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

• URL: http://arxiv.org/abs/2506.04450v2
• Date: Wed, 06 Aug 2025 20:17:58 GMT
• Title: Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification
• Authors: Payel Bhattacharjee, Fengwei Tian, Geoffrey D. Rubin, Joseph Y. Lo, Nirav Merchant, Heidi Hanson, John Gounley, Ravi Tandon,
• Abstract summary: This study proposes a framework for fine-tuning large language models (LLMs) with differential privacy (DP) to perform multi-abnormality classification on radiology report text.<n>We used 50,232 radiology reports from the publicly available MIMIC-CXR chest radiography and CT-RATE computed tomography datasets.
• Score: 6.649039909154803
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Purpose: This study proposes a framework for fine-tuning large language models (LLMs) with differential privacy (DP) to perform multi-abnormality classification on radiology report text. By injecting calibrated noise during fine-tuning, the framework seeks to mitigate the privacy risks associated with sensitive patient data and protect against data leakage while maintaining classification performance. Materials and Methods: We used 50,232 radiology reports from the publicly available MIMIC-CXR chest radiography and CT-RATE computed tomography datasets, collected between 2011 and 2019. Fine-tuning of LLMs was conducted to classify 14 labels from MIMIC-CXR dataset, and 18 labels from CT-RATE dataset using Differentially Private Low-Rank Adaptation (DP-LoRA) in high and moderate privacy regimes (across a range of privacy budgets = {0.01, 0.1, 1.0, 10.0}). Model performance was evaluated using weighted F1 score across three model architectures: BERT-medium, BERT-small, and ALBERT-base. Statistical analyses compared model performance across different privacy levels to quantify the privacy-utility trade-off. Results: We observe a clear privacy-utility trade-off through our experiments on 2 different datasets and 3 different models. Under moderate privacy guarantees the DP fine-tuned models achieved comparable weighted F1 scores of 0.88 on MIMIC-CXR and 0.59 on CT-RATE, compared to non-private LoRA baselines of 0.90 and 0.78, respectively. Conclusion: Differentially private fine-tuning using LoRA enables effective and privacy-preserving multi-abnormality classification from radiology reports, addressing a key challenge in fine-tuning LLMs on sensitive medical data.

Related papers

• FedGIN: Federated Learning with Dynamic Global Intensity Non-linear Augmentation for Organ Segmentation using Multi-modal Images [0.0]
  Medical image segmentation plays a crucial role in AI-assisted diagnostics, surgical planning, and treatment monitoring.<n>We propose FedGIN, a Federated Learning framework that enables multimodal organ segmentation without sharing raw patient data.
  arXiv  Detail & Related papers  (2025-08-07T08:16:35Z)
• Comparative analysis of privacy-preserving open-source LLMs regarding extraction of diagnostic information from clinical CMR imaging reports [0.49998148477760973]
  We evaluated nine open-source Large Language Models (LLMs) on their ability to identify diagnoses and classify patients into various cardiac diagnostic categories.<n>Google's Gemma2 model achieved the highest average F1 score of 0.98, followed by Qwen2.5:32B and DeepseekR1-32B with F1 scores of 0.96 and 0.95, respectively.
  arXiv  Detail & Related papers  (2025-05-29T11:25:10Z)
• A Demographic-Conditioned Variational Autoencoder for fMRI Distribution Sampling and Removal of Confounds [49.34500499203579]
  We create a variational autoencoder (VAE)-based model, DemoVAE, to decorrelate fMRI features from demographics. We generate high-quality synthetic fMRI data based on user-supplied demographics.
  arXiv  Detail & Related papers  (2024-05-13T17:49:20Z)
• Quantifying uncertainty in lung cancer segmentation with foundation models applied to mixed-domain datasets [6.712251433139412]
  Medical image foundation models have shown the ability to segment organs and tumors with minimal fine-tuning.<n>These models are typically evaluated on task-specific in-distribution (ID) datasets.<n>We introduce a comprehensive set of computationally fast metrics to evaluate the performance of multiple foundation models trained with self-supervised learning (SSL)<n>SMIT produced the highest F1-score (LRAD: 0.60, 5Rater: 0.64) and lowest entropy (LRAD: 0.06, 5Rater: 0.12), indicating higher tumor detection rate and confident segmentations.
  arXiv  Detail & Related papers  (2024-03-19T19:36:48Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• Source-Free Collaborative Domain Adaptation via Multi-Perspective Feature Enrichment for Functional MRI Analysis [55.03872260158717]
  Resting-state MRI functional (rs-fMRI) is increasingly employed in multi-site research to aid neurological disorder analysis. Many methods have been proposed to reduce fMRI heterogeneity between source and target domains. But acquiring source data is challenging due to concerns and/or data storage burdens in multi-site studies. We design a source-free collaborative domain adaptation framework for fMRI analysis, where only a pretrained source model and unlabeled target data are accessible.
  arXiv  Detail & Related papers  (2023-08-24T01:30:18Z)
• Exploratory Analysis of Federated Learning Methods with Differential Privacy on MIMIC-III [0.7349727826230862]
  Federated learning methods offer the possibility of training machine learning models on privacy-sensitive data sets. We present an evaluation of the impact of different federation and differential privacy techniques when training models on the open-source MIMIC-III dataset.
  arXiv  Detail & Related papers  (2023-02-08T17:27:44Z)
• Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging [47.99192239793597]
  We evaluated the effect of privacy-preserving training of AI models regarding accuracy and fairness compared to non-private training. Our study shows that -- under the challenging realistic circumstances of a real-life clinical dataset -- the privacy-preserving training of diagnostic deep learning models is possible with excellent diagnostic accuracy and fairness.
  arXiv  Detail & Related papers  (2023-02-03T09:49:13Z)
• Differentially Private Estimation of Heterogeneous Causal Effects [9.355532300027727]
  We introduce a general meta-algorithm for estimating conditional average treatment effects (CATE) with differential privacy guarantees. Our meta-algorithm can work with simple, single-stage CATE estimators such as S-learner and more complex multi-stage estimators such as DR and R-learner.
  arXiv  Detail & Related papers  (2022-02-22T17:21:18Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity [77.78624443410216]
  We propose improved FDAM algorithms for detecting heterogeneous chest data. A result of this paper is that the communication of the proposed algorithm is strongly independent of the number of machines and also independent of the accuracy level. Experiments have demonstrated the effectiveness of our FDAM algorithm on benchmark datasets and on medical chest Xray images from different organizations.
  arXiv  Detail & Related papers  (2021-02-09T04:05:19Z)
• Privacy Preserving Recalibration under Domain Shift [119.21243107946555]
  We introduce a framework that abstracts out the properties of recalibration problems under differential privacy constraints. We also design a novel recalibration algorithm, accuracy temperature scaling, that outperforms prior work on private datasets.
  arXiv  Detail & Related papers  (2020-08-21T18:43:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.