FAI: Foundations of Fair AI in Medicine: Ensuring the Fair Use of Patient Attributes

FAI：医学中公平人工智能的基础：确保患者属性的公平使用

基本信息

批准号：
2040880
负责人：
Flavio Calmon
金额：
$ 62.5万
依托单位：
Harvard University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2021
资助国家：
美国
起止时间：
2021-07-01 至 2024-06-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2040880&HistoricalAwards=false
关键词：
FAI Foundations Fair AI Medicine

项目摘要

Machine learning models support decisions that affect millions of patients in the U.S. healthcare system in diagnosing illnesses, facilitating triage in emergency rooms, and informing supervision at intensive care units. In such applications, models will often include group attributes such as age, weight, and employment status to capture differences between patient subgroups. Standard techniques to build models with group attributes typically improve aggregate performance across the entire patient population. As a result, however, such models may lead to worse performance for specific groups. In such cases, the model may assign these groups preventable inaccurate predictions that undermine medical care and health outcomes. This project aims to prevent this harm by developing tools to ensure the fair use of group attributes in predictive models. The goal is to ensure that a model uses group attributes in a way that yields a tailored performance benefit for every group. Currently deployed machine learning models in medicine may exhibit fair use violations that undermine health outcomes. This project mitigates fair use violations at key stages in the deployment of machine learning in medicine: verification, model development, and communication. First, it develops tools to check if a model ensures fair use. These tools include theoretical guarantees that characterize when common approaches to model development produce fair use violations, and statistical tests to verify if a model violates fair use before and during deployment. Second, it develops algorithms for learning models with fair use guarantees. Algorithms will be tailored for salient use cases in medicine, paired with open-source software, and applied to build decision support tools for real-world medical applications. Third, it creates tools to inform key stakeholders (regulators, physicians, and patients) about a model's fair use guarantees. The project draws on machine learning, information theory, optimization, human-centered design, as well as expertise in deploying models in clinical settings. The resulting toolkit for ensuring fair use of group attributes in medicine will be embedded in real-world systems through collaborations with medical researchers and industry.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.

机器学习模型支持影响美国医疗保健系统中数百万患者的决策，包括诊断疾病、促进急诊室分诊以及通知重症监护病房的监督。在此类应用中，模型通常包括年龄、体重和就业状况等群体属性，以捕获患者亚组之间的差异。构建具有群体属性的模型的标准技术通常可以提高整个患者群体的总体表现。然而，这样的模型可能会导致特定群体的表现较差。在这种情况下，该模型可能会为这些群体分配可预防的不准确预测，从而损害医疗保健和健康结果。该项目旨在通过开发工具来确保预测模型中群体属性的公平使用，从而防止这种损害。目标是确保模型使用组属性的方式为每个组产生量身定制的性能优势。目前在医学中部署的机器学习模型可能会表现出违反合理使用的行为，从而损害健康结果。该项目减少了医学机器学习部署关键阶段的合理使用违规行为：验证、模型开发和通信。首先，它开发工具来检查模型是否确保公平使用。这些工具包括表征模型开发的常见方法何时产生合理使用违规的理论保证，以及验证模型在部署之前和部署期间是否违反合理使用的统计测试。其次，它开发了具有合理使用保证的学习模型算法。算法将针对医学中的突出用例量身定制，与开源软件配合使用，并应用于为现实世界的医疗应用构建决策支持工具。第三，它创建了工具来向主要利益相关者（监管机构、医生和患者）通报模型的合理使用保证。该项目利用了机器学习、信息论、优化、以人为本的设计以及在临床环境中部署模型的专业知识。由此产生的用于确保在医学中公平使用群体属性的工具包将通过与医学研究人员和行业的合作嵌入到现实世界的系统中。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优点和更广泛的评估进行评估，被认为值得支持。影响审查标准。

项目成果

期刊论文数量（7）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Arbitrary Decisions are a Hidden Cost of Differentially Private Training

武断的决定是差别化私人训练的隐性成本

DOI：
10.1145/3593013.3594103
发表时间：
2023-06
期刊：
and Transparency
影响因子：
0
作者：
Kulynych, Bogdan;Hsu, Hsiang;Troncoso, Carmela;Calmon, Flavio P.
通讯作者：
Calmon, Flavio P.

Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels

使用加性噪声通道属性的噪声迭代算法的泛化界限

DOI：
发表时间：
2023-01
期刊：
Journal of machine learning research
影响因子：
6
作者：
Wang, Hao;Gao, Rui;Calmon, Flavio P.
通讯作者：
Calmon, Flavio P.

Beyond Adult and COMPAS: Fair Multi-Class Prediction via Information Projection

超越成人和 COMPAS：通过信息投影进行公平的多类别预测

DOI：
发表时间：
2022-12
期刊：
Advances in neural information processing systems
影响因子：
0
作者：
Alghamdi, W.;Hsu, H.;Jeong H.;Wang H.;Michalak, P.W.;Asoodeh, S.;Calmon F.P.
通讯作者：
Calmon F.P.

Analyzing the Generalization Capability of SGLD Using Properties of Gaussian Channels

利用高斯通道特性分析SGLD的泛化能力