Collaborative Research: NSF-CSIRO: HCC: Small: Understanding Bias in AI Models for the Prediction of Infectious Disease Spread

合作研究:NSF-CSIRO:HCC:小型:了解预测传染病传播的 AI 模型中的偏差

基本信息

  • 批准号:
    2302970
  • 负责人:
  • 金额:
    $ 12.39万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2023
  • 资助国家:
    美国
  • 起止时间:
    2023-04-01 至 2026-03-31
  • 项目状态:
    未结题

项目摘要

Artificial intelligence (AI) provides powerful techniques for understanding and prediction of complex systems such as modeling and predicting the spread of infectious diseases. Despite this, these predictive capabilities are rarely adopted by public health decision-makers to support policy interventions. One of the issues preventing their adoption is that AI methods are known to amplify the bias in the data they are trained on. This is especially problematic in infectious disease models which leverage available large and inherently biased spatiotemporal data. These biases may propagate through the modeling pipeline to decision-making, resulting in inequitable and ineffective policy interventions. This project investigates how the AI disease modeling pipeline can lead from biased data to biased predictions and to derive solutions that mitigate this bias in three aims: 1) creating an AI system to predict the spread of emerging infectious diseases in space and time, 2) simulating a population from which we will collect data often used as input for AI systems in a way that the bias is controlled, and 3) exploring links between bias in the collected data and the resulting bias in the AI model and deriving solutions for their mitigation. The project will enable AI-driven infectious disease models and predictions that will support fair and equitable decision-making and interventions. The project will enrich education and training related to ethical AI practices and will support professional development opportunities for early-career researchers, graduate, undergraduate, and high school students in the United States and Australia. In Aim 1, the team of researchers will use a self-supervised contrastive learning approach that uses mobility prediction as a pre-text task to learn representations of spatial regions. These representations can be used for infectious disease spread prediction given only very little infectious disease ground truth data. The investigators hypothesize that such a model is susceptible to data bias. Thus, in Aim 2, the team of researchers will leverage a large-scale agent-based simulation that will serve as a sandbox world for which we have perfect knowledge of and from which we can collect data and inject various types of bias. For Aim 3, the team of researchers will investigate how different types of simulated data bias leads to biased AI predictions by leveraging different metrics of fairness in AI and studying how these fairness measures can be incorporated into the AI optimization procedure to mitigate bias. By understanding, measuring, and mitigating bias inherent to traditional AI solutions, the project will enable accurate, scalable, and rapid predictions to support fair and equitable decision-making for pandemic prevention.This is a joint project between researchers in the United States and Australia funded by the Collaboration Opportunities in Responsible and Equitable AI under the U.S. NSF and the Australian Commonwealth Scientific and Industrial Research Organization (CSIRO).This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
人工智能 (AI) 为理解和预测复杂系统提供了强大的技术,例如建模和预测传染病的传播。尽管如此,公共卫生决策者很少采用这些预测能力来支持政策干预。阻碍其采用的问题之一是,众所周知,人工智能方法会放大其训练数据中的偏差。这在利用现有的大量且固有偏差的时空数据的传染病模型中尤其成问题。这些偏见可能会通过建模渠道传播到决策,导致不公平和无效的政策干预。该项目研究人工智能疾病建模流程如何从有偏见的数据导致有偏见的预测,并得出缓解这种偏见的解决方案,以实现三个目标:1)创建人工智能系统来预测新出现的传染病在空间和时间上的传播,2)模拟一个群体,我们将从中收集通常用作人工智能系统输入的数据,并以控制偏差的方式进行;3)探索收集的数据中的偏差与人工智能模型中由此产生的偏差之间的联系,并得出缓解其影响的解决方案。该项目将实现人工智能驱动的传染病模型和预测,从而支持公平公正的决策和干预措施。该项目将丰富与人工智能道德实践相关的教育和培训,并将为美国和澳大利亚的早期职业研究人员、研究生、本科生和高中生提供专业发展机会。 在目标 1 中,研究人员团队将使用自我监督的对比学习方法,该方法使用移动性预测作为前置任务来学习空间区域的表示。仅在很少的传染病地面实况数据的情况下,这些表示可用于传染病传播预测。研究人员假设这种模型容易受到数据偏差的影响。因此,在目标 2 中,研究人员团队将利用大规模的基于代理的模拟,该模拟将作为一个沙盒世界,我们对此有完美的了解,并且可以从中收集数据并注入各种类型的偏差。对于目标 3,研究人员团队将通过利用人工智能中的不同公平指标,研究不同类型的模拟数据偏差如何导致有偏差的人工智能预测,并研究如何将这些公平措施纳入人工智能优化程序中以减轻偏差。通过理解、测量和减轻传统人工智能解决方案固有的偏见,该项目将实现准确、可扩展和快速的预测,以支持公平公正的流行病预防决策。这是美国和澳大利亚研究人员之间的联合项目由美国 NSF 和澳大利亚联邦科学与工业研究组织 (CSIRO) 下的负责任和公平人工智能合作机会资助。该奖项反映了 NSF 的法定使命,经评估认为值得支持基金会的智力价值和更广泛的影响审查标准。

