SCH: Leveraging Clinical Time Series to Learn Optimal Treatment of Acute Dyspnea

SCH：利用临床时间序列学习急性呼吸困难的最佳治疗方法

• 批准号: 9927810
• 负责人: Michael William Sjoding
• 金额: $ 23.85万
• 依托单位: UNIVERSITY OF MICHIGAN AT ANN ARBOR
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-10 至 2023-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9927810
• 关键词: Acute; Affect; Chronic Obstructive Airway Disease; Clinical; Clinical Data; Congestive Heart Failure; Data; Data Set; Decision Making; Diagnosis; Dyspnea; Electronic Health Record; Ensure; Evaluation; Goals; Health; Healthcare; Hospitalization; Instruction; Learning; Machine Learning; Methods; Modeling; Outcome; Patient Rights; Patient-Focused Outcomes; Patients; Physicians; Pneumonia; Policies; Principal Investigator; Psychological reinforcement; Quality of Care; Research; Respiratory Failure; Right to Treatments; Series; Shortness of Breath; Signs and Symptoms; Societies; Symptoms; System; Techniques; Test Result; Time; Training; Work; base; clinical care; clinical decision support; health data; high dimensionality; improved; mortality; novel; optimal treatments; patient response; patient stratification; programs; prospective; theories; tool; treatment strategy

The ability to rapidly match the right patients to the right treatments at the right time is critical to ensuring patients receive high quality care. The vast majority of machine learning applications in healthcare focus on diagnosing or stratifying patients for a particular outcome. In contrast, reinforcement learning (RL) aims to learn how clinical states (i.e., sets of signs, symptoms, and test results) respond to specific sequences of treatments, with the goal of optimizing clinical outcomes. RL does not aim to diagnose, but infers diagnosis based on a patient's response to specific treatments--in many ways mimicking how clinicians operate in practice. This proposal will develop a novel clinician-in-the-loop reinforcement learning (RL) framework that analyzes electronic health record (EHR) clinical time-series data to support physician decision making, iteratively providing physicians the estimated outcome of potential treatment strategies. Our topic of focus for this work is the evaluation and treatment of patients hospitalized with acute dyspnea (shortness of breath) and signs of impending respiratory failure. Acute dyspnea is an ideal condition for an RL approach, since it can be due to three overlapping conditions: congestive heart failure, chronic obstructive pulmonary disease and pneumonia. Determining optimal treatment for these patients is clinically difficult, as a patient's presentation is frequently ambiguous, rapidly changing, and often due to multiple causes. Inappropriate treatment may occur in up to a third of patients leading to increased mortality. While developing this RL framework, we will also develop methods to learn more useful representations of high-dimensional clinical time-series data to improve the efficiency of RL model training. In addition, given the challenges of working with observational health data, we will develop new methods for evaluation of learned policies and develop new theory to better understand the limitations of RL using observational data. The project has four aims: 1) create a shareable, de-identified EHR time-series dataset of 35,000 patients with acute dyspnea, 2) develop techniques for exploiting invariances In tasks involving clinical time-series data to improve the efficiency of RL model training, 3) develop and evaluate an RL-based framework for learning optimal treatment policies for acute dyspnea, and 4) prospectively validate the learned treatment model. This research will result in new techniques for learning representations from time-series data and will study both the theoretical and practical limitations of RL using observational clinical data, leading to key advancements in ML and RL for clinical care. The tools developed for clinical decision support in this proposal have the potential for high impact because of their ability to generalize beyond the problem studied here to other conditions, laying the groundwork for clinical systems that directly impact society by aiding in the timely and appropriate treatment of patients.

在正确的时间将正确的患者与正确的治疗方法快速匹配的能力对于确保患者 得到高质量的护理。医疗保健领域的绝大多数机器学习应用都专注于诊断或 对患者进行特定结果的分层。相比之下，强化学习（RL）旨在学习临床状态如何 (i.e.,体征、症状和检测结果）对特定治疗序列有反应，目的是 优化临床结果。RL的目的不是诊断，而是根据患者对以下问题的反应推断诊断： 具体的治疗--在许多方面模仿临床医生在实践中的操作。这一提议将发展出一部小说 临床医生在环强化学习（RL）框架，分析电子健康记录（EHR）临床 时间序列数据，以支持医生的决策，迭代地为医生提供估计的结果， 潜在的治疗策略。我们这项工作的重点是对住院患者的评估和治疗 伴有急性呼吸困难（呼吸短促）和呼吸衰竭即将发生的体征。急性呼吸困难是理想的 RL方法的条件，因为它可能是由于三个重叠的条件：充血性心力衰竭，慢性 阻塞性肺病和肺炎。确定这些患者的最佳治疗在临床上是困难的， 因为患者的表现经常是模糊的，快速变化的，并且通常是由于多种原因。 多达三分之一的患者可能发生不适当的治疗，导致死亡率增加。在开发这个 RL框架，我们还将开发方法来学习更有用的表示高维临床 时间序列数据，以提高RL模型训练的效率。此外，鉴于与联合国合作的挑战， 观察健康数据，我们将开发新的方法来评估学习的政策，并开发新的理论， 使用观测数据更好地理解RL的局限性。该项目有四个目标：1）创建一个可共享的， 35，000例急性呼吸困难患者的去识别EHR时间序列数据集，2）开发技术， 在涉及临床时间序列数据的任务中，为了提高RL模型训练的效率，3）开发和 评估基于RL的框架，以学习急性呼吸困难的最佳治疗策略，以及4）前瞻性 验证学习的治疗模型。这项研究将导致新的技术，学习表征从 时间序列数据，并将使用观察性临床数据研究RL的理论和实践局限性， 导致临床护理ML和RL的关键进步。为临床决策支持开发的工具， 这些建议有可能产生很大的影响，因为它们有能力超越这里研究的问题， 其他条件，为通过及时和及时地提供援助直接影响社会的临床系统奠定基础， 对患者进行适当治疗。