Characterizing patients at risk for sepsis through Big Data (Supplement)

通过大数据描述有败血症风险的患者（补充）

• 批准号: 10599662
• 负责人: Andre L Holder
• 金额: $ 21.59万
• 依托单位: EMORY UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-01 至 2024-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10599662
• 关键词: Advocate; Algorithms; Artificial Intelligence; Big Data; Black American; Communities; Computer software; Computerized Medical Record; Data; Data Scientist; Decision Making; Demographic Factors; Detection; Disadvantaged; Disease; Ethicists; Ethics; Exposure to; Focus Groups; Future; Goals; Grouping; Healthcare; Hour; Immigrant community; Justice; Label; Link; Mentored Patient-Oriented Research Career Development Award; Modeling; Output; Parents; Patients; Persons; Process; Risk; Sepsis; Societies; Son of Sevenless Proteins; Statistical Bias; System; Techniques; Testing; Training; Work; base; design; detection platform; experience; health equity; high risk; improved; interest; intersectionality; multidisciplinary; novel; predictive modeling; predictive tools; social bias; tool

“Ethics and Equity in Developing Artificial Intelligence models for Patients at Risk of Sepsis” SUMMARY The goal of this K23 supplement application proposal is to create ethical, disease-specific statistical bias detection for prediction models. The proposal introduces the first two steps of such as system: convene a ethics-driven focus group to identify important demographic factors for which to consider correcting, when applicable; and (2) create a novel bias detection metric, “Selection and Information Bias Exposure and Rank” or SIBER, which details the involvement and relative importance of each demographic factor (selected by the focus group) to the prediction output of existing models. In the first part of the workflow, a multidisciplinary group of ethicists, data scientists, clinicians, and community-based healthcare advocates are asked to attend three 2-hour sessions focused on improving health equity in the disease of interest (e.g., sepsis). At the end of the three sessions, the group is expected to have identified the demographic groupings needed for the algorithmic component. The data from the focus groups will be analyzed using qualitative analytic techniques. Among the results will be the list of demographic groups/labels that are at risk for experiencing healthcare bias. A utility function of each demographic variable will be created to weigh their relative importance in prediction output, but only among those who are deemed at high risk of bias. (The process for determining bias is beyond the scope of this proposal, but will be in future work.) The bias detection system (SIBER) will be exposed to two different sepsis prediction models, one of which being the model deliverable for aim 1 of my K23. The models will determine sepsis risk on unseen data. The proposal will test the ability of SIBER to identify and rank the different demographic factors contributing to wide prediction intervals. This supplement builds upon the ongoing work of aim 1 in the parent K23 award, which is to derive and validate SOS using electronic medical record data. Sepsis is the test case to prove the utility of SIBER, but the work proposed in this supplement is critical to creating equitable predictive models in general. It demonstrates that selection and information bias is present in the electronic medical record, and attempts to link it with certain demographic factors. It is the first step in operationalizing healthcare justice using data. It also demonstrates the intersectionality that exists between many demographic factors.

“为脓毒症风险患者开发人工智能模型的道德和公平性” 概括 此 K23 补充剂申请提案的目标是创造道德、特定疾病的统计偏差 预测模型的检测。该提案介绍了该系统的前两个步骤：召集一个 道德驱动的焦点小组，以确定需要考虑纠正的重要人口统计因素 适用的; (2) 创建一种新颖的偏差检测指标“选择和信息偏差暴露和排名” 或 SIBER，详细介绍了每个人口统计因素的参与度和相对重要性（由 焦点小组）到现有模型的预测输出。在工作流程的第一部分，多学科 要求伦理学家、数据科学家、临床医生和社区医疗保健倡导者参加 三个 2 小时的会议重点关注改善相关疾病（例如脓毒症）的健康公平性。结束时 在这三届会议上，预计该小组将确定实施该计划所需的人口分组 算法组件。来自焦点小组的数据将使用定性分析技术进行分析。 结果将包括有可能遭受医疗保健偏见风险的人口群体/标签列表。 将创建每个人口统计变量的效用函数，以权衡它们在预测中的相对重要性 输出，但仅限于那些被认为存在高偏见风险的人。 （确定偏差的过程超出了 该提案的范围，但将在未来的工作中。）偏差检测系统（SIBER）将暴露于 两种不同的脓毒症预测模型，其中之一是我的 K23 目标 1 的可交付模型。这 模型将根据未见的数据确定脓毒症风险。该提案将测试 SIBER 识别和 对影响宽预测区间的不同人口统计因素进行排序。 本补充建立在母 K23 奖项中目标 1 正在进行的工作的基础上，该目标旨在得出 并使用电子病历数据验证 SOS。脓毒症是证明效用的测试案例 SIBER，但本补充中提出的工作对于创建一般的公平预测模型至关重要。它 证明电子病历中存在选择和信息偏差，并试图 将其与某些人口因素联系起来。这是利用数据实施医疗保健正义的第一步。它 还证明了许多人口因素之间存在的交叉性。