Saved in:
Bibliographic Details
Main Authors: Pijanowski, Justin, Mezgueldi, Yakout, Lee, Alan, Moghanaki, Drew, Savjani, Ricky R., Lamb, James
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.23492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915821303889920
author Pijanowski, Justin
Mezgueldi, Yakout
Lee, Alan
Moghanaki, Drew
Savjani, Ricky R.
Lamb, James
author_facet Pijanowski, Justin
Mezgueldi, Yakout
Lee, Alan
Moghanaki, Drew
Savjani, Ricky R.
Lamb, James
contents We evaluated the viability of using a Large Language Model (LLM) to extract patient-specific specific toxicity and progression outcomes from unstructured radiology reports. We retrospectively extracted 160 follow-up CT and PET/CT electronic medical record notes for patients treated with lung stereotactic body radiotherapy (SBRT) at our institution from January 2017 through December 2023. Using the Llama 3.3-70-B-Instruct LLM, we engineered prompts to extract four clinical endpoints from each radiology report: locoregional progression, distant progression, radiation-induced fibrosis, and radiation-induced rib fractures. Progression endpoints were classified as yes, no, or maybe, while fibrosis and rib fractures were binary (yes or no). Ground truth labels were defined using two-grader consensus for the 60-note training set, used for prompt development, and a three-grader majority vote for the 100-note test set. LLM performance was evaluated using sensitivity, specificity, and accuracy. As detailed by our evaluation metrics, the strong performance of our methods demonstrates the viability of using prompt-engineered LLMs to extract radiation-toxicities and progression classification from radiology reports.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23492
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automated Extraction of Unstructured Post-SBRT Toxicity Data from Radiology Reports Using Large Language Models
Pijanowski, Justin
Mezgueldi, Yakout
Lee, Alan
Moghanaki, Drew
Savjani, Ricky R.
Lamb, James
Medical Physics
We evaluated the viability of using a Large Language Model (LLM) to extract patient-specific specific toxicity and progression outcomes from unstructured radiology reports. We retrospectively extracted 160 follow-up CT and PET/CT electronic medical record notes for patients treated with lung stereotactic body radiotherapy (SBRT) at our institution from January 2017 through December 2023. Using the Llama 3.3-70-B-Instruct LLM, we engineered prompts to extract four clinical endpoints from each radiology report: locoregional progression, distant progression, radiation-induced fibrosis, and radiation-induced rib fractures. Progression endpoints were classified as yes, no, or maybe, while fibrosis and rib fractures were binary (yes or no). Ground truth labels were defined using two-grader consensus for the 60-note training set, used for prompt development, and a three-grader majority vote for the 100-note test set. LLM performance was evaluated using sensitivity, specificity, and accuracy. As detailed by our evaluation metrics, the strong performance of our methods demonstrates the viability of using prompt-engineered LLMs to extract radiation-toxicities and progression classification from radiology reports.
title Automated Extraction of Unstructured Post-SBRT Toxicity Data from Radiology Reports Using Large Language Models
topic Medical Physics
url https://arxiv.org/abs/2602.23492