Use Explainable AI to Improve the Trust of and Detect the Bias of AI Models

使用可解释的人工智能来提高人工智能模型的信任度并检测其偏差

• 批准号: 10599655
• 负责人: Peter F. Kokkinos
• 金额: $ 32.3万
• 依托单位: GEORGE WASHINGTON UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10599655
• 关键词: Address; Age; Alzheimer' s disease related dementia; American; Artificial Intelligence; Award; Behavioral Sciences; Bioethical Issues; Biological Markers; Detection; Development; Electronic Health Record; Environment; Ethical Issues; Ethics; Human; Individual; Link; Measures; Methods; Modeling; Parents; Physical activity; Public Health; Race; Recommendation; Risk; Risk Factors; Subgroup; Techniques; Technology; Testing; Trust; Veterans; Work; base; cardiorespiratory fitness; deep learning; design; epidemiology study; fitness; improved; method development; parent grant; recruit; risk prediction model; sex; tool

Project Summary/Abstract AD/ADRD is a growing national public health crisis as the number of Americans ≥65 years is projected to double by 2050. Our parent grant was designed to measure cardiorespiratory fitness (CRF) as a biomarker of physical activity in the most extensive epidemiological study in nearly 1 million Veterans using VA’s world-class electronic health record and advanced artificial intelligence technologies. The parent grant aims are (1) to determine the relationship between CRF and incident AD/ADRD, taking into consideration a non-linear relationship and potential interactions of CRF with other risk factors and (2) to define incremental CRF levels that are linked to progressively lower risk of AD/ADRD, overall, and in subgroups by age, sex, and race. Our Aim 3 is to develop and validate a deep learning-based risk prediction model to determine the optimal CRF level for individuals to achieve the lowest risk of AD/ADRD. Deep learning is a key Artificial intelligence (AI) technique. AI has demonstrated great strides in the past decade. However, AI models are often viewed as “black box” as they are difficult to explain. Understanding what an AI model does is a prerequisite to the ethical use of AI, because stakeholders can’t trust a model or detect the potentially intended and unintended biases associated with the development or utilization of the model without understanding it. We believe that explainable AI is a powerful tool to address the bioethics issues of trust and bias. The purpose of explainable AI is to make it possible for human users to understand and trust the decisions or recommendations offered by the AI model, and to debug and refine it. Specifically, this supplement will test the effect of AI model explanation on trust and bias detection in a simulated environment by recruiting a set of stakeholders and using a scenario-based approach. The potential broad impact of the proposed work is that it will advance the ethical development and use of AI/ML in biomedical and behavioral sciences using explainable AI methods.

项目摘要/摘要 随着美国人的数量≥65岁，AD/ADRD是日益增长的国家公共卫生危机 预计到2050年将翻一番。我们的父母赠款旨在衡量心肺 健身（CRF）是最广泛的流行病学研究中体育活动的生物标志物 使用VA的世界一流电子健康记录和高级艺术的近100万退伍军人 情报技术。父母赠款的目的是（1）确定 考虑到非线性关系和潜力，CRF和事件AD/ADRD CRF与其他风险因素的相互作用以及（2）定义链接的增量CRF水平 逐渐降低按年龄，性别和种族的亚组降低AD/ADRD的风险。我们的目标 3是开发和验证基于深度学习的风险预测模型，以确定最佳 CRF水平使个人达到最低的AD/ADRD风险。深度学习是一个关键的人造 情报（AI）技术。在过去的十年中，AI取得了长足的进步。但是，AI 由于难以解释，通常将模型视为“黑匣子”。了解什么人AI 模型做是AI道德使用的先决条件，因为利益相关者无法相信模型或 检测与开发相关的潜在意图和意外偏见或 在不了解模型的情况下利用模型。我们认为可解释的AI是一种强大的工具 解决信任和偏见的生物伦理问题。可以解释的AI的目的是实现 人类用户可以理解和信任由 AI模型，并调试和完善它。具体而言，该补充将测试AI的效果 通过招募一组，在模拟环境中对信任和偏见检测的模型解释 利益相关者并使用基于方案的方法。提议的潜在广泛影响 工作是它将推动生物医学和行为中AI/ML的道德发展和使用 使用可解释的AI方法的科学。