Supplement: SCH: Enabling Data Outsourcing and Sharing for AI-powered Parkinson's Research

补充：SCH：为人工智能驱动的帕金森病研究提供数据外包和共享

• 批准号: 10594084
• 负责人: Shigang Chen
• 金额: $ 28.13万
• 依托单位: UNIVERSITY OF FLORIDA
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-03 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10594084
• 关键词: Artificial Intelligence; Biomedical Computing; Biomedical Research; Case Study; Cloud Computing; Communities; Complex; Data; Data Set; Diagnosis; Disease; Ensure; Evaluation; Foundations; Machine Learning; Manuscripts; Masks; Medical; Methods; Modeling; Modernization; Neural Network Simulation; Noise; Outcome; Outsourcing; Parkinson Disease; Parkinsonian Disorders; Patient Data Privacy; Patients; Performance; Privacy; Process; Public Health Informatics; Randomized; Readiness; Research; Technology; Training; Universities; Visit; accurate diagnosis; artificial neural network; base; biomedical informatics; cloud based; cost; data privacy; data sharing; deep learning; digital; disease diagnosis; experimental study; improved; mobile computing; novel; privacy protection; random forest; theories

Supplement Project Summary What does Project R01 LM014027-01 do? Artificial intelligence holds the promise of transforming data-driven biomedical research and computational health informatics for more accurate diagnosis and better treatment at lower cost. In the meantime, modern digital and mobile technologies make it much easier to collect information from patients in large scale. While “big” medical data offers unprecedented opportunities of building deep-learning artificial neural network (ANN) models to advance the research of complex diseases such as Parkinson's disease (PD), it also presents unique challenges to patient data privacy. This project will develop novel data masking technologies based on randomized orthogonal transformation to enable AI-computation outsourcing and data sharing, with the following two aims: 1) Perform two experimental studies of training ANN models with data masking in the HiperGator cloud for PD prediction and Parkinsonism diagnosis; 2) establish the theoretical foundation on data privacy, inference accuracy, and training performance of the ANN models used in the experimental studies. Why do we make this supplement request? Dr. Aidong Adam Ding from Northeastern University visited us in Summer 2022. Together we produced a manuscript that expanded our data masking method with noise addition to achieve differential privacy (DiP) when we outsource medical data to the cloud for AI model training. This is a significant advance that goes beyond the originally proposed technical approaches; yet it remains in the scope of the research plan. Therefore, we request a supplement project that utilizes our new DiP method to transform two PD data sets for guaranteed differential privacy and make them AI-ready for cloud-based machine learning studies. Our analysis has showed that the new DiP method could be improved with much less noise addition, which would result in much better model accuracy. We plan to bring Dr. Ge Han from Towson University into the team. His expertise in random forests and perturbations could help us reduce the noise. The proposed supplement tasks for the two aims of Project R01 LM014027-01 are below. Supplement Task to Aim 1: Produce two sharable PD data sets with differential privacy and perform a machine learning case study on the DiP-protected data for AI-readiness evaluation. We will process our two PD data sets with the new DiP method to ensure differential privacy. We will perform an experimental study over the two data sets to evaluate PD-diagnosis models learned from the DiP-protected data and to quantify the tradeoff between model accuracy and privacy protection, which helps us determine the best configuration of the privacy-protected data that we will share with the community. Supplement Task to Aim 2: Improve the DiP Method and Enhance the Quality of AI-Ready, DiP- Protected Data. We will refine the DiP method for less noise addition, which helps improve the accuracy of ML/AI models trained from the DiP-protected data.

补充项目摘要 项目R01 LM014027-01的作用是什么？Artifi社会情报机构有望实现 数据驱动的生物医学研究和计算健康信息学，可实现更准确的诊断和 以更低的成本获得更好的治疗。与此同时，现代数字和移动技术使它 更容易大规模收集患者的信息。而“海量”的医疗数据提供了前所未有的 建立深度学习人工神经网络(ANN)模型推进研究的机遇 除了帕金森氏病(PD)等复杂疾病外，它还对患者数据隐私提出了独特的挑战。 该项目将开发基于随机正交变换的新型数据掩蔽技术 为了实现人工智能计算外包和数据共享，有以下两个目标：1)执行两个 HiPerGator云带数据掩蔽训练神经网络模型预测局部放电的实验研究 和帕金森氏症的诊断；2)建立了数据保密性、推理准确性和 实验研究中使用的神经网络模型的训练性能。 我们为何提出这项补充要求？东北大学丁爱东博士来访 2022年夏天的美国。我们一起制作了一份手稿，用噪声扩展了我们的数据掩蔽方法 此外，当我们将医疗数据外包到云以用于AI模型时，还可以实现差异隐私(DIP) 训练。这是一个明显的fi不能超越最初提出的技术方法的进步；然而它 仍在研究计划的范围内。因此，我们要求一个补充项目，利用我们的新 DIP方法转换两个PD数据集，以确保差异隐私并使它们为AI做好准备 基于云的机器学习研究。我们的分析表明，新的浸渍方法可以改进。 添加的噪声要少得多，这将导致更好的模型精度。我们计划把葛医生带到 来自陶森大学的韩加入了这个团队。他在随机森林和扰动方面的专业知识可以帮助我们 降低噪音。R01项目LM014027-01两个目标的拟议补充任务如下。 补充目标1的任务：生成两个具有不同隐私的可共享PD数据集，并执行 用于人工智能准备评估的DIP保护数据的机器学习案例研究。我们将处理我们的 使用新的DIP方法的两个PD数据集，以确保差异隐私。我们将进行一项实验 对两个数据集的研究，以评估从DIP保护数据中学习的PD诊断模型 量化模型准确性和隐私保护之间的权衡，这有助于我们确定最佳 我们将与社区共享受隐私保护的数据的CONfiGATURE。 目标2的补充任务：改进DIP方法，提高AI-Ready、DIP-2的质量 受保护数据。我们将重新fiNe DIP方法，以减少噪声添加，这有助于提高精度 从受DIP保护的数据训练的ML/AI模型。