在机器学习领域，特定领域的标注数据是训练有效模型的宝贵资源。但在医疗领域，这类数据通常包含个人健康信息（Personal Health Information, PHI），引发了严重的隐私担忧。围绕PHI的严格法规限制了医疗数据集的获取与共享，给致力于开发先进机器学习模型的研究者和从业者带来了巨大挑战。本文提出了一种“克隆”含PHI数据集的新方法。该方法确保克隆后的数据集保留原始数据的核心特征与效用，同时不会损害患者隐私。通过利用差分隐私技术和一种新型微调任务，我们的方法生成的数据集不含可识别信息，同时保留了模型训练所需的统计特性。我们开展了效用测试，评估在克隆数据集上训练的机器学习模型的性能。结果表明，我们的克隆数据集不仅符合隐私标准，而且与在传统匿名化数据集上训练的模型相比，还能提升模型性能。这项工作为机器学习领域中敏感医疗数据的合规有效利用提供了可行方案，有助于推动医学研究进展和鲁棒预测模型的开发。
英文摘要：
In the field of machine learning, domain-specific annotated data is an invaluable resource for training effective models. However, in the medical domain, this data often includes Personal Health Information (PHI), raising significant privacy concerns. The stringent regulations surrounding PHI limit the availability and sharing of medical datasets, which poses a substantial challenge for researchers and practitioners aiming to develop advanced machine learning models. In this paper, we introduce a novel method to "clone" datasets containing PHI. Our approach ensures that the cloned datasets retain the essential characteristics and utility of the original data without compromising patient privacy. By leveraging differential-privacy techniques and a novel fine-tuning task, our method produces datasets that are free from identifiable information while preserving the statistical properties necessary for model training. We conduct utility testing to evaluate the performance of machine learning models trained on the cloned datasets. The results demonstrate that our cloned datasets not only uphold privacy standards but also enhance model performance compared to those trained on traditional anonymized datasets. This work offers a viable solution for the ethical and effective utilization of sensitive medical data in machine learning, facilitating progress in medical research and the development of robust predictive models.
Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
University of Notre Dame（圣母大学）；University of Pennsylvania（宾夕法尼亚大学）；Dartmouth College（达特茅斯学院）；Georgia Institute of Technology（佐治亚理工学院）；George Mason University（乔治梅森大学）
Generative clinical time series models trained on moderate amounts of patient data are privacy preserving
Mathematical Modelling and Data Analysis Department, Physikalisch-Technische Bundesanstalt (PTB)（物理技术联邦机构（PTB）数学建模与数据分析部门）；Institute of Medical Informatics, Charité – Universitätsmedizin Berlin（柏林查理医院医学信息学研究所）
Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg（埃朗根-纽伦堡弗里德里希-亚历山大大学模式识别实验室）；Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen（亚琛大学诊断与介入放射科）；Department of Radiology, Stanford University（斯坦福大学放射科）；Department of Urology, Stanford University（斯坦福大学泌尿科）
Secure Multi-Modal Data Fusion in Federated Digital Health Systems via MCP
School of Information, Computer, and Communication Technology（信息、计算机与通信技术学院）；Sirindhorn International Institute of Technology, Thammasat University（泰国朱拉安吞国际技术学院，泰国 Thammasat 大学）
DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Texts
Technical University of Berlin（柏林工业大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）
De-identification is not enough: a comparison between de-identified and synthetic clinical notes
Department of Computer Science, University of Manitoba（曼尼托巴大学计算机科学系）；McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心麦克威廉姆斯生物医学信息学院）
Retrieval-Reasoning Large Language Model-based Synthetic Clinical Trial Generation
Institute for Clarity in Documentation（清晰文档研究所）；Inria Paris-Rocquencourt（巴黎- Rocquencourt 国家信息与自动化研究所）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒实验室）；University of Chicago（芝加哥大学）；Stanford University（斯坦福大学）；Purdue University（普渡大学）；University of Southern California（南加州大学）
Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Research
Infmedix, Co., Ltd.（Infmedix公司）；Department of Transdisciplinary Studies, Seoul National University（首尔国立大学跨学科研究系）；Healthcare AI Research Institute, Seoul National University Hospital（首尔国立大学医院医疗人工智能研究所）；Department of Medicine, Seoul National University College of Medicine（首尔国立大学医学院医学系）；Department of Transdisciplinary Medicine, Seoul National University Hospital（首尔国立大学医院跨学科医学系）；Department of Radiology, Massachusetts General Hospital and Harvard Medical School（麻省总医院放射科及哈佛医学院）
Self-Prompting Small Language Models for Privacy-Sensitive Clinical Information Extraction
McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston（德克萨斯大学健康科学中心休斯顿分校麦克威廉斯生物医学信息学学院）；School of Public Health, The University of Texas Health Science Center at Houston（德克萨斯大学健康科学中心休斯顿分校公共卫生学院）；School of Dentistry, The University of Texas Health Science Center at Houston（德克萨斯大学健康科学中心休斯顿分校牙科学院）；Willamette Dental and Skourtes Institute（威廉特牙科与斯库尔特斯研究所）
Small Language Models for Privacy-Preserving Clinical Information Extraction in Low-Resource Languages
Student Research Committee Isfahan University of Medical Sciences（伊斯法罕医学科学大学学生研究委员会）；Department of Emergency Medicine Isfahan University of Medical Sciences（伊斯法罕医学科学大学急诊医学科）
Comparative analysis of privacy-preserving open-source LLMs regarding extraction of diagnostic information from clinical CMR imaging reports
The D-Lab, Department of Precision Medicine, GROW - Research Institute for Oncology and Reproduction, Maastricht University（D实验室，精准医学系，GROW癌症与生殖研究研究所，马斯特里赫特大学）；Division of Cardiovascular Imaging, Department of Cardiology I, University Hospital Münster（心血管影像科，心内科第一部门，穆恩斯特大学医院）
Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models
MedVisAI Lab, Singapore（新加坡MedVisAI实验室）；Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, China（中国上海交通大学医学院瑞金医院）；Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore（新加坡南洋理工大学Lee Kong Chian医学院）
Privacy-Preserving Local Language Models for Longitudinal Data Retrieval in Chronic Dermatologic Disease: Implementation in Pemphigus Patients
Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, Imperial College London（系统医学系，代谢、消化与生殖部，帝国理工学院伦敦分校）；Department of Dermatology and Venereology, Istanbul Research and Training Hospital（皮肤科与性病科，伊斯坦布尔研究与培训医院）；Department of Dermatology and Venereology, Istanbul Medeniyet University（皮肤科与性病科，伊斯坦布尔梅德尼yet大学）；Department of Dermatology and Venereology, Istanbul Medicana Atakoy Hospital（皮肤科与性病科，伊斯坦布尔Medicana阿塔科伊医院）
Domain-Adapted Small Language Models for Reliable Clinical Triage
Department of Computer Science, Virginia Tech, Blacksburg, VA, US（弗吉尼亚理工学院计算机科学系，弗吉尼亚理工学院，布莱克斯堡，VA，美国）；Children’s National Hospital, Washington DC, USA（儿童医学中心，华盛顿特区，美国）
DeIDClinic: A Risk-Aware Pseudonymization Framework for Clinical Text De-identification and Re-identification Risk Assessment
University of Manchester（曼彻斯特大学）；Leiden Institute of Advanced Computer Science (LIACS)（莱顿先进计算机科学研究所）；Leiden University（莱顿大学）；Biomedical Data Sciences, Leiden University Medical Center（莱顿大学医学中心生物医学数据科学）
Preserving Privacy, Increasing Accessibility, and Reducing Cost: An On-Device Artificial Intelligence Model for Medical Transcription and Note Generation
