Achieving Model Fairness on Automatic Primary Open-angle Glaucoma Screening

实现自动原发性开角型青光眼筛查的模型公平性

• 批准号: 10726928
• 负责人: Yifan Peng
• 金额: $ 46.61万
• 依托单位: WEILL MEDICAL COLL OF CORNELL UNIV
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-30 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10726928
• 关键词: Address; Adopted; African American population; Area; Artificial Intelligence; Blindness; Clinical; Clinical Medicine; Conscious; Data; Data Science; Data Scientist; Data Set; Dedications; Disease; Ensure; Ethnic Origin; Exhibits; Eye; Health Disparities Research; Hispanic Americans; Human; Learning; Minority; Mission; Modeling; Ophthalmologist; Outcome; Participant; Patient Triage; Patients; Performance; Population Heterogeneity; Primary Open Angle Glaucoma; Public Health; Quality of life; Race; Research; Risk Estimate; Strategic Planning; Systematic Bias; Unconscious State; United States; Validation; Vision; Vision research; algorithm training; algorithmic bias; demographics; ethnic minority; experience; health disparity; health equity; health information technology; improved; innovation; insight; loss of function; novel; outcome disparities; predictive modeling; prevent; racial minority; response; screening; secondary analysis; sex; success

Project summary/abstract In the United States, primary open-angle glaucoma (POAG) is the leading cause of blindness, especially among African and Hispanic Americans. Because visual function loss from POAG is irreversible, it is critical to estimate the risk of POAG and prevent further vision loss. Recently, there has been growing concern that the predictive model may reflect and amplify human bias and reduce the quality of their performance if used in the clinical pipeline for patient triage. Motivated by known differences in disease manifestation in patients such as sex and race/ethnicity, this study hypothesizes that algorithms trained on existing datasets will exhibit systematic biases in subpopulations. Popular approaches to remove such biases suggested that having a greater number of positive cases across demographics helped models perform better in validation. However, collecting new data often suffers from a lack of demographic representation. In response to NOT-EY-22-004 (Research Addressing Eye and Vision Health Equity/Health Disparities) and PAR-22-141 (Secondary Analysis of Existing Datasets), this project will develop and validate a new artificial intelligence approach to improve the fairness of the predictive model on POAG risk estimation without the need for demographically balanced datasets. Based on our preliminary data and our experience with an interdisciplinary team of data scientists and ophthalmologists, we plan to execute specific aims: 1) studying “algorithmic bias” in the POAG risk estimation and 2) examining the impact of “transfer bias” from the biased to the demographically balanced data. The studies proposed in this project are novel and innovative because the secondary analyses of existing data provide additional insight into POAG health disparities. Aim 1 will be the first to perform a systematic study of algorithm bias in the DL-based POAG predictive models and identify the factors contributing to model fairness. Aim 2 will be the first study to examine that bias transfer may arise in the POAG prediction setting and can occur even when the POAG dataset is explicitly de-biased. We argue that our models provide simple, interpretable, and easily checkable frameworks to allow better POAG risk estimation for protected groups. The expected outcome of this project is a holistic framework to mitigate the impacts of inequity by improving the inference performance for minorities. The success of this project will provide additional insight into health disparities of POAG risk estimation by (1) reducing clinical decisions tainted by unconscious or conscious bias, and (2) developing brand-new models that reflect learned POAG features but not patient demographic to ensure robustness across diverse populations. This project is highly feasible and potentially transformative for both data science and clinical medicine.

项目概要/摘要 在美国，原发性开角型青光眼 (POAG) 是导致失明的主要原因，尤其是 在非洲裔和西班牙裔美国人中。由于 POAG 导致的视功能丧失是不可逆的，因此至关重要 评估 POAG 的风险并防止进一步的视力丧失。最近，人们越来越担心 如果将预测模型用于以下领域，则可能会反映并放大人类偏见并降低其绩效质量 患者分类的临床管道。受患者疾病表现已知差异的驱动，例如 性别和种族/民族，这项研究假设在现有数据集上训练的算法将表现出系统性 亚群体中的偏见。消除此类偏见的流行方法表明，拥有更多的人 跨人口统计的积极案例帮助模型在验证中表现更好。然而，收集新数据 往往缺乏人口代表性。回应 NOT-EY-22-004（研究寻址 眼睛和视力健康公平/健康差异）和 PAR-22-141（现有数据集的二次分析）， 该项目将开发并验证一种新的人工智能方法，以提高预测的公平性 POAG 风险估计模型，无需人口统计平衡数据集。基于我们的 初步数据以及我们与数据科学家和眼科医生组成的跨学科团队的经验，我们 计划执行特定目标：1）研究 POAG 风险估计中的“算法偏差”，2）检查 “转移偏差”从有偏见的数据到人口统计平衡数据的影响。本文提出的研究 该项目新颖且具有创新性，因为对现有数据的二次分析提供了额外的见解 POAG 健康差异。目标 1 将是第一个对基于 DL 的算法偏差进行系统研究的项目。 POAG 预测模型并确定影响模型公平性的因素。目标 2 将是第一个研究 检查 POAG 预测设置中是否可能出现偏差转移，甚至在 POAG 数据集时也可能发生偏差转移 是明确去偏见的。我们认为我们的模型提供了简单、可解释且易于检查的框架 以便更好地评估受保护群体的 POAG 风险。该项目的预期成果是一个全面的 通过提高少数群体的推理性能来减轻不平等影响的框架。成功 该项目的研究将通过以下方式提供对 POAG 风险评估的健康差异的更多见解：(1) 减少临床 受到无意识或有意识偏见影响的决策，以及（2）开发反映所学知识的全新模型 POAG 具有特征，但不具有患者人口统计特征，以确保不同人群的稳健性。这个项目是 对于数据科学和临床医学来说具有高度的可行性和潜在的变革性。