikkan Sikkan S, Vidhya Varshany J Rajkumar, Sriram Computation and Language Artificial Intelligence 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. |
| title | Evaluating Prompting Strategies with MedGemma for Medical Order Extraction |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2511.10583 |