@inproceedings{mehta-2025-pnlp,
title = "{PNLP} at {MEDIQA}-{OE} 2025: A Zero-Shot Prompting Strategy with Gemini for Medical Order Extraction",
author = "Mehta, Parth",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 7th Clinical Natural Language Processing Workshop",
month = oct,
year = "2025",
address = "Virtual",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.clinicalnlp-1.9/",
pages = "75--83",
abstract = "Medical order extraction from doctor-patient conversations presents a critical challenge in reducing clinical documentation burden and ensuring accurate capture of patient care instructions. This paper describes our system for the MEDIQA-OE 2025 shared task using the ACI-Bench and PriMock57 datasets, which achieved second place on the public leaderboard with an average score of 0.6014 across four metrics: description ROUGE-1 F1, reason ROUGE-1 F1, order-type strict F1, and provenance multi-label F1. Unlike traditional approaches that rely on fine-tuned biomedical language models, we demonstrate that a carefully engineered zero-shot prompting strategy using Gemini 2.5 Pro can achieve competitive performance without requiring model training or GPU resources. Our approach employs a deterministic state-machine prompt design incorporating chain-of-thought reasoning, self-verification protocols, and structured JSON output generation. The system particularly excels in reason extraction, achieving 0.4130 ROUGE-1 F1, the highest among the top performing teams. Our results suggest that advanced prompt engineering can effectively bridge the gap between general-purpose large language models and specialized clinical NLP tasks, offering a computationally efficient and immediately deployable alternative to traditional fine-tuning approaches with significant implications for resource-constrained healthcare settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehta-2025-pnlp">
<titleInfo>
<title>PNLP at MEDIQA-OE 2025: A Zero-Shot Prompting Strategy with Gemini for Medical Order Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parth</namePart>
<namePart type="family">Mehta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical order extraction from doctor-patient conversations presents a critical challenge in reducing clinical documentation burden and ensuring accurate capture of patient care instructions. This paper describes our system for the MEDIQA-OE 2025 shared task using the ACI-Bench and PriMock57 datasets, which achieved second place on the public leaderboard with an average score of 0.6014 across four metrics: description ROUGE-1 F1, reason ROUGE-1 F1, order-type strict F1, and provenance multi-label F1. Unlike traditional approaches that rely on fine-tuned biomedical language models, we demonstrate that a carefully engineered zero-shot prompting strategy using Gemini 2.5 Pro can achieve competitive performance without requiring model training or GPU resources. Our approach employs a deterministic state-machine prompt design incorporating chain-of-thought reasoning, self-verification protocols, and structured JSON output generation. The system particularly excels in reason extraction, achieving 0.4130 ROUGE-1 F1, the highest among the top performing teams. Our results suggest that advanced prompt engineering can effectively bridge the gap between general-purpose large language models and specialized clinical NLP tasks, offering a computationally efficient and immediately deployable alternative to traditional fine-tuning approaches with significant implications for resource-constrained healthcare settings.</abstract>
<identifier type="citekey">mehta-2025-pnlp</identifier>
<location>
<url>https://aclanthology.org/2025.clinicalnlp-1.9/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>75</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PNLP at MEDIQA-OE 2025: A Zero-Shot Prompting Strategy with Gemini for Medical Order Extraction
%A Mehta, Parth
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 7th Clinical Natural Language Processing Workshop
%D 2025
%8 October
%I Association for Computational Linguistics
%C Virtual
%F mehta-2025-pnlp
%X Medical order extraction from doctor-patient conversations presents a critical challenge in reducing clinical documentation burden and ensuring accurate capture of patient care instructions. This paper describes our system for the MEDIQA-OE 2025 shared task using the ACI-Bench and PriMock57 datasets, which achieved second place on the public leaderboard with an average score of 0.6014 across four metrics: description ROUGE-1 F1, reason ROUGE-1 F1, order-type strict F1, and provenance multi-label F1. Unlike traditional approaches that rely on fine-tuned biomedical language models, we demonstrate that a carefully engineered zero-shot prompting strategy using Gemini 2.5 Pro can achieve competitive performance without requiring model training or GPU resources. Our approach employs a deterministic state-machine prompt design incorporating chain-of-thought reasoning, self-verification protocols, and structured JSON output generation. The system particularly excels in reason extraction, achieving 0.4130 ROUGE-1 F1, the highest among the top performing teams. Our results suggest that advanced prompt engineering can effectively bridge the gap between general-purpose large language models and specialized clinical NLP tasks, offering a computationally efficient and immediately deployable alternative to traditional fine-tuning approaches with significant implications for resource-constrained healthcare settings.
%U https://aclanthology.org/2025.clinicalnlp-1.9/
%P 75-83
Markdown (Informal)
[PNLP at MEDIQA-OE 2025: A Zero-Shot Prompting Strategy with Gemini for Medical Order Extraction](https://aclanthology.org/2025.clinicalnlp-1.9/) (Mehta, ClinicalNLP 2025)
ACL