CAREER: Fundamental Intelligent Building Blocks of the Intensive Care Unit (ICU) of the Future

职业：未来重症监护病房 (ICU) 的基本智能构建模块

• 批准号: 1750192
• 负责人: Parisa Rashidi
• 金额: $ 54.37万
• 依托单位: University of Florida
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-04-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1750192&HistoricalAwards=false
• 关键词: CAREER; Fundamental; Intelligent; Building; Blocks

In the United States, intensive care units (ICUs) costs exceed 4% of national health costs, and ICU mortality rates can be as high as 29%. Precise assessment and prediction of patient status in the ICU can enable early interventions, and can result in improved patient outcomes. However, today's ICUs still face many barriers for assessing and predicting patient status. First, essential information such as pain and functional status are not captured automatically, but rather are repetitively measured by overburdened ICU nurses, with new assessments added each year. Second, existing methods for predicting patient status have limited accuracy and are used infrequently (e.g. every 24 hours as opposed to in real-time). This leads to missing opportunities for early interventions. Finally, existing models cannot automatically incorporate family caregiver feedback for improved patient status prediction. Together, these challenges point to the critical need for developing several fundamental intelligent building blocks of future ICUs. These building blocks should address: (a) how to learn new patient status prediction models without compromising performance on previous prediction models, (b) how to handle the complex clinical data for precise prediction of patient outcome, and (c) how to incorporate family caregiver feedback into the prediction models.This project will pursue three specific research objectives that will address these issues: (1) Lifelong Multi-Task Learning: Novel multi-task deep learning models will be developed for recognizing clinical expressions and functional activities related to pain and functional status assessments. These models will be customized in an innovative manner to maximize information sharing among related tasks. (2) Multi-Scale and Dynamic Learning: Novel multi-scale recurrent neural networks will be developed to predict precise patient outcomes while handling multiple temporal scales and implicit input changes over time. (3) Continual Opportunistic Learning: Novel active deep learning models will be developed to query the labels of the most informative data points for improving the models over time, with minimum burden on users. The proposed project will bring together novel elements of machine learning algorithms and critical care medicine. This will represent the first attempt to autonomously assess pain and functional status in the ICU, to predict precise patient trajectory from high-resolution data, and to improve predictive clinical models through user feedback. In addition, the research will be impactful because what is learned here, will contribute to a broader understanding of future design considerations for the next generation of lifelong learning systems and intelligent hospitals. The PI will also provide a highly-integrated research and educational program for Florida high school teachers and students, and University of Florida (UF) undergraduate students in the context of the intelligent ICU. The PI proposes to: (1) sponsor summer internships for math teachers, (2) organize an Intelligent Machines workshop on coding and machine intelligence for the high school students, and (3) develop focused research and training activities for undergraduate students. These outreach and training programs will be used to promote interest in science, technology, engineering, and mathematics (STEM) fields among Florida high school students and UF undergraduate students.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

在美国，重症监护病房（ICU）的费用超过国家卫生费用的4%，ICU死亡率可高达29%。准确评估和预测ICU中的患者状态可以实现早期干预，并可以改善患者的预后。然而，今天的ICU在评估和预测患者状态方面仍然面临许多障碍。首先，疼痛和功能状态等基本信息不会自动捕获，而是由负担过重的ICU护士重复测量，每年增加新的评估。第二，用于预测患者状态的现有方法具有有限的准确性并且很少使用（例如，每24小时，而不是实时使用）。这导致错过早期干预的机会。最后，现有的模型不能自动纳入家庭护理人员的反馈，以改善患者的状态预测。总之，这些挑战表明迫切需要开发未来ICU的几个基本智能构建模块。这些模块应解决：（a）如何学习新的患者状态预测模型，而不影响先前预测模型的性能;（B）如何处理复杂的临床数据，以精确预测患者结果;以及（c）如何将家庭护理人员的反馈纳入预测模型。本项目将追求三个具体的研究目标，以解决这些问题：（1）终身多任务学习：将开发新型多任务深度学习模型，用于识别与疼痛和功能状态评估相关的临床表现和功能活动。这些模型将以创新的方式定制，以便在相关任务之间最大限度地分享信息。(2)多尺度和动态学习：将开发新型多尺度递归神经网络，以预测精确的患者结局，同时处理多个时间尺度和隐式输入随时间的变化。(3)持续学习：将开发新的主动深度学习模型来查询信息量最大的数据点的标签，以便随着时间的推移改进模型，同时最大限度地减少用户负担。拟议的项目将汇集机器学习算法和重症监护医学的新元素。这将是首次尝试自主评估ICU中的疼痛和功能状态，从高分辨率数据中预测精确的患者轨迹，并通过用户反馈改进预测性临床模型。此外，这项研究将是有影响力的，因为在这里学到的东西将有助于更广泛地了解下一代终身学习系统和智能医院的未来设计考虑因素。PI还将在智能ICU的背景下为佛罗里达高中教师和学生以及佛罗里达大学（UF）本科生提供高度集成的研究和教育计划。PI建议：（1）赞助数学教师的暑期实习，（2）为高中生组织关于编码和机器智能的智能机器研讨会，（3）为本科生开发有针对性的研究和培训活动。这些推广和培训计划将用于促进佛罗里达高中生和UF本科生对科学，技术，工程和数学（STEM）领域的兴趣。该奖项反映了NSF的法定使命，并被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估来支持的。

项目成果

Discovery and Validation of Urinary Molecular Signature of Early Sepsis.

• DOI: 10.1097/cce.0000000000000195
• 发表时间: 2020-10
• 期刊: Critical care explorations
• 作者: Bandyopadhyay S;Lysak N;Adhikari L;Velez LM;Sautina L;Mohandas R;Lopez MC;Ungaro R;Peng YC;Kadri F;Efron P;Brakenridge S;Moldawer L;Moore F;Baker HV;Segal MS;Ozrazgat-Baslanti T;Rashidi P;Bihorac A
• 通讯作者: Bihorac A

Artificial intelligence approaches to improve kidney care.

人工智能改善肾脏护理的方法。

• DOI: 10.1038/s41581-019-0243-3
• 发表时间: 2020-02
• 期刊: Nature reviews. Nephrology
• 作者: Rashidi P;Bihorac A
• 通讯作者: Bihorac A

Opportunities for machine learning to improve surgical ward safety.

• DOI: 10.1016/j.amjsurg.2020.02.037
• 发表时间: 2020-10
• 期刊: American journal of surgery
• 影响因子: 3
• 作者: Loftus TJ;Tighe PJ;Filiberto AC;Balch J;Upchurch GR Jr;Rashidi P;Bihorac A
• 通讯作者: Bihorac A

Human Activity Recognition using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey.

使用惯性，生理和环境传感器的人类活动识别：一项综合调查。

• DOI: 10.1109/access.2020.3037715
• 发表时间: 2020
• 期刊: IEEE access : practical innovations, open solutions
• 作者: Demrozi F;Pravadelli G;Bihorac A;Rashidi P
• 通讯作者: Rashidi P

Primer on machine learning: utilization of large data set analyses to individualize pain management.

• DOI: 10.1097/aco.0000000000000779
• 发表时间: 2019-10
• 期刊: Current Opinion in Anaesthesiology
• 作者: Parisa Rashidi;David A. Edwards;P. Tighe