Developing Suicide Risk Algorithms for Diverse Clinical Settings using Data Fusion

使用数据融合开发针对不同临床环境的自杀风险算法

• 批准号: 10414116
• 负责人: Robert H Aseltine
• 金额: $ 77.9万
• 依托单位: UNIVERSITY OF CONNECTICUT SCH OF MED/DNT
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-16 至 2024-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10414116
• 关键词: Accreditation; Address; Adult; Algorithms; American; Award; Back; Caring; Cessation of life; Characteristics; Clinic; Clinical; Clinical Data; Clinical assessments; Connecticut; Data; Data Set; Data Sources; Databases; Development; Economics; Electronic Health Record; Elements; Goals; Health; Health Personnel; Health system; Healthcare; Healthcare Systems; Hospitals; Individual; Integrated Delivery Systems; Joints; Location; Machine Learning; Maintenance; Measures; Medical; Medical Records; Methods; Modeling; Nature; Neighborhood Health Center; Outpatients; Patients; Performance; Population; Primary Health Care; Process; Provider; Public Health; Recovery; Research; Risk; Risk Factors; Sensitivity and Specificity; Suicide; Suicide attempt; System; Techniques; Testing; United States; Variant; acute care; behavioral health; clinical care; clinical practice; clinical risk; data fusion; data mining; health care disparity; health care service organization; health care settings; health information technology; health plan; improved; innovation; medical specialties; meetings; multimodal data; patient population; patient safety; predictive modeling; predictive test; provider behavior; suicidal behavior; suicidal morbidity; suicidal risk; suicide mortality; transfer learning; urgent care

Suicide is one of the most serious public health problems facing the United States. Recent evidence indicates that many if not most of individuals who die by suicide have been in contact with the healthcare system in the months prior to their death, providing data that can be used to identify patients at risk prior to an attempt. The proposed project will develop an innovative method for identifying patients at risk of suicidal behavior using data from a large multistate health information exchange, integrated with data from the State of Connecticut’s CHIME hospital database. We will develop and test suicide risk algorithms using principles associated with transfer learning, in which information from a comprehensive external data source is used to improve prediction in a more limited dataset. Specifically, we will use multimodal data fusion techniques to develop and test algorithms that can identify patients at risk of suicidal behavior by clinicians in hospitals with limited numbers of patients, select patient populations, and lack of access to outpatient data. This approach is not only generalizable to hospitals throughout the US but can be extended to very diverse clinical settings, e.g., primary and specialty care practices, community health centers, urgent care clinics. The potential public health significance of this study is substantial. The fragmentation of the healthcare system, particularly in relation to patients’ behavioral health needs, highlights the critical need to cultivate comprehensive, system-wide approaches to identifying and managing at patients at risk of suicide.

自杀是美国面临的最严重的公共卫生问题之一。最近的证据表明 许多人，如果不是大多数人死于自杀的人都与医疗保健系统有过接触， 在他们死亡前几个月，提供可用于在尝试之前识别风险患者的数据。的 拟议的项目将开发一种创新的方法，用于识别有自杀行为风险的患者， 来自大型多州健康信息交换的数据，与康涅狄格州的数据相结合， CHIME医院数据库。我们将开发和测试自杀风险算法使用的原则与 迁移学习，其中来自全面外部数据源的信息用于提高 在更有限的数据集中进行预测。具体来说，我们将使用多模态数据融合技术来开发和 测试算法，可以识别患者在医院的临床医生有自杀行为的风险， 患者数量、选定的患者人群以及无法获得门诊数据。这种方法并不 仅可推广到整个美国的医院，但可扩展到非常多样化的临床环境，例如， 初级和专业护理实践，社区卫生中心，紧急护理诊所。 这项研究的潜在公共卫生意义是巨大的。医疗保健的碎片化 系统，特别是与患者的行为健康需求有关，突出了培养 全面的、系统性的方法来识别和管理有自杀风险的病人。