SCH: Dementia Early Detection for Under-represented Populations via Fair Multimodal Self-Supervised Learning

SCH：通过公平的多模式自我监督学习对代表性不足的人群进行痴呆症早期检测

• 批准号: 10816864
• 负责人: Arjun Vijay Masurkar
• 金额: $ 28.64万
• 依托单位: NEW YORK UNIVERSITY SCHOOL OF MEDICINE
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10816864
• 关键词: Address; Algorithm Design; Algorithms; Alzheimer disease detection; Alzheimer' s Disease; Alzheimer' s disease related dementia; American; Black Populations; Calibration; Classification; Clinic; Clinical; Clinical Data; Clinical Trials; Cognitive; Cohort Studies; Complex; Data; Data Set; Data Sources; Dementia; Detection; Diagnosis; Disease; Early Diagnosis; Electronic Health Record; Ensure; Ethnic Population; Family; Health; Hispanic Populations; Image; Impaired cognition; Learning; Longitudinal cohort; Machine Learning; Magnetic Resonance Imaging; Measures; Medical; Methodology; Methods; Modeling; Monitor; Patients; Performance; Population; Population Heterogeneity; Positron-Emission Tomography; Primary Care; Research; Sampling; Scheme; Target Populations; Techniques; Training; Underrepresented Populations; Woman; Work; clinical biomarkers; cognitive testing; cohort; comorbidity; complex data; ethnic minority; fluorodeoxyglucose positron emission tomography; high risk; human old age (65+); imaging biomarker; learning strategy; multimodal data; multimodality; neuroimaging; novel; patient subsets; primary care setting; racial minority; racial population; supervised learning; tool

An estimated 6.2 million Americans aged 65 and older are living with Alzheimer's Disease and its Related Dementias (AD/ADRD) in 2022. Of these, two thirds are women. Blacks and Hispanics have been shown to have a higher risk of AD/ADRD compared with whites. The vast majority of diagnosis of AD/ADRD occurs in non- specialty settings such as primary care. But by 2019, only 16% of seniors were regularly screened for cognitive impairment in the primary care setting. Late diagnosis deprives patients and their families of the opportunity to receive anticipatory guidance, participate in clinical trials, or benefit from any potential disease-modifying therapy. Leveraging data sources such as MRI imaging and electronic health records (EHR) can potentially allow scalable monitoring of cognitive health and early detection of AD/ADRD. However, existing tools are built with mostly white educated populations without significant comorbidities. Patients represented in real-world clinics are more diverse and medically complex. However, working with such data requires solving several core machine learning challenges. Here, we propose a set of novel methods that enable us to use large real-world clinical multi-modal datasets for the purpose of building robust, unbiased, fair and accurate models for early AD/ADRD detection for diverse populations, with an emphasis on under-represented groups. Specifically, we propose to develop novel self-supervised learning techniques that learn robust representations from large unlabeled datasets which can then be used to design algorithmically fair models. Our proposal offers new objective functions to leverage multi-modality (pairing of T1, FLAIR and PET MRI images and EHR data) as an asset to better train models. This work can extend beyond AD/ADRD diagnosis to diseases which have imaging and clinical biomarkers.

估计有65岁及65岁以上的美国人患有阿尔茨海默氏病及其相关的痴呆症（AD/ADRD）。其中，其中三分之二是女性。与白人相比，黑人和西班牙裔的AD/ADRD风险更高。绝大多数AD/ADRD诊断都发生在非专业环境中，例如初级保健。但是到2019年，只有16％的老年人经常在初级保健环境中进行认知障碍。晚期诊断剥夺了患者及其家人获得预期指导，参加临床试验或受益于任何潜在疾病改良疗法的机会。利用MRI成像和电子健康记录（EHR）之类的数据源可以潜在地允许对认知健康和AD/ADRD的早期检测。但是，现有的工具是在没有大量合并症的情况下大多是白人教育的人群。在现实世界诊所代表的患者更加多样化和医学上的复杂。但是，使用此类数据需要解决几个核心机器学习挑战。在这里，我们提出了一组新型方法，使我们能够使用大型现实世界的临床多模式数据集，目的是为了构建强大的，公正的，公平的，公平的和准确的模型，以用于早期的AD/ADRD检测，以重点介绍不足的群体。具体而言，我们建议开发新颖的自我监督学习技术，这些学习技术从大型未标记的数据集中学习强大的表示，然后可以用来设计算法上公平的模型。我们的建议提供了新的目标功能，以利用多模式（T1，FLAIR和PET MRI图像以及EHR数据的配对）作为更好的火车模型的资产。这项工作可以扩展到具有成像和临床生物标志物的疾病的广告/ADRD诊断。