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

“为有脓毒症风险的患者开发人工智能模型的伦理和公平性” 摘要 这项K23补充剂应用提案的目标是创建伦理的、特定于疾病的统计偏差 预测模型的检测。该方案介绍了如系统的前两步：召开一次 道德驱动的焦点小组，以确定重要的人口统计因素，以考虑在以下情况下进行更正 适用；以及(2)创建一种新的偏差检测指标，“选择和信息偏差暴露和排名” 或Siber，它详细说明了每个人口统计因素的参与程度和相对重要性(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 伦理学家、数据科学家、临床医生和基于社区的医疗保健倡导者小组被邀请参加 三个2小时的会议集中于改善感兴趣疾病(如败血症)的健康公平性。在…的末尾 在三次会议上，预计该小组将确定 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。 在结果中，将列出面临医疗保健偏见风险的人口群体/标签。 将创建每个人口变量的效用函数，以权衡它们在预测中的相对重要性 产出，但仅限于那些被认为存在高偏见风险的人。(确定偏见的过程超出了 这项提议的范围，但将在未来的工作中。)偏置检测系统(SIBER)将暴露在 两个不同的脓毒症预测模型，其中一个是我的K23目标1的可交付模型。这个 模型将根据看不见的数据确定脓毒症风险。该提案将考验西伯尔识别和识别和 对导致预测区间较宽的不同人口统计因素进行排名。 本附录建立在父K23奖中目标1正在进行的工作的基础上，该奖项将派生出 并使用电子病历数据验证SOS。脓毒症是一个测试案例，证明了 但本附录中提出的工作对于总体上创建公平的预测模型至关重要。它 证明电子病历中存在选择和信息偏差，并试图 将其与某些人口统计因素联系起来。这是使用数据实现医疗正义的第一步。它 也表明了许多人口因素之间存在的交叉性。

“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.