Identifying and addressing missingness and bias to enhance discovery from multimodal health data

识别和解决缺失和偏见，以增强多模式健康数据的发现

• 批准号: 10637391
• 负责人: Pengyu Hong
• 金额: $ 40.06万
• 依托单位: BRIGHAM AND WOMEN'S HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-05-10 至 2027-02-28
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10637391
• 关键词: Address; Advanced Development; Algorithms; Area; Artificial Intelligence; Attention; Awareness; Big Data; Characteristics; Chronic; Clinical Data; Collaborations; Complex; Critical Care; Data; Data Set; Decision Making; Development; Effectiveness; Electronic Health Record; Ensure; Evaluation; Evaluation Methodology; Gender; Goals; Health; Health Personnel; Healthcare; Healthcare Systems; Hospitals; Insurance; Intensive Care Units; Knowledge Discovery; Life; Machine Learning; Massachusetts; Measurement; Medical Informatics; Medicine; Methods; Modeling; Patients; Performance; Prevalence; Process; Race; Reproducibility; Research; Retinal blind spot; Risk Factors; Statistical Methods; Techniques; Technology; Time; Training; Training Technics; Visualization; Work; biomedical informatics; clinical decision support; clinical decision-making; clinical practice; computer science; deep learning; design; equity, diversity, and inclusion; health care delivery; health data; health equity; improved; innovation; large datasets; machine learning algorithm; machine learning method; machine learning model; multimodality; novel; open source; outcome prediction; predict clinical outcome; predictive modeling; success; tool

PROJECT SUMMARY Recent successes of machine learning (especially deep learning) in analyzing electronic health record (EHR) data have not only stimulated excitement in stake holders but have also raised concerns potential unfair or biased clinical decision making facilitated by machine learning. A number of fairness measurements have been proposed. However, they underappreciate the chronical systematic differences between the distributions of protected and unprotected groups. Hence, when used to develop machine learning methods, they may worsen within-group issues and dampen performance of the trained machine learning models. The situation can be further complicated by missing values that are common in EHR data, which will exacerbate unfairness if not handled properly. In this project, we aim to develop a novel fairness evaluation methodology (Aim 1) and incorporate it into the development of innovative machine learning models and techniques to reduce biases and increase interpretability (Aim 2). To better and more fairly handle missing values, we will develop new machine learning models that contain trainable in-process missing value imputation components and new algorithms to train them with constraints defined by our new fairness evaluation method (Aim 3). In addition, we will develop proactive machine learning techniques to advance heath equity (Aim 4). We will evaluate and improve our new fairness measurements and machine learning techniques in the context of facilitating clinical decision making (Aim 5). Large datasets from two of the largest US healthcare systems will be used in carrying out the proposed research.

项目摘要 最近机器学习（特别是深度学习）在分析电子健康记录（EHR）数据方面的成功， 这不仅刺激了利益相关者的兴奋，也引起了人们对潜在的不公平或有偏见的临床决策的担忧。 通过机器学习来实现。已经提出了许多公平性测量。但他们 低估了受保护群体和未受保护群体分布之间的长期系统性差异。因此，我们认为， 当用于开发机器学习方法时，它们可能会恶化组内问题，并抑制机器学习的性能。 训练的机器学习模型EHR数据中常见的缺失值可能会使情况进一步复杂化， 如果处理不当，会加剧不公平。在这个项目中，我们的目标是开发一种新的公平性评价 方法（目标1），并将其纳入创新机器学习模型和技术的开发中， 减少偏差，提高可解释性（目标2）。为了更好、更公平地处理缺失值，我们将开发新的 机器学习模型，包含可训练的过程中缺失值插补组件和新的算法来训练 他们与我们的新的公平性评价方法（目标3）定义的约束。此外，我们将积极发展 机器学习技术促进健康公平（目标4）。我们将评估和改进我们新的公平性衡量标准 和机器学习技术在促进临床决策的背景下（目标5）。两个大型数据集， 美国最大的医疗保健系统将用于开展拟议的研究。