Improved multifactorial prediction of suicidal behavior through integration of multiple datasets

通过整合多个数据集改进自杀行为的多因素预测

• 批准号: 9762979
• 负责人: Ben Y Reis
• 金额: $ 51.4万
• 依托单位: MASSACHUSETTS GENERAL HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-08-13 至 2022-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9762979
• 关键词: Accounting; Adoption; Calibration; Cause of Death; Cessation of life; Chronology; Clinical; Clinical Data; Complex; Data; Data Element; Data Set; Databases; Electronic Health Record; Event; Feeling suicidal; Future; Goals; Health; Health Professional; Healthcare; Healthcare Systems; Hospitalization; Individual; Information Resources; Intervention; Legal; Life; Link; Machine Learning; Maps; Markov Chains; Medical; Medical Records; Methods; Modeling; Natural Language Processing; Outcome; Patient Self-Report; Patients; Pattern; Performance; Platelet Factor 4; Records; Reporting; Research; Research Domain Criteria; Resources; Risk; Risk Behaviors; Risk Factors; Sampling; Sensitivity and Specificity; Source; Structure; Suicide; Suicide attempt; Techniques; Testing; Text; Time; United States; Work; base; clinical risk; clinically relevant; data resource; discrete time; electronic structure; health care settings; high risk; improved; improved outcome; learning strategy; markov model; novel; predictive modeling; process repeatability; risk prediction model; sociodemographics; socioeconomics; success; suicidal behavior; suicidal risk; suicide rate; tool

Suicide is the tenth leading cause of death in the United States, accounting for more than 40,000 deaths annually. Despite ongoing efforts to reduce the burden of suicide and suicidal behavior, rates have remained relatively constant over the past half century. Attempts to predict suicidal behavior have relied almost exclusively on self-reporting of suicidal thoughts and intentions. This is problematic because of well-known reporting biases and the fact that many people at high risk are motivated to deny suicidal thoughts to avoid hospitalization. Even though the majority of all suicide decedents have contact with a healthcare professional in the month before their death, suicide risk is rarely detected in such cases. Efforts to identify risk factors have also been stymied by the fact that suicide is a low-base rate event so that very large samples are needed to test the complex combinations of factors that are likely to contribute to risk. The widespread adoption of longitudinal electronic health records (EHRs) has created a powerful but still under-utilized resource for detecting and predicting important health outcomes. In prior work using machine learning methods to analyze structured EHR data, we have developed predictive models that detect up to 45% of first-episode suicidal behavior, on average 3 years in advance. Here we aim to systematically extend and improve our EHR prediction methods in a large healthcare system (N = 4.6 million patients) by incorporating 1) external public record datasets (LexisNexis SocioEconomic Health Attribute data) that include environmental, socioeconomic, and life event information; 2) natural language processing (NLP) to leverage unstructured EHR text, including text-based scores that capture RDoC domains; 3) a novel method of deriving temporal risk envelopes to capture the time-dependent effects of individual risk factors; and 4) clinical risk trajectories that incorporate ordered temporal sequences of risk factors. We will systematically compare the performance of each of these approaches to identify optimal strategies for enhancing risk surveillance and prediction in healthcare settings. Completion of these aims would represent a crucial step towards novel, clinically deployable, and potentially transformative tools for improving outcomes for those at risk for suicide and suicidal behavior.

自杀是美国第十大死因，导致超过 40,000 人死亡 每年。尽管不断努力减轻自杀和自杀行为的负担，但自杀率仍然很高 过去半个世纪相对稳定。预测自杀行为的尝试几乎依赖于 专门针对自杀想法和意图的自我报告。这是有问题的，因为众所周知 报告偏见以及许多高危人群有动机否认自杀念头以避免自杀的事实 住院治疗。尽管大多数自​​杀死者都与医疗保健专业人员有过联系 在此类案件中，在死亡前一个月，很少发现自杀风险。识别风险因素的努力已经 自杀是一种低基准率事件，因此需要非常大的样本来进行研究，这一事实也阻碍了研究 测试可能导致风险的因素的复杂组合。广泛采用 纵向电子健康记录 (EHR) 为患者创造了强大但仍未得到充分利用的资源 检测和预测重要的健康结果。在之前的工作中使用机器学习方法来分析 结构化 EHR 数据，我们开发了预测模型，可以检测高达 45% 的首发自杀行为 行为，平均提前 3 年。我们的目标是系统地扩展和改进我们的 EHR 大型医疗保健系统（N = 460 万名患者）中的预测方法，包括 1) 外部公众 记录数据集（LexisNexis 社会经济健康属性数据），包括环境、社会经济、 以及生活事件信息； 2) 自然语言处理 (NLP)，以利用非结构化 EHR 文本，包括 捕获 RDoC 域的基于文本的分数； 3）一种推导时间风险包络的新方法 捕获个体风险因素随时间变化的影响； 4) 临床风险轨迹，其中包括 风险因素的有序时间序列。我们将系统地比较每一个的性能 确定加强医疗保健环境中风险监测和预测的最佳策略的方法。 这些目标的完成将代表着向新颖的、临床上可部署的和潜在的方向迈出了关键的一步。 改善有自杀风险和自杀行为的人的结果的变革性工具。