CRII: SCH: Towards robustness to data disparities: a framework for efficient and reliable data-driven decision-making tools for all

CRII：SCH：实现数据差异的稳健性：为所有人提供高效可靠的数据驱动决策工具的框架

• 批准号: 2153083
• 负责人: Maggie Makar
• 金额: $ 17.5万
• 依托单位: Regents of the University of Michigan - Ann Arbor
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-03-15 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2153083&HistoricalAwards=false
• 关键词: CRII; SCH; Towards; robustness; data

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).One of the most promising applications of machine learning (ML), is its ability to guide personalized decision making, especially in the context of healthcare. Predictive ML models can help clinicians identify patients at high risk of adverse outcomes, enabling them to make informed decisions about preventative measures. Causal ML models can help clinicians and patients understand the effects of interventions enabling them to make more informed decisions about the treatment options. Importantly, the reliability of predictive and causal ML methods depends on the quality of data used to develop them. Unfortunately, data quality often reflects systemic inequalities in both access to and quality of healthcare leading to data disparities. Examples of unequal quality of care include settings in which Black patients are less likely to receive referrals to specialists or in which women’s pain is less likely to be taken seriously, both leading to potential delays in diagnosis and treatment. This means that data collected from specific subgroups of the population are more prone to missingness. In terms of access, data reveal that Black and Hispanic groups are more likely to be uninsured and less likely to have a usual place to go to for medical care. This results in the underrepresentation of subgroups of the population in observational data such as electronic health records typically used to develop ML models. In this proposal, we will develop and theoretically analyze robust ML methods (both predictive and causal) that ameliorate the effects of data disparities. The proposed research has two main prongs. The first prong focuses on developing prediction tools for diagnosis that are robust to inaccuracies due to underrepresentation of minorities. We will develop model training methods that discourage the models from learning patterns that are reflective of data biases rather than true causal mechanisms. We will theoretically analyze the robustness and efficiency of our models. The second prong focuses on developing methods for estimation of causal effects of interventions that are robust to data missingness and measurement error. While most existing work attempts to estimate the causal effect of an intervention, this project will study the estimation of intervals or bounds on the causal estimates which reflect the uncertainty in the quality of the collected data. We theoretically analyze the credibility and tightness of our bounds when trained using limited data.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.

该奖项全部或部分由2021年美国救援计划法案（公法117-2）资助。机器学习（ML）最有前途的应用之一是其指导个性化决策的能力，特别是在医疗保健方面。预测性ML模型可以帮助临床医生识别具有不良后果高风险的患者，使他们能够就预防措施做出明智的决定。因果ML模型可以帮助临床医生和患者了解干预措施的效果，使他们能够对治疗方案做出更明智的决定。重要的是，预测和因果ML方法的可靠性取决于用于开发它们的数据的质量。不幸的是，数据质量往往反映了在获得医疗保健和医疗保健质量方面的系统性不平等，导致数据差异。护理质量不平等的例子包括黑人病人不太可能被转诊给专家，或者妇女的疼痛不太可能被认真对待，这两种情况都可能导致诊断和治疗的延误。这意味着从特定的人口亚群收集的数据更容易丢失。在获取方面，数据显示，黑人和西班牙裔群体更有可能没有保险，也不太可能有一个通常的地方去接受医疗保健。这导致观察数据中的人口亚组代表性不足，例如通常用于开发ML模型的电子健康记录。在本提案中，我们将开发和理论分析稳健的ML方法（包括预测和因果），以改善数据差异的影响。 拟议中的研究有两个主要方面。第一个方面侧重于开发用于诊断的预测工具，这些工具对由于少数群体代表性不足而造成的不准确性具有鲁棒性。我们将开发模型训练方法，阻止模型学习反映数据偏差的模式，而不是真正的因果机制。我们将从理论上分析我们的模型的鲁棒性和效率。第二个方面的重点是制定方法，估计因果影响的干预措施，是强大的数据缺失和测量误差。虽然大多数现有的工作试图估计干预的因果效应，本项目将研究因果估计的区间或界限的估计，反映了收集的数据质量的不确定性。我们从理论上分析我们的边界的可信度和严密性时，使用有限的数据进行训练。这个奖项反映了NSF的法定使命，并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。

项目成果

Causally motivated multi-shortcut identification & removal

因果驱动的多捷径识别

• 发表时间: 2022
• 期刊: Advances in neural information processing systems
• 作者: Zheng, Jiayun;Makar, Maggie
• 通讯作者: Makar, Maggie

Uncovering the Varied Impact of Behavioral Change Messages on Population Groups

揭示行为改变信息对人群的不同影响

• 发表时间: 2023
• 期刊: Proceedings of Machine Learning Research
• 作者: Xu, Jiaai;Mihalcea, Rada;Frank, Elena;Sen, Srijan;Makar, Maggie
• 通讯作者: Makar, Maggie

Conditional differential measurement error: partial identifiability and estimation

条件微分测量误差：部分可识别性和估计

• 发表时间: 2022
• 期刊: NeurIPS workshop on causal machine learning for real world impact
• 作者: Huang, Pengrun;Makar, Maggie
• 通讯作者: Makar, Maggie

Learning Concept Credible Models for Mitigating Shortcuts.

学习概念减少捷径的可靠模型。

• 发表时间: 2022
• 期刊: Advances in neural information processing systems
• 作者: Wang,Jiaxuan;Jabbour,Sarah;Makar,Maggie;Sjoding,Michael;Wiens,Jenna
• 通讯作者: Wiens,Jenna

Fairness and robustness in anti-causal prediction

• DOI: 10.48550/arxiv.2209.09423
• 发表时间: 2022-09
• 期刊: Trans. Mach. Learn. Res.
• 作者: Maggie Makar;A. D'Amour