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

基本信息

项目摘要

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.
据估计,2022年,65岁及以上的美国人中有620万人患有阿尔茨海默病及其相关痴呆(AD/ADRD)。其中,三分之二是女性。与白人相比,黑人和西班牙裔患AD/ADRD的风险更高。绝大多数AD/ADRD的诊断发生在非专科环境中,如初级保健。但到2019年,只有16%的老年人在初级保健环境中定期接受认知障碍筛查。延迟诊断剥夺了患者及其家人接受前瞻性指导、参与临床试验或受益于任何潜在的疾病修正治疗的机会。利用核磁共振成像和电子健康记录(EHR)等数据源,有可能实现认知健康的可扩展监控和AD/ADRD的早期检测。然而,现有的工具主要是与受过教育的白人人口一起构建的,没有显著的共生性。现实世界诊所中的患者更加多样化,医学上也更加复杂。然而,处理这样的数据需要解决几个核心的机器学习挑战。在这里,我们提出了一套新的方法,使我们能够使用真实世界的大型临床多模式数据集来构建稳健、无偏倚、公平和准确的模型,用于不同人群的早期AD/ADRD检测,重点是代表性不足的群体。具体地说,我们建议开发新的自监督学习技术,该技术从大型未标记数据集中学习稳健的表示,然后可以用于设计算法公平的模型。我们的提案提供了新的目标函数,以利用多模式(T1、FLAIR和PET MRI图像和EHR数据的配对)作为资产,以更好地培训模型。这项工作可以从AD/ADRD诊断扩展到具有成像和临床生物标记物的疾病。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Arjun Vijay Masurkar其他文献

Arjun Vijay Masurkar的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Arjun Vijay Masurkar', 18)}}的其他基金

Differential impact of Alzheimer disease on neuronal subpopulations in dorsal hippocampal CA1
阿尔茨海默病对背侧海马 CA1 神经元亚群的不同影响
  • 批准号:
    10213474
  • 财政年份:
    2021
  • 资助金额:
    $ 28.64万
  • 项目类别:
Alterations in Ventral Hippocampal CA1 Processing as a Mechanism for Anxiety in Alzheimer’s Disease
腹侧海马 CA1 处理的改变作为阿尔茨海默病焦虑的机制
  • 批准号:
    10322745
  • 财政年份:
    2021
  • 资助金额:
    $ 28.64万
  • 项目类别:
Clinical Core
临床核心
  • 批准号:
    10643924
  • 财政年份:
    2020
  • 资助金额:
    $ 28.64万
  • 项目类别:
Clinical Core
临床核心
  • 批准号:
    10439579
  • 财政年份:
    2020
  • 资助金额:
    $ 28.64万
  • 项目类别:
Clinical Core
临床核心
  • 批准号:
    9921987
  • 财政年份:
  • 资助金额:
    $ 28.64万
  • 项目类别:
Core B. Clinical Core
核心 B. 临床核心
  • 批准号:
    9750578
  • 财政年份:
  • 资助金额:
    $ 28.64万
  • 项目类别:

相似海外基金

REU Site: Algorithm Design --- Theory and Engineering
REU网站:算法设计---理论与工程
  • 批准号:
    2349179
  • 财政年份:
    2024
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Standard Grant
REU Site: Quantum Machine Learning Algorithm Design and Implementation
REU 站点:量子机器学习算法设计与实现
  • 批准号:
    2349567
  • 财政年份:
    2024
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Standard Grant
Product structures theorems and unified methods of algorithm design for geometrically constructed graphs
几何构造图的乘积结构定理和算法设计统一方法
  • 批准号:
    23K10982
  • 财政年份:
    2023
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Algorithm Design in Strategic and Uncertain Environments
战略和不确定环境中的算法设计
  • 批准号:
    RGPIN-2016-03885
  • 财政年份:
    2022
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Discovery Grants Program - Individual
Human-Centered Algorithm Design for High Stakes Decision-Making in Public Services
以人为本的公共服务高风险决策算法设计
  • 批准号:
    DGECR-2022-00401
  • 财政年份:
    2022
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Discovery Launch Supplement
Human-Centered Algorithm Design for High Stakes Decision-Making in Public Services
以人为本的公共服务高风险决策算法设计
  • 批准号:
    RGPIN-2022-04570
  • 财政年份:
    2022
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Discovery Grants Program - Individual
Algorithm Design
算法设计
  • 批准号:
    CRC-2015-00122
  • 财政年份:
    2022
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Canada Research Chairs
Control Theory and Algorithm Design for Nonlinear Systems Based on Finite Dimensionality of Holonomic Functions
基于完整函数有限维的非线性系统控制理论与算法设计
  • 批准号:
    22K17855
  • 财政年份:
    2022
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
Scalable Algorithm Design for Unbiased Estimation via Couplings of Markov Chain Monte Carlo Methods
通过马尔可夫链蒙特卡罗方法耦合进行无偏估计的可扩展算法设计
  • 批准号:
    2210849
  • 财政年份:
    2022
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Continuing Grant
Modern mathematical models of big data-driven problems in biological sequence analysis with applications to efficient algorithm design
生物序列分析中大数据驱动问题的现代数学模型及其在高效算法设计中的应用
  • 批准号:
    569312-2022
  • 财政年份:
    2022
  • 资助金额:
    $ 28.64万
  • 项目类别:
    Alexander Graham Bell Canada Graduate Scholarships - Doctoral
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了