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 }}

Taylor Anderson其他文献

Building evidence for family group decision-making in child welfare: operationalizing the intervention
为儿童福利方面的家庭群体决策建立证据:实施干预措施
  • DOI:
    10.1080/15548732.2021.1891185
  • 发表时间:
    2021-03-07
  • 期刊:
  • 影响因子:
    1.6
  • 作者:
    M. Lalayants;D. DePanfilis;Lisa Merkel‐Holguin;Melinda J. Baldwin;Michele Cranwell Schmidt;J. Treinen;Danielle Zuñiga;Casey Mackereth;Taylor Anderson
  • 通讯作者:
    Taylor Anderson
GeoSim 2022 Workshop Report: The 5th ACM SIGSPATIAL International Workshop on Geospatial Simulation
GeoSim 2022 研讨会报告:第五届 ACM SIGSPATIAL 国际地理空间模拟研讨会
  • DOI:
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Joon;Taylor Anderson;Ashwin Shashidharan;Alexander Hohl
  • 通讯作者:
    Alexander Hohl
Bridging micro and macro: accurate registration of the BigBrain dataset with the MNI PD25 and ICBM152 atlases
连接微观和宏观:BigBrain 数据集与 MNI PD25 和 ICBM152 地图集的准确配准
  • DOI:
    10.1101/561118
  • 发表时间:
    2019-02-25
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yiming Xiao;J. C. Lau;J. C. Lau;Taylor Anderson;J. DeKraker;D. Collins;Terry M. Peters;Terry M. Peters;Ali R. Khan
  • 通讯作者:
    Ali R. Khan
Ileal lengthening through internal distraction: A novel procedure for ultrashort bowel syndrome
通过内部牵引延长回肠:一种治疗超短肠综合征的新方法
  • DOI:
    10.1016/j.yjpso.2024.100124
  • 发表时间:
    2024-01-01
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Aaron J Cunningham;Taylor Anderson;Claudia Mueller;Matias Bruzoni;James C Dunn
  • 通讯作者:
    James C Dunn
Prospective identification by neonatal screening of patients with guanidinoacetate methyltransferase deficiency.
通过新生儿筛查前瞻性鉴定胍基乙酸甲基转移酶缺乏症患者。
  • DOI:
    10.1016/j.ymgme.2021.07.012
  • 发表时间:
    2021-07-29
  • 期刊:
  • 影响因子:
    3.8
  • 作者:
    K. Hart;A. Rohrwasser;Heidi Wallis;Heather Golsan;Jianyin Shao;Taylor Anderson;Xiaoli Wang;Nicolas Szabo‐Fresnais;Mark A. Morrissey;Denise M. Kay;M. Wojcik;P. Galvin;N. Longo;M. Caggana;M. Pasquali
  • 通讯作者:
    M. Pasquali

