Critical Care Informatics

重症监护信息学

基本信息

批准号：
10772272
负责人：
Leo Anthony G Celi
金额：
$ 39.75万
依托单位：
MASSACHUSETTS INSTITUTE OF TECHNOLOGY
依托单位国家：
美国
项目类别：
财政年份：
2014
资助国家：
美国
起止时间：
2014-08-01 至 2025-04-30
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10772272
关键词：
Address Adoption Affect Algorithms Artificial Intelligence Award Behavioral Sciences COVID-19 Caring Classification Clinical Clinical Data Clinical Research Clip Code Community Health Critical Care Data Data Element Data Science Data Scientist Data Set Data Sources Databases Detection Development Discrimination Documentation Education Electronic Health Record Engineering Equity Ethics Ethnic Origin Face Funding Grant Guidelines Health Health Sciences Healthcare Hospitals Human Image Informatics Intensive Care Intensive Care Units Knowledge Koreans Laboratories Learning Link Machine Learning Maps Masks Medical Medical Imaging Medicine Methods Modality Modeling National Institute of Biomedical Imaging and Bioengineering Ontology Outcome Paper Patients Physiology Portuguese Process Professional Organizations Public Health Public Health Applications Research Public Health Informatics Publications Publishing Qualitative Research Quality of Care Race Research Research Personnel Resources Shapes Social Sciences Societies Source Students Techniques Test Result Testing Textbooks Thoracic Radiography Translating United States Universities University Hospitals Writing algorithmic bias base clinical care clinical center clinical predictors data science education design eHealth global health health care settings health data health disparity health equity implementation framework improved mHealth machine learning algorithm machine learning method model development mortality multidisciplinary novel diagnostics novel therapeutic intervention online course outcome disparities outreach pandemic disease population based population health prevent radiological imaging research study secondary analysis social health determinants sociodemographics success

项目摘要

Abstract This is a renewal application for the Critical Care Informatics grant (NIBIB R01 EB017205) that was awarded to the Laboratory for Computational Physiology (LCP) in 2014. This grant has supported the development of the Medical Information Mart for Intensive Care (MIMIC) research database, which is a de-identified database for research and health data science education around the world. We aim to address the foremost issues in machine learning in healthcare today, focusing on health disparities, algorithmic bias, and understanding the barriers to effective and equitable implementation of algorithmic models. Our proposal will enrich MIMIC with new data types and sources, including publicly available population health datasets, advance progress on a federated critical care dataset, and add a new module with COVID-19 specific ontology and codes. Our research will build on prior findings showing the pervasiveness of hidden socio-demographic bias in data sources including clinical data, medical images, and narrative patient documentation. Health care data science ultimately exists for the purpose of improving human health. Yet, extremely few models published in research papers have impacted clinical care due to challenges in implementation. In layman’s terms, this means knowledge gained about tests and treatments leads to the best possible outcome for every patient in the intensive care unit (ICU) regardless of demographic. We will conduct a rigorous qualitative research study to better understand the barriers faced by key stakeholders - clinicians and data scientists - in the development and implementation of equity-centered artificial intelligence. This information will be used to develop guidelines to integrate with implementation science frameworks to support the effective implementation of equitable AI in clinical settings. With these aims, MIMIC will significantly expand the relevance of this research resource to a greater diversity of investigators including those in the social and behavioral sciences and public health and continue to be a resource for clinical research and increasingly sophisticated model development, advancing our understanding of critical issues of fairness and equity in healthcare, data science, and the broader society.

抽象的这是重新护理信息学补助金（Nibib R01 EB017205）的续签申请 2014年计算生理学实验室（LCP）。该赠款支持了重症监护（MIMIC）研究数据库的医疗信息MART，这是一个被取消识别的数据库全球研究和健康数据科学教育。我们旨在解决机器中最重要的问题当今的医疗保健学习，专注于健康分布，算法偏见，并了解算法模型的有效实施。我们的建议将丰富模仿新数据类型和来源，包括公开可获得的人口健康数据集重症监护数据集，并添加一个具有COVID-19特定本体论和代码的新模块。我们的研究将建立关于先前的发现，显示了隐藏的社会人口统计学偏见在包括临床在内的数据源中的普遍性数据，医学图像和叙事性患者文档。医疗数据科学最终存在于改善人类健康的目的。然而，在研究论文中发表的极少数模型影响了由于实施挑战而引起的临床护理。用外行的话来说，这意味着知识获得了测试无论如何人群。我们将进行严格的定性研究，以更好地了解主要利益相关者 - 临床医生和数据科学家 - 以股权为中心的发展和实施人工智能。该信息将用于制定与实施科学集成的准则支持在临床环境中有效实施公平AI的框架。以这些目的，模仿将大大扩展该研究资源的相关性，包括那些从事社会和行为科学和公共卫生的人，并继续成为临床研究的资源以及越来越复杂的模型开发，促进了我们对公平关键问题的理解以及医疗保健，数据科学和更广泛的社会的公平。