DeepCOPD: Development and Implementation of Deep Learning to Predict and Prevent COPD Health Care Encounters

DeepCOPD：开发和实施深度学习来预测和预防慢性阻塞性肺病医疗保健遭遇

• 批准号: 10542393
• 负责人: Jeremiah R Brown
• 金额: $ 74.16万
• 依托单位: DARTMOUTH COLLEGE
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-12-20 至 2025-11-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10542393
• 关键词: Acceleration; Acute; Adoption; Adverse event; Ambulatory Care; Automated Annotation; Calibration; Caregivers; Caring; Chronic; Chronic Obstructive Pulmonary Disease; Clinic; Clinical; Code; Communities; Consumption; Controlled Vocabulary; Data; Detection; Development; Diagnosis; Dimensions; Disease; Disease Progression; Early identification; Electronic Health Record; Event; Financial Hardship; Future; Health; Health Personnel; Health Policy; Health system; Healthcare; Healthcare Systems; Home; Hospitalization; Human; Individual; Ingestion; Machine Learning; Maintenance; Manuals; Maps; Medical; Methods; Modeling; National Heart, Lung, and Blood Institute; Natural Language Processing; Nature; Outcome; Outpatients; Oxygen; Oxygen Therapy Care; Patient Care; Patient Care Management; Patients; Performance; Persons; Physicians; Procedures; Process; Provider; Recording of previous events; Research; Resources; Risk; Risk Factors; Structure; Symptoms; System; Techniques; Text; Time; Update; Validation; Visit; Visualization; biomedical informatics; clinical application; clinical care; clinical implementation; cost; data streams; data visualization; deep learning; deep learning algorithm; deep learning model; discrete data; end stage disease; functional status; health care delivery; health care service utilization; high risk; hospital readmission; improved; learning strategy; machine learning method; predictive modeling; predictive tools; prevent; programs; prospective; readmission risk; social; structured data; support tools; tool; unstructured data; usability; user centered design; web site

In the US, ~24 million persons live with COPD, half undiagnosed, and ~150,000 die of COPD annually. COPD causes over 700,000 US hospitalizations and costs nearly $50 billion per year. The human and financial burdens of COPD could likely be reduced if disease progression and other adverse events could be anticipated, enabling caregivers to focus finite resources on at-risk patients. We propose to create a decision-support tool that integrates biomedical informatics with advanced machine learning (ML) and deep learning (DL) algorithms to predict acute and chronic healthcare encounters (hospital admissions, readmissions, and ED encounters) and major disease progression events (home oxygen therapy) for outpatients with COPD. Such a tool would confer immediate clinical benefits and accelerate research on COPD disease progression and treatment. Predictive modeling is widely used to identify high-risk patients for care management in COPD and other disorders, with a strong emphasis on readmission risk. However, extant techniques are not sufficiently accurate and do not identify the specific nature of likely future medical events, estimate time-to-event, and specifically forecast medical encounters and disease progression events for individuals with COPD. Recent research in disease progression modeling support the application of DL and other ML methods to electronic health records (EHRs) to predict aspects of health history. EHRs contain both readily accessible structured data (e.g., lab results in well-defined fields) and unstructured texts such as physician’s notes. Unstructured texts contain a great deal of clinical information, but this information is laborious to access; impeding its routine use in research and the clinic. This has motivated attempts to use natural language processing (NLP) methods to automate annotation. We will apply NLP to identify symptoms, treatments, procedures, diagnoses, social risk factors, and functional status from clinical notes, expanding the data available from EHRs far beyond the usual coded variables. Also, and distinctively, we will carry out a stepped-wedge clinical implementation of the proposed predictive tool and evaluate its performance, a first for ML and DL prediction of COPD health events. Therefore, we propose four Specific Aims: AIM 1: Transform EHR data streams to provision patient-level feature sets for ML and DL consumption. AIM 2: Develop a set of ML and DL models to predict the time-to-event for home oxygen therapy initiation and healthcare encounters among patients with COPD. AIM 3: To develop and implement a prospective performance surveillance and calibration maintenance system to maintain the final Aim 2 model for each outcome. AIM 4: Evaluate adoption and usability of the DeepCOPD toolkit in near-realtime clinical use in two healthcare systems. The application is responsive to the NHLBI IDEA2Health (NOT-HL-19-712).

在美国，约 2400 万人患有慢性阻塞性肺病，其中一半未得到诊断，约 15 万人死于慢性阻塞性肺病 慢性阻塞性肺病每年导致超过 70 万人住院，花费近 500 亿美元。 如果疾病进展和其他方面的进展，慢性阻塞性肺病的人力和经济负担可能会减少 不良事件是可以预见的，使护理人员能够将有限的资源集中在高危患者身上。 我们建议创建一个将生物医学信息学与先进技术相结合的决策支持工具 用于预测急慢性医疗保健的机器学习 (ML) 和深度学习 (DL) 算法 遭遇（入院、再入院和急诊室遭遇）和主要疾病进展 为慢性阻塞性肺病门诊患者提供紧急事件（家庭氧疗），这样的工具可以立即进行临床治疗。 益处并加速 COPD 疾病进展和治疗的研究。 广泛用于识别慢性阻塞性肺病和其他疾病的高危患者进行护理管理，具有 然而，现有的技术不够准确并且确实如此。 无法识别未来可能发生的医疗事件的具体性质，无法估计事件发生的时间，特别是 预测 COPD 患者近期的医疗遭遇和疾病进展事件。 疾病进展建模研究支持深度学习和其他机器学习方法的应用 电子健康记录 (EHR) 可以轻松预测健康史的各个方面。 可访问的结构化数据（例如，定义明确的字段中的实验室结果）和非结构化文本，例如 非结构化文本包含大量临床信息，但这些信息是 难以获取；阻碍了其在研究和临床中的常规使用。 使用自然语言处理（NLP）方法来自动化注释我们将应用NLP来识别。 临床症状、治疗、手术、诊断、社会风险因素和功能状态 指出，电子病历中可用的数据远远超出了通常的编码变量。 与众不同的是，我们将对所提出的预测工具进行阶梯式临床实施 并评估其性能，这是 COPD 健康事件的 ML 和 DL 预测的首次。 四项提出具体目标： 目标 1：转变 EHR 数据流以提供患者级别的功能集 针对 ML 和 DL 消费 AIM 2：开发一组 ML 和 DL 模型来预测事件发生时间。 慢性阻塞性肺病 (COPD) 患者的家庭氧疗开始和医疗保健遭遇 目标 3： 开发并实施前瞻性性能监视和校准维护系统 维护每个结果的最终目标 2 模型：评估目标的采用和可用性。 DeepCOPD 工具包在两个医疗保健系统中近实时临床使用。 响应 NHLBI IDEA2Health (NOT-HL-19-712)。