Decentralized differentially-private methods for dynamic data release and analysis

用于动态数据发布和分析的去中心化差分隐私方法

• 批准号: 10740597
• 负责人: Xiaoqian Jiang
• 金额: $ 61.37万
• 依托单位: YALE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-01-01 至 2025-12-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10740597
• 关键词: Acceleration; Acute; Address; Algorithms; Artificial Intelligence; COVID-19; COVID-19 patient; COVID-19 risk; Calibration; California; Cessation of life; Chronic; Chronic Disease; Clinical; Communication; Consent; Country; County; Data; Data Analyses; Data Discovery; Data Linkages; Decentralization; Development; Disease; Equilibrium; Evaluation; Event; Genome; Geography; Goals; Health; Health Insurance Portability and Accountability Act; Health Sciences; Health protection; Healthcare; Heterogeneity; Hospitalization; Image; Incidence; Institution; Intervention; Knowledge; Laboratories; Learning; Linear Models; Link; Literature; Marketing; Medical center; Methodology; Methods; Modality; Modeling; Morbidity - disease rate; Outcome; Parents; Patient-Focused Outcomes; Patients; Pattern; Performance; Persons; Phase; Phenotype; Population; Predictive Analytics; Privacy; Privatization; Publishing; Reaction; Records; Recovery; Registries; Research; Research Personnel; Resolution; Resource Allocation; Resources; Running; Sample Size; Security; Site; Source; Structure; Techniques; Testing; Texas; Time; Training; Underrepresented Minority; Universities; Visit; analytical tool; artificial intelligence algorithm; clinical decision support; clinical decision-making; combat; combinatorial; cost; data dissemination; data integration; data privacy; data sharing; design; distributed data; federated data; federated learning; future outbreak; hospital readmission; individual patient; large datasets; model building; mortality; multimodality; new pandemic; novel; novel strategies; outcome prediction; pandemic disease; patient privacy; predictive modeling; privacy preservation; privacy protection; profiles in patients; repository; software development; statistical learning; supervised learning; transmission process; unsupervised learning; virtual

Project Summary Large data sets are important in the development and evaluation of artificial intelligence (AI) and statistical learning models to predict morbidity, mortality, and other important health outcomes. Healthcare institutions are stewards of their patients’ data, and want to contribute to the development, evaluation, and utilization of predictive analytics tools. However, they also know that simple “de-identification” per HIPAA rules is not sufficient to protect patient privacy. Additionally, other factors such as protection of market share, lack of control about who uses shared data for what purposes, and concerns about patients’ reactions to having their data shared without explicit consent make initiatives such as certain registries and centralized repositories difficult to implement. We have shown that it is possible to decompose algorithms so that they can run on data that stays at each healthcare center, thus mitigating the concerns about control and potential misuse. In the first phase of this project, we concentrated on demonstrating the accuracy and performance of these algorithms for the study of chronic diseases in which (1) acquisition of new knowledge about the condition is slow (i.e., the disease is well understood, so scientific discoveries are not being published at a rapid pace); and (2) the incidence and presentation of the disease do not vary dramatically from place to place, and from person to person. In this competitive renewal, we propose to develop decentralized predictive models that meet all requirements for chronic diseases, but the methods are also applicable to rapidly evolving acute conditions such as COVID-19. We propose new approaches to deal with sites that may be missing certain patient profiles or certain variables but can still participate in model learning, evaluation and implementation. These new AI algorithms will permit supervised and unsupervised learning across institutions, using data from multiple modalities (e.g., imaging, genomes, laboratory tests), and will allow privacy-protecting record linkage. We will test these algorithms and approaches in data from three highly diverse medical centers across the US: Emory University in Atlanta, University of Texas Health Science Center at Houston, and University of California, San Diego.

项目摘要 大型数据集在人工智能（AI）的开发和评估中非常重要， 统计学习模型，以预测发病率，死亡率和其他重要的健康结果。 医疗机构是患者数据的管理者，并希望为 开发、评估和利用预测分析工具。然而，他们也知道， 根据HIPAA规则，简单的“去识别”不足以保护患者隐私。 此外，其他因素，如保护市场份额，缺乏控制谁使用， 出于什么目的共享数据，以及对患者对其数据共享的反应的担忧 在没有明确同意的情况下， 难以实施。我们已经证明，有可能分解算法，使它们 可以在每个医疗中心的数据上运行，从而减轻了对控制的担忧 潜在的滥用。在这个项目的第一阶段，我们集中展示了 这些算法用于慢性疾病研究的准确性和性能，其中（1） 获得关于病症的新知识是缓慢的（即，人们对这种疾病已经很了解了，所以 科学发现没有以快速的速度发表）;（2）发病率和 疾病的表现并没有显着不同的地方，从人到人， 人.在这种竞争性更新中，我们建议开发分散的预测模型， 满足慢性病的所有要求，但这些方法也适用于快速发展的 如COVID-19等急性疾病。我们提出了新的方法来处理网站， 缺少某些患者概况或某些变量但仍然可以参与模型学习， 评价和执行。这些新的人工智能算法将允许监督和无监督 跨机构学习，使用来自多种模式的数据（例如，成像，基因组， 实验室测试），并将允许隐私保护记录链接。我们将测试这些算法 和方法的数据来自美国三个高度多样化的医疗中心：埃默里 亚特兰大大学、德克萨斯大学休斯顿健康科学中心和 加州，圣地亚哥。