Abstract Details

Title A Modular Expert System for Stroke Vascular Localization from Clinical Free Text

Topic Cerebrovascular Disease and Interventional Neurology

Presentation(s) P10 - Poster Session 10 (8:00 AM-9:00 AM)

Poster/Presentation
Number 4-004

Objective We developed a multimodular expert system for stroke vascular localization based on verbatim clinical text using contemporary LLM-driven approaches.

Background Being able to neurologically localize to a vascular territory is essential in distinguishing true strokes from mimics—a challenge in settings with limited neurologist availability.

Design/Methods Chief complaints, neurological examinations, and neuroradiologic imaging were extracted from 369 cases in the MIMIC-IV-Note database and processed through a three-layered multimodular system across three trials. The first layer utilized gemini-2.5-flash-lite to structure clinical free-text into symptom surveys. The second layer generated regional brain predictions through a scoring system, while the third mapped these predictions to major vascular territories using rule-based logic.

Results The stroke symptom survey, brain-region, and vascular-territory predictions achieved average Jaccard indices of 0.81, 0.88, and 0.93, respectively across three trials. Lesion-side were highly reliable (accuracy 0.91, F1 0.91), while brain region-level localization was more challenging (accuracy 0.71, F1 0.51). The vascular-territory classifier showed strong overall performance (accuracy 0.93, F1 0.92), maintaining high accuracy even when combined with side predictions (accuracy 0.93, F1 0.86). Across vascular territories, middle cerebral artery predictions achieved an accuracy of 0.93 and F1 score of 0.96. The posterior cerebral artery achieved the highest accuracy (0.99) and F1 of 0.85. The basilar artery showed an accuracy of 0.96 and F1 of 0.56. Vertebral predictions showed accuracy of 0.98 and F1 of 0.71.

Conclusions The new multimodular system demonstrates that integrating large language models for structured data extraction with transparent rule-based reasoning provides both flexibility and stability in stroke localization from free-text clinical documentation, enabling its use as a powerful clinical, educational, and research tool.

Authors/Disclosures
Jung-Hyun Lee, MD (SUNY Downstate Medical Center) PRESENTER	Dr. Lee has nothing to disclose.
Sujith Vasireddy, MBBS (SUNY Downstate)	Dr. Vasireddy has nothing to disclose.
Shih-Syuan Wang, MD (SUNY Downstate Medical Center)	Dr. Wang has nothing to disclose.
Svetlana Kozlova, MD (SUNY Downstate Health Sciences University)	Dr. Kozlova has nothing to disclose.
Sergio L. Angulo Castro, MD, PhD	Dr. Angulo Castro has nothing to disclose.
Steven Levine, MD, FAHA (SUNY Downstate Medical Center)	Dr. Levine has received personal compensation in the range of $500-$4,999 for serving as an Editor, Associate Editor, or Editorial Advisory Board Member for MEDLINK. Dr. Levine has received personal compensation in the range of $50,000-$99,999 for serving as an Expert Witness for Law Firms. The institution of Dr. Levine has received research support from NIH.
William W. Lytton, MD (SUNY Downstate)	Dr. Lytton has nothing to disclose.

��ɫ��

��ɫ��