EQuitable, Uniform and Intelligent Time-based conformal Inference (EQUITI) Framework

公平、统一和智能的基于时间的共形推理 (EQUITI) 框架

基本信息

批准号：
10599622
负责人：
Rishikesan Kamaleswaran
金额：
$ 23.22万
依托单位：
EMORY UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2021
资助国家：
美国
起止时间：
2021-09-10 至 2026-06-30
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10599622
关键词：
Accident and Emergency department Address Admission activity Algorithms Animal Model Automobile Driving Award Awareness Cessation of life Clinical Clinical Management Comprehension Country Critical Illness Data Decision Making Development Early treatment Environment Ethics Functional disorder Funding Futility Goals Health Health Professional Hospital Mortality Hospitals Hour Human Immune response Individual Infection Intelligence Intensive Care Units Intervention Knowledge Length of Stay Mathematics Methodology Modeling Morbidity - disease rate Organ Outcome Output Parents Patient Care Patients Performance Physiological Probability Public Health Publications Research Resources Risk Sepsis Severities Source Testing Time Training Uncertainty Vendor Vulnerable Populations Work Workforce Development base care outcomes clinical translation data streams high risk improved improved outcome mathematical model mortality mortality risk novel screening secondary infection sensor skill acquisition statistical and machine learning targeted treatment theories tool trustworthiness ward

项目摘要

Project Summary Sepsis is a major public health challenge caused by a dysfunctional host response to infection, resulting in multiple organ dysfunction and increased risk of death. In the parent award, we investigate the physiological mechanisms that contribute to increased likelihood sepsis among patients admitted to the ICU. In this supplement we evaluate possible causes of uncertainty by utilizing conformal predictions and hypothesis tests. We will derive a novel framework which we term EQUITI that can be used to characterize the degree to which the model is uncertain, due to the influence of bias in the data. Furthermore, this supplement will also contribute workforce and skills development aids that are proposed to be used to improve clinicians and healthcare professionals understanding of ambiguities in model estimated output. Finally, these aids will also help health professionals better understand how these uncertainties can be identified and used to improve individual and team situational awareness.

项目概要脓毒症是一个重大的公共卫生挑战，由宿主对感染的反应功能失调引起，导致多器官功能障碍和死亡风险增加。在家长奖中，我们调查了生理学导致入住 ICU 的患者败血症可能性增加的机制。在这个补充我们通过利用保形预测和假设检验来评估不确定性的可能原因。我们将推导出一个新的框架，我们称之为 EQUITI，它可以用来描述由于数据偏差的影响，模型是不确定的。此外，本补充还将贡献劳动力和技能发展援助，建议用于提高临床医生和医疗保健专业人员对模型估计输出中的模糊性的理解。最后，这些辅助工具还将帮助卫生专业人员更好地了解如何识别和利用这些不确定性来改善个人和团队的态势感知。