Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification.

Payel Bhattacharjee1, Fengwei Tian1, Geoffrey D Rubin2

  • 1Department of Electrical and Computer Engineering, The University of Arizona, Tucson, AZ 85719, USA.

IEEE Access : Practical Innovations, Open Solutions
|June 1, 2026
PubMed
Summary

Related Concept Videos

Radiological Investigation III: Pulmonary Angiogram and PET Scan01:13

Radiological Investigation III: Pulmonary Angiogram and PET Scan

Radiological investigations are paramount in the diagnosis and management of various pulmonary diseases. Two essential investigations are the Pulmonary Angiogram and the Positron Emission Tomography (PET) Scan.
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and the...

You might also read

Related Articles

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

Sort by
Same author

Mitigating Algorithmic Bias in Cancer Site Classification Models.

JCO clinical cancer informatics·2026
Same author

Utility of the virtual imaging trials methodology for objective characterization of AI systems and training data.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Associations between Ambient Air Pollution and Cardiovascular and Respiratory Healthcare Visits in Adolescent and Young Adult Cancer Survivors.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026
Same author

Cross-National Radiomics Validation Using Mammography to Predict Occult Invasion in Ductal Carcinoma in Situ.

Radiology·2025
Same author

Improving annotation efficiency for fully labeling a breast mass segmentation dataset.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

The Duke Lung Cancer Screening (DLCS) Dataset: A Reference Dataset of Annotated Low-Dose Screening Thoracic CT.

Radiology. Artificial intelligence·2025
Same journal

A Multi-Head Attention Transformer Model for Wearable in Situ Fall Detection.

IEEE access : practical innovations, open solutions·2026
Same journal

Validating Single-Camera Pose Estimation Against Multi-Camera Motion Capture for Accessible Biomechanical Assessment.

IEEE access : practical innovations, open solutions·2026
Same journal

Radio-Frequency Toroid Susceptometry of Magnetic Nanoparticles: What Goes Around Comes Around.

IEEE access : practical innovations, open solutions·2026
Same journal

Cross-Architecture Knowledge Distillation for Histopathological Image Analysis.

IEEE access : practical innovations, open solutions·2026
Same journal

Mislabel Identification Using Transfer Learning-Based Ensemble Method.

IEEE access : practical innovations, open solutions·2026
Same journal

Deep Learning for Path Loss Prediction at 7 GHz in Urban Environment.

IEEE access : practical innovations, open solutions·2026
See all related articles
This summary is machine-generated.

This study introduces a differentially private fine-tuning method for Large Language Models (LLMs) to classify multiple abnormalities in radiology reports. The approach, DP-LoRA, protects patient data privacy while maintaining high classification accuracy, demonstrating effective privacy-utility trade-offs.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence
  • Natural Language Processing

Background:

  • Large Language Models (LLMs) are increasingly used in healthcare for tasks like disease diagnosis and abnormality classification from medical reports.
  • Fine-tuning LLMs on private patient data enhances accuracy but poses significant privacy risks due to potential data memorization and extraction.
  • Privacy-preserving methods for fine-tuning LLMs in medical text classification, particularly for multi-abnormality classification, are underexplored.

Purpose of the Study:

  • To propose and evaluate a novel differentially private (DP) fine-tuning approach for LLMs to perform multi-abnormality classification on text-based radiology reports.
  • To address the critical need for privacy preservation in applying LLMs to sensitive medical data.
  • To investigate the privacy-utility trade-off in DP fine-tuning for medical text classification.
Keywords:
Differential privacychest radiology reportslarge language modelsmulti-abnormality classificationnatural language processing

Related Experiment Videos

Main Methods:

  • Developed a differentially private (DP) fine-tuning framework using Low Rank Adaptation (LoRA) for LLMs.
  • Leveraged DP optimization techniques to fine-tune LLMs on local patient data, mitigating risks of sensitive information leakage.
  • Utilized labels generated by a larger LLM to fine-tune a smaller LLM for accelerated inference while adhering to privacy constraints.

Main Results:

  • The proposed DP-LoRA framework achieved high performance on the MIMIC-CXR dataset, with weighted F1-scores up to 0.89 under moderate privacy budgets (ϵ = 10).
  • Performance closely approached that of non-private LoRA (0.90) and full fine-tuning (0.96), indicating minimal utility loss.
  • Demonstrated the efficacy of the DP fine-tuning method across varying privacy regimes and datasets (MIMIC-CXR, CT-RATE).

Conclusions:

  • The DP-LoRA approach effectively enables privacy-preserving multi-abnormality classification from radiology reports using LLMs.
  • Strong privacy protection can be achieved with only moderate performance degradation, making LLMs more viable for sensitive healthcare applications.
  • This work represents the first study to incorporate DP fine-tuning of LLMs for multi-abnormality classification in text-based radiology reports.