Automated Identification of Stroke Thrombolysis Contraindications from Synthetic Clinical Notes: A Proof-of-Concept Study

Introduction: Timely thrombolytic therapy improves outcomes in acute ischemic stroke. Manual chart review to screen for thrombolysis contraindications may be time-consuming and prone to errors. We developed and tested a large language model (LLM)-based tool to identify thrombolysis contra...

Full description

Saved in:
Bibliographic Details
Main Authors: Bing Yu Chen, Fares Antaki, Marco Gonzalez, Ken Uchino, Samer Albahra, Scott Robertson, Sidonie Ibrikji, Eric Aube, Andrew Russman, Muhammad Shazam Hussain
Format: Article
Language:English
Published: Karger Publishers 2025-03-01
Series:Cerebrovascular Diseases Extra
Online Access:https://karger.com/article/doi/10.1159/000545317
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321572981014528
author Bing Yu Chen
Fares Antaki
Marco Gonzalez
Ken Uchino
Samer Albahra
Scott Robertson
Sidonie Ibrikji
Eric Aube
Andrew Russman
Muhammad Shazam Hussain
author_facet Bing Yu Chen
Fares Antaki
Marco Gonzalez
Ken Uchino
Samer Albahra
Scott Robertson
Sidonie Ibrikji
Eric Aube
Andrew Russman
Muhammad Shazam Hussain
author_sort Bing Yu Chen
collection DOAJ
description Introduction: Timely thrombolytic therapy improves outcomes in acute ischemic stroke. Manual chart review to screen for thrombolysis contraindications may be time-consuming and prone to errors. We developed and tested a large language model (LLM)-based tool to identify thrombolysis contraindications from clinical notes using synthetic data in a proof-of-concept study. Methods: We generated 150 synthetic clinical notes containing randomly assigned thrombolysis contraindications using LLMs. We then used Llama 3.1 405B with a custom prompt to generate a list of thrombolysis contraindications from each note. Performance was evaluated using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and F1 score. Results: A total of 150 synthetic notes were generated using five different models: ChatGPT-4o, Llama 3.1 405B, Llama 3.1 70B, ChatGPT-4o mini, and Gemini 1.5 Flash. On average, each note contained 241.6 words (SD 110.7; range 80–549) and included 1.5 contraindications (SD 1.1; range 0–5). Our tool achieved a sensitivity of 90.9% (95% CI: 86.3%–94.3%), specificity of 99.2% (95% CI: 98.8%–99.5%), PPV of 87.7% (95% CI: 82.7%–91.7%), NPV of 99.4% (95% CI: 99.1%–99.6%), accuracy of 98.7% (95% CI: 98.2%–99.0%), and an F1 score of 0.892. Among the false positives, 24 (86%) were due to the inclusion of irrelevant contraindications, and 4 (14%) resulted from repetitive information. No hallucinations were observed. Conclusion: Our LLM-based tool may identify stroke thrombolysis contraindications from synthetic clinical notes with high sensitivity and PPV. Future studies will validate its performance using real EMR data and integrate it into acute stroke workflows to facilitate faster and safer thrombolysis decision-making.
format Article
id doaj-art-a261535fef634dac8240d91aed8212a5
institution Kabale University
issn 1664-5456
language English
publishDate 2025-03-01
publisher Karger Publishers
record_format Article
series Cerebrovascular Diseases Extra
spelling doaj-art-a261535fef634dac8240d91aed8212a52025-08-20T03:49:42ZengKarger PublishersCerebrovascular Diseases Extra1664-54562025-03-0115113013610.1159/000545317Automated Identification of Stroke Thrombolysis Contraindications from Synthetic Clinical Notes: A Proof-of-Concept StudyBing Yu ChenFares AntakiMarco GonzalezKen Uchinohttps://orcid.org/0000-0001-9468-4172Samer AlbahraScott RobertsonSidonie IbrikjiEric AubeAndrew RussmanMuhammad Shazam Hussain Introduction: Timely thrombolytic therapy improves outcomes in acute ischemic stroke. Manual chart review to screen for thrombolysis contraindications may be time-consuming and prone to errors. We developed and tested a large language model (LLM)-based tool to identify thrombolysis contraindications from clinical notes using synthetic data in a proof-of-concept study. Methods: We generated 150 synthetic clinical notes containing randomly assigned thrombolysis contraindications using LLMs. We then used Llama 3.1 405B with a custom prompt to generate a list of thrombolysis contraindications from each note. Performance was evaluated using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and F1 score. Results: A total of 150 synthetic notes were generated using five different models: ChatGPT-4o, Llama 3.1 405B, Llama 3.1 70B, ChatGPT-4o mini, and Gemini 1.5 Flash. On average, each note contained 241.6 words (SD 110.7; range 80–549) and included 1.5 contraindications (SD 1.1; range 0–5). Our tool achieved a sensitivity of 90.9% (95% CI: 86.3%–94.3%), specificity of 99.2% (95% CI: 98.8%–99.5%), PPV of 87.7% (95% CI: 82.7%–91.7%), NPV of 99.4% (95% CI: 99.1%–99.6%), accuracy of 98.7% (95% CI: 98.2%–99.0%), and an F1 score of 0.892. Among the false positives, 24 (86%) were due to the inclusion of irrelevant contraindications, and 4 (14%) resulted from repetitive information. No hallucinations were observed. Conclusion: Our LLM-based tool may identify stroke thrombolysis contraindications from synthetic clinical notes with high sensitivity and PPV. Future studies will validate its performance using real EMR data and integrate it into acute stroke workflows to facilitate faster and safer thrombolysis decision-making. https://karger.com/article/doi/10.1159/000545317
spellingShingle Bing Yu Chen
Fares Antaki
Marco Gonzalez
Ken Uchino
Samer Albahra
Scott Robertson
Sidonie Ibrikji
Eric Aube
Andrew Russman
Muhammad Shazam Hussain
Automated Identification of Stroke Thrombolysis Contraindications from Synthetic Clinical Notes: A Proof-of-Concept Study
Cerebrovascular Diseases Extra
title Automated Identification of Stroke Thrombolysis Contraindications from Synthetic Clinical Notes: A Proof-of-Concept Study
title_full Automated Identification of Stroke Thrombolysis Contraindications from Synthetic Clinical Notes: A Proof-of-Concept Study
title_fullStr Automated Identification of Stroke Thrombolysis Contraindications from Synthetic Clinical Notes: A Proof-of-Concept Study
title_full_unstemmed Automated Identification of Stroke Thrombolysis Contraindications from Synthetic Clinical Notes: A Proof-of-Concept Study
title_short Automated Identification of Stroke Thrombolysis Contraindications from Synthetic Clinical Notes: A Proof-of-Concept Study
title_sort automated identification of stroke thrombolysis contraindications from synthetic clinical notes a proof of concept study
url https://karger.com/article/doi/10.1159/000545317
work_keys_str_mv AT bingyuchen automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy
AT faresantaki automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy
AT marcogonzalez automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy
AT kenuchino automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy
AT sameralbahra automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy
AT scottrobertson automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy
AT sidonieibrikji automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy
AT ericaube automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy
AT andrewrussman automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy
AT muhammadshazamhussain automatedidentificationofstrokethrombolysiscontraindicationsfromsyntheticclinicalnotesaproofofconceptstudy