Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 20, 2026

Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT

Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT

Published on: January 22, 2018

Rules-Augmented GLM-5.1 Prompting for Four-Class Chest CT Protocol Selection.

Kartik Gupta¹, Jaron Chong²

¹Schulich School of Medicine and Dentistry, Western University, 1151 Richmond St, London, ON, N6A 5C1, Canada. kartikg9@gmail.com.

Journal of Imaging Informatics in Medicine

|June 18, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Multiple-Choice Question Positional Bias and Input Modality Effects in Multimodal Large Language Models.

Radiology·2026

Same author

Chain-of-Thought Reasoning Improves ChatGPT's Diagnostic Accuracy in Radiology.

Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes·2026

Same author

Deep Learning Models Connecting Images and Text: A Primer for Radiologists.

Radiographics : a review publication of the Radiological Society of North America, Inc·2025

Same author

A comparative study of machine learning models predicting post-hepatectomy liver failure: Enhancing risk estimation in over 25,000 National Surgical Quality Improvement Program patients.

Annals of hepato-biliary-pancreatic surgery·2025

Same author

Comparative diagnostic accuracy of GPT-4o and LLaMA 3-70b: Proprietary vs. open-source large language models in radiology.

Clinical imaging·2024

Same author

Laterality: A Potential Pitfall in Applying Multimodal Large Language Models to Radiology.

Radiology·2024

Same journal

Kolmogorov-Arnold Guided Local-Global Attention for Medical Image Classification.

Journal of imaging informatics in medicine·2026

Same journal

Artificial Intelligence-Assisted Inner Ear Computed Tomography Analysis: Radiomics-Based Comparison of Affected and Unaffected Ears in Idiopathic Sudden Sensorineural Hearing Loss.

Journal of imaging informatics in medicine·2026

Same journal

High Adoption, Higher Expectations: A Cross-Sectional Survey of Radiologist Engagement with Artificial Intelligence in the United Arab Emirates.

Journal of imaging informatics in medicine·2026

Same journal

Complex-valued Multi-scale Hybrid Attention Network for Fast MRI via Sparsified Data Learning.

Journal of imaging informatics in medicine·2026

Same journal

Automatic Phase and Sequence Identification in Gd-EOB-DTPA-Enhanced Liver MRI Using Deep Convolutional and Sequential Learning.

Journal of imaging informatics in medicine·2026

Same journal

Ultrasound-Based AI in Predicting Hormone Receptor Status in Breast Cancer: Is "Digital Biopsy" Possible.

Journal of imaging informatics in medicine·2026

See all related articles

Rule-augmented large language models (LLMs) show promise for radiology protocol selection. GLM-5.1 prompting performed comparably to classical methods on imbalanced chest CT data, supporting local rule encoding.

Area of Science:

Radiology and Medical Imaging
Artificial Intelligence in Healthcare
Natural Language Processing

Background:

Large language models (LLMs) are being explored for clinical applications, but their effectiveness in specific, imbalanced tasks like radiology protocol selection is not well-established.
Classical machine learning models and human expertise are current standards for radiology protocol selection.

Purpose of the Study:

To evaluate the performance of a rule-augmented LLM (GLM-5.1) against classical text classifiers for chest CT protocol selection.
To determine if LLM prompting can be competitive for small, imbalanced local tasks in medical imaging.

Main Methods:

Retrospective analysis of 755 chest CT requests from a single Canadian center.
Comparison of GLM-5.1 with a classification-rules prompt against a majority baseline, random forest with TF-IDF and oversampling (RF-ROS), and fine-tuned BioClinicalBERT.

Keywords:

Class imbalance GLM-5.1 Large language models Radiology protocoling Rule-augmented prompting

More Related Videos

Identifying Coronary Artery Calcification on Non-gated Computed Tomography Scans

Identifying Coronary Artery Calcification on Non-gated Computed Tomography Scans

Published on: August 28, 2018

Related Experiment Videos

Last Updated: Jun 20, 2026

Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT

Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT

Published on: January 22, 2018

Identifying Coronary Artery Calcification on Non-gated Computed Tomography Scans

Identifying Coronary Artery Calcification on Non-gated Computed Tomography Scans

Published on: August 28, 2018

Models were evaluated on stratified 70:30 held-out splits using balanced accuracy and macro-F1 metrics.

Main Results:

GLM-5.1 achieved a balanced accuracy of 0.918 and macro-F1 of 0.838, outperforming the majority baseline and BioClinicalBERT.
GLM-5.1's performance was not significantly different from RF-ROS (p=0.82) or BioClinicalBERT (p=0.20).
GLM-5.1 correctly classified all 8 held-out interstitial lung disease CT cases.

Conclusions:

Rule-augmented GLM-5.1 prompting is a feasible approach for radiology protocol selection in narrow, single-center tasks.
LLM performance was comparable to imbalance-aware classical machine learning methods.
Findings suggest local rule encoding is a viable adaptation strategy for LLMs, rather than a complete replacement for classical ML or human oversight.