Project-001

项目-001

• 批准号: 10863455
• 负责人: MATTHEW K NOCK
• 金额: $ 89.09万
• 依托单位: MASSACHUSETTS GENERAL HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-08 至 2028-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10863455
• 关键词: Accident and Emergency department; Adherence; Adolescent; Algorithms; Behavior; Biometry; Boston; Caring; Cause of Death; Cessation of life; Clinical; Collaborations; Communities; Country; Data; Data Reporting; Data Science; Data Scientist; Decision Making; Dedications; Development; Economics; Education; Electronic Health Record; Emergency Department patient; Emergency department visit; Evaluation; General Hospitals; Goals; Grant; Health Personnel; Health system; Healthcare Systems; Hospital Administration; Hospitalization; Hospitals; Inpatients; Intervention; Learning; Massachusetts; Methods; Patient Self-Report; Patient risk; Patients; Persons; Prevention; Probability; Psychiatry; Psychology; Public Health Schools; Randomized; Research; Research Personnel; Research Project Grants; Risk; Safety; Scientific Advances and Accomplishments; Scientist; Societies; Structure; Suicide; Suicide attempt; Suicide prevention; Target Populations; Technology; Testing; Time; Training; Translating; Universities; Vision; Visit; Woman; Work; acute care; adaptive intervention; alternative treatment; biomedical informatics; career; clinical care; clinical decision support; clinical decision-making; clinical practice; community building; community partnership; computer science; digital; digital platform; effective therapy; effectiveness testing; health care settings; health data; high risk; implementation efforts; improved; innovation; innovative technologies; inpatient psychiatric settings; machine learning algorithm; machine learning prediction algorithm; medical schools; member; minority children; novel; outreach; population health; practice setting; predictive modeling; programs; randomized trial; risk prediction; risk stratification; social health determinants; statistics; suicidal behavior; suicidal risk; suicide rate; therapy development; tool; treatment optimization; trial design

Suicide is one of the leading causes of death worldwide and the 10th leading cause of death in the US. A major barrier to suicide prevention has been that the cutting-edge scientific advances that have occurred in the past few decades have not yet been translated and implemented into clinical practice settings. We propose the development of a practice-based Center for Suicide Research and Prevention (CSRP) that will support the development, deployment, and evaluation of practice-ready and deployment-focused interventions aimed at improving the identification and effective treatment of those at risk of suicide. This Center will be a collaborative effort between researchers, clinicians, and stakeholders at Mass General Brigham (MGB) and Harvard University. Our focus is on improving the identification and prevention of suicide-related behaviors (SRBs) among patients presenting for treatment at emergency departments (EDs) and psychiatric inpatient units. Decades of research have shown that 50% of people who die by suicide are seen in a healthcare setting within one month before their death, 40% visit an ED the year before their death, and the suicide rate is highest in the weeks immediately following discharge from a psychiatric inpatient hospitalization. Our first aim is to