Can suicide theory-guided natural language processing of clinical progress notes improve existing prediction models of Veteran suicide mortality?

自杀理论指导的临床进展笔记自然语言处理能否改善现有的退伍军人自杀死亡率预测模型？

• 批准号: 10187800
• 负责人: Alex Sox-Harris
• 金额: --
• 依托单位: VETERANS ADMIN PALO ALTO HEALTH CARE SYS
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-06-01 至 2024-11-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10187800
• 关键词: Age; Area; Attention; Automated Annotation; Caring; Clinical; Data; Data Collection; Data Science; Detection; Development; Electronic Health Record; Ensure; Event; Feeling hopeless; Feeling suicidal; Female; Gender; Goals; Information Retrieval; Intervention; Knowledge; Language; Leadership; Linguistics; Machine Learning; Maps; Medical; Medicine; Mental Health; Methodology; Methods; Modeling; Natural Language Processing; Nomenclature; Ontology; Pain; Patients; Performance; Readability; Research; Resources; Risk Assessment; Risk Behaviors; Risk Factors; Signal Transduction; Structure; Suicide; Suicide attempt; Suicide prevention; System; Systematized Nomenclature of Medicine; Target Populations; Text; Time; Translating; Veterans; Veterans Health Administration; clinical encounter; clinical practice; concept mapping; data repository; data warehouse; design; hands-on learning; high risk; implementation facilitation; improved; innovation; machine learning algorithm; novel; phrases; predictive modeling; psychologic; random forest; reducing suicide; risk prediction model; structured data; suicidal behavior; suicidal morbidity; suicidal risk; suicide mortality; suicide rate; support vector machine; text searching; theories; tool

Background: Reducing suicide and suicide attempts among U.S. Veterans is a major national priority, as more than 6,000 Veterans die by suicide every year and many more attempt suicide. In 2017, the most recent year for which data are available, the suicide rate among Veterans was 1.5 times the rate of non-Veterans, and the suicide rate among female Veterans was 2.2 times the rate of non-Veteran females. Current VHA suicide risk prediction models suffer from high numbers of false negatives - Veterans not deemed at high risk of suicide who do attempt or die by suicide. These suicide prediction models have not incorporated the rich information from clinical progress notes that may improve our ability to predict suicidal behavior. Much of this information in clinical progress notes is unstructured free text. A suicide-specific ontology and information extraction system that can extract suicide-related information from unstructured clinical progress notes is not available. Significance/Impact: Enhancing VHA's ability to identify Veterans who are most likely to attempt suicide ensures that limited intervention resources can be focused on Veterans with the highest risk, before they attempt suicide or die by suicide. The proposed study is well-aligned with priorities for HSR&D research and with VA strategic goals for 2018 – 2024 set out by VA leadership, who listed suicide prevention as “VA's highest clinical priority.” Innovation: Our key methodological innovation is to pair a state-of-the-art theoretical framework (3-step Theory of Suicide) to predict who is most likely to act on their suicidal thoughts with state-of-the-art data science methods (NLP, machine learning). Since our suicide-theory concepts, that is hopelessness, connectedness, psychological pain, and capacity for suicide, are not represented in structured patient data, we will develop novel NLP and information extraction tools and apply them to clinical progress notes, the potential of which has not been fully levied to improve suicide prediction models. Specific Aims: We have three specific aims: 1. Develop a suicide-specific ontology for machine recognition of hopelessness, connectedness, psychological pain, and capacity for suicide in progress notes of clinical encounters with Veterans who attempted or died by suicide. 2. Extract information on the presence and intensity of hopelessness, connectedness, psychological pain, and capacity for suicide in clinical progress notes and describe change in these concepts in proximity of a suicide or suicide attempt. 3. Determine the predictive validity of hopelessness, connectedness, psychological pain, and capacity for suicide regarding Veteran suicide attempts and mortality in two prediction models that VA currently uses in clinical practice: STORM and REACHVET. Methodology: The proposed mixed-methods study has an exploratory sequential design where a qualitative component (Aim 1) informs quantitative analyses (Aims 2 and 3). Data collection will be from existing clinical progress notes in VHA's Corporate Data Warehouse, VA's Suicide Prevention Applications Network and from the VA/DoD Suicide Data Repository. We will use linguistic annotation and thematic analysis for Aim 1 and natural language processing and machine learning models for Aims 2 and 3. The target population is Veterans who receive care through VHA. Next Steps/Implementation: Our most important next step is to be in regular contact with local and national colleagues at the VA Office of Mental Health and Suicide Prevention (OMHSP) to facilitate implementation of our results in the operational versions of STORM and REACHVET.

背景：减少美国退伍军人的自杀和自杀未遂是国家的一项重大优先事项，因为 每年有超过 6,000 名退伍军人自杀身亡，最近一次是 2017 年，更多退伍军人尝试自杀。 根据现有数据，退伍军人的自杀率是非退伍军人的 1.5 倍，并且 女性退伍军人的自杀率是当前 VHA 女性非退伍军人自杀率的 2.2 倍。 风险预测模型存在大量误报 - 退伍军人不被认为具有高风险 这些自杀预测模型并未将富人纳入其中。 临床进展的信息表明，这可能会提高我们预测自杀行为的能力。 临床进展笔记中的信息是非结构化的自由文本，是针对自杀的本体论和信息。 可以从非结构化临床进展记录中提取自杀相关信息的提取系统并不存在 可用的。 意义/影响：增强 VHA 识别最有可能试图自杀的退伍军人的能力 确保有限的干预资源可以集中在风险最高的退伍军人身上，然后再 拟议的研究与 HSR&D 研究的优先事项非常一致。 VA 领导层制定了 VA 2018 – 2024 年战略目标，其中将预防自杀列为“VA 临床优先级最高。” 创新：我们的关键方法创新是将最先进的理论框架（三步 自杀理论）利用最先进的数据预测谁最有可能按照自杀想法采取行动 科学方法（NLP，机器学习）自从我们的自杀理论概念以来，那就是绝望， 连通性、心理痛苦和自杀能力并未在结构化患者数据中体现，我们 将开发新颖的 NLP 和信息提取工具并将其应用于临床进展记录，潜在的 其中尚未完全用于改善自杀预测模型。 具体目标：我们有三个具体目标： 1. 开发一种针对自杀的本体论，用于机器识别绝望、关联性、 心理痛苦和自杀能力的进展记录与退伍军人的临床接触 企图自杀或自杀身亡。 2. 提取有关绝望、联系、心理痛苦的存在和强度的信息， 和临床进展中的自杀能力记录并描述这些概念的变化 自杀或自杀未遂。 3. 确定绝望、联系、心理痛苦和能力的预测有效性 退伍军人自杀企图和死亡率的自杀率目前有两个预测模型 临床实践中的用途：STORM 和 REACHVET。 方法：拟议的混合方法研究采用探索性序贯设计，其中定性研究 组件（目标 1）为定量分析提供信息（目标 2 和 3）数据收集来自现有的临床。 VHA 企业数据仓库、VA 自杀预防应用网络以及来自 我们将为目标 1 和 VA/DoD 自杀数据库使用语言注释和主题分析。 目标 2 和 3 的自然语言处理和机器学习模型。目标人群是退伍军人 通过 VHA 接受护理的人。 后续步骤/实施：我们下一步最重要的步骤是与当地和国家定期联系 退伍军人管理局心理健康和自杀预防办公室 (OMHSP) 的同事们致力于促进实施 我们在 STORM 和 REACHVET 运行版本中的结果。