Taylor Anderson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('Taylor Anderson', 18)}}的其他基金

Data-Driven Modeling to Improve Understanding of Human Behavior, Mobility, and Disease Spread
数据驱动建模以提高对人类行为、流动性和疾病传播的理解
  • 批准号:
    2109647
  • 财政年份:
    2021
  • 资助金额:
    $ 12.39万
  • 项目类别:
    Continuing Grant
RAPID: An Ensemble Approach to Combine Predictions from COVID-19 Simulations
RAPID:结合 COVID-19 模拟预测的集成方法
  • 批准号:
    2030685
  • 财政年份:
    2020
  • 资助金额:
    $ 12.39万
  • 项目类别:
    Standard Grant

相似国自然基金

SYNJ1蛋白片段通过促进突触蛋白NSF聚集在帕金森病发生中的机制研究
  • 批准号:
  • 批准年份:
    2022
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
NSF蛋白亚硝基化修饰所介导的GluA2 containing-AMPA受体膜稳定性在卒中后抑郁中的作用及机制研究
  • 批准号:
    82071300
  • 批准年份:
    2020
  • 资助金额:
    55 万元
  • 项目类别:
    面上项目
circ100783作为miR-34b分子海绵在铅暴露海马SNARE 复合体形成和突触囊泡释放中的机制研究
  • 批准号:
    81872577
  • 批准年份:
    2018
  • 资助金额:
    57.0 万元
  • 项目类别:
    面上项目
Mon1b 协同NSF调控早期内吞体膜融合的机制研究
  • 批准号:
    31671397
  • 批准年份:
    2016
  • 资助金额:
    67.0 万元
  • 项目类别:
    面上项目
美国国家科学基金会组织与管理的法律制度研究
  • 批准号:
    L0822107
  • 批准年份:
    2008
  • 资助金额:
    9.5 万元
  • 项目类别:
    专项基金项目

相似海外基金

Collaborative Research: NSF-AoF: CIF: Small: AI-assisted Waveform and Beamforming Design for Integrated Sensing and Communication
合作研究:NSF-AoF:CIF:小型:用于集成传感和通信的人工智能辅助波形和波束成形设计
  • 批准号:
    2326622
  • 财政年份:
    2024
  • 资助金额:
    $ 12.39万
  • 项目类别:
    Standard Grant
Collaborative Research: NSF-AoF: CIF: Small: AI-assisted Waveform and Beamforming Design for Integrated Sensing and Communication
合作研究:NSF-AoF:CIF:小型:用于集成传感和通信的人工智能辅助波形和波束成形设计
  • 批准号:
    2326621
  • 财政年份:
    2024
  • 资助金额:
    $ 12.39万
  • 项目类别:
    Standard Grant
Collaborative Research: NSF-ANR MCB/PHY: Probing Heterogeneity of Biological Systems by Force Spectroscopy
合作研究:NSF-ANR MCB/PHY:通过力谱探测生物系统的异质性
  • 批准号:
    2412550
  • 财政年份:
    2024
  • 资助金额:
    $ 12.39万
  • 项目类别:
    Standard Grant
NSF-BSF: Collaborative Research: Solids and reactive transport processes in sewer systems of the future: modeling and experimental investigation
NSF-BSF:合作研究:未来下水道系统中的固体和反应性输送过程:建模和实验研究
  • 批准号:
    2134747
  • 财政年份:
    2024
  • 资助金额:
    $ 12.39万
  • 项目类别:
    Standard Grant
Collaborative Research: NSF-AoF: CIF: Small: AI-assisted Waveform and Beamforming Design for Integrated Sensing and Communication
合作研究:NSF-AoF:CIF:小型:用于集成传感和通信的人工智能辅助波形和波束成形设计
  • 批准号:
    2326622
  • 财政年份:
    2024
  • 资助金额:
    $ 12.39万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了