Large Language Models-Supported Thrombectomy Decision-Making in Acute Ischemic Stroke Based on Radiology Reports: Feasibility Qualitative Study

 

Artificial intelligence does nothing if the underlying research for 100% recovery is not there! This may help in this limited instance, but artificial intelligence is NOT the answer to stroke recovery.

Large Language Models-Supported Thrombectomy Decision-Making in Acute Ischemic Stroke Based on Radiology Reports: Feasibility Qualitative Study

• February 2025
• Journal of Medical Internet Research 27:e48328

DOI:10.2196/48328

Authors:

Jonathan Kottlors

• University of Cologne

Robert Hahnfeldt

Lukas Goertz

• University of Cologne

Andra Iuga

• University of Cologne

Show all 15 authors

To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Background 

The latest advancement of artificial intelligence (AI) is generative pretrained transformer large language models (LLMs). They have been trained on massive amounts of text, enabling humanlike and semantical responses to text-based inputs and requests. Foreshadowing numerous possible applications in various fields, the potential of such tools for medical data integration and clinical decision-making is not yet clear. 

Objective 

In this study, we investigate the potential of LLMs in report-based medical decision-making on the example of acute ischemic stroke (AIS), where clinical and image-based information may indicate an immediate need for mechanical thrombectomy (MT). The purpose was to elucidate the feasibility of integrating radiology report data and other clinical information in the context of therapy decision-making using LLMs. 

Methods 

A hundred patients with AIS were retrospectively included, for which 50% (50/100) was indicated for MT, whereas the other 50% (50/100) was not. The LLM was provided with the computed tomography report, information on neurological symptoms and onset, and patients’ age. The performance of the AI decision-making model was compared with an expert consensus regarding the binary determination of MT indication, for which sensitivity, specificity, and accuracy were calculated. 

Results 

The AI model had an overall accuracy of 88%, with a specificity of 96% and a sensitivity of 80%. The area under the curve for the report-based MT decision was 0.92. 

Conclusions 

The LLM achieved promising accuracy in determining the eligibility of patients with AIS for MT based on radiology reports and clinical information. Our results underscore the potential of LLMs for radiological and medical data integration. This investigation should serve as a stimulus for further clinical applications of LLMs, in which this AI should be used as an augmented supporting system for human decision-making.