Novel Deep Learning Tools for Clinical Decision Support in Postoperative Pain Management

用于术后疼痛管理临床决策支持的新型深度学习工具

• 批准号: 10670469
• 负责人: Baiming Zou
• 金额: $ 42.3万
• 依托单位: UNIV OF NORTH CAROLINA CHAPEL HILL
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-16 至 2024-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10670469
• 关键词: Acute; Address; Age; Algorithms; American; Analgesics; Anesthesia procedures; Basic Science; Caring; Chronic; Clinical; Cohort Studies; Complement; Complex; Critical Care; Data; Data Analyses; Data Sources; Databases; Education; Electronic Health Record; Etiology; Florida; Funding; Goals; Health; Healthcare Systems; Heterogeneity; Image; Individual; Inpatients; Intervention; Lead; Length of Stay; Measures; Mediation; Medical Care Costs; Methods; Modeling; Morbidity - disease rate; Network-based; Neural Network Simulation; North Carolina; Operative Surgical Procedures; Outcome; Pain; Pain Measurement; Pain intensity; Pain management; Patients; Perioperative; Pharmaceutical Preparations; Physicians; Policies; Policy Maker; Population; Postoperative Pain; Postoperative Period; Process; Race; Randomized Controlled Trials; Regimen; Research; Research Personnel; Risk; Risk Factors; Socioeconomic Status; Structure; Subgroup; Techniques; Testing; Time; United States National Institutes of Health; Universities; analytical tool; base; circadian; clinical care; clinical decision support; clinical practice; cohort; computerized tools; convolutional neural network; cost; cost effective; data warehouse; deep learning; deep learning model; deep neural network; design; experience; improved; individual patient; learning strategy; machine learning model; mortality; novel; opioid overuse; outcome prediction; pain outcome; pain score; patient subsets; personalized medicine; response; semiparametric; sex; substance use; tool; user friendly software

Abstract Postoperative pain (POP) burdens millions of Americans, and it costs hundreds of billions dollars to the US healthcare system annually. Poorly managed acute POP often leads to increased morbidity, mortality, and many other complications, such as chronic POP and opioid overuse. Accurate prediction of POP outcomes and in-depth understandings of causal mechanisms of POP is critical to develop effective POP management. Also, many POP studies indicate heterogeneity of responses to anesthesia methods and postoperative substance use, suggesting a critical need for effective methods to accurately identify patient subgroups for more effective POP management tailored to the individual patient's needs. However, achieving these goals is challenging due to the complex POP mechanisms and limited data from ideal large randomized controlled trials. On the other hand, abundant observational POP data found in surgery patients' electronic health records (EHRs) are readily available, and they can serve as a cost-effective alternative to address the critical challenges in POP management. However, the etiology of POP is intricate, i.e. many factors may interweave with each other and impact POP outcomes non-linearly and non-additively, introducing daunting modeling challenges. Furthermore, confounding, a major concern associated with observational data, represents a particular challenge for conducting causal analysis on POP data. Also, POP outcomes such as POP intensity scores are often irregularly and repeatedly measured, and distributed non-normally with two distinct data processes, requiring more advanced analysis methods. This proposal aims to overcome these analytic and modeling challenges with state-of-the-art deep learning methods to improve POP management. Specifically, we will 1) establish robust deep learning models for more accurate predictions of both acute and chronic POP to achieve timely POP control and care; 2) develop valid deep learning based semi-parametric methods to identify true causal factors and mechanisms of POP to design more effective POP management interventions; and 3) build powerful models to conduct robust hidden subgroup analysis to develop the optimal POP management tailored to the individual patient's needs. Methods developed in Aims 1 3 are motivated and will be tested by two unique data: a large EHR data from the University of North Carolina at Chapel Hill's Carolina Data Warehouse for Health (CDW-H), and a high-quality cohort data from NIH- funded TEMporal PostOperative Pain Signatures study, which complements the CDW-H in scale and scope. The project will elucidate the scientific underpinnings of POP mechanisms and provide improved POP management.

抽象的 术后疼痛（POP）伯恩伦斯伯恩斯数百万美国人，它花了数亿美元才向美国 每年医疗保健系统。管理不善的急性流行通常会导致发病率增加，许多 其他并发症，例如慢性流行和阿片类药物过度使用。准确预测流行成果和深入的预测 对POP的因果机制的理解对于发展有效的流行管理至关重要。另外，许多流行音乐 研究表明对麻醉方法和术后使用的反应异质性，表明 对有效方法准确识别患者子组以进行更有效的流行管理的关键需求 根据患者的需求量身定制。但是，由于复杂的 来自理想大型随机对照试验的流行机制和有限的数据。另一方面，丰富 手术患者的电子健康记录（EHR）中发现的观察性流行数据很容易获得，并且 它们可以作为应对流行管理中关键挑战的经济高效替代方案。 但是，POP的病因很复杂，即许多因素可能相互交织并影响POP 结果是非线性和非高级的，引入了艰巨的建模挑战。此外，混乱， 与观察数据相关的主要问题，代表了进行催化的特殊挑战 对流行数据的分析。同样，流行的结果（例如流行强度得分）通常是不规则且反复的 通过两个不同的数据过程进行测量和非正常分布，需要更高级的分析 方法。该建议旨在克服这些分析和建模的挑战 改善流行管理的学习方法。特定的，我们将1）建立强大的深度学习模型 对急性和慢性流行的更准确预测，以实现及时的流行控制和护理； 2）发展有效 基于深度学习的半参数方法，以识别POP设计的真正因果因素和机制 更有效的流行管理干预措施； 3）建立强大的模型以进行强大的隐藏子组 分析以开发满足个人患者需求的最佳流行管理。开发了方法 在目标1 3中是动机的，将通过两个独特的数据进行测试：北大学的大量EHR数据 卡罗来纳州教堂山的卡罗来纳州卡罗来纳州数据仓库（CDW-H），以及NIH-的高质量队列数据 资助的时间术后疼痛特征研究，在规模和范围内完成CDW-H。这 项目将阐明流行机制的科学基础，并提供改进的流行管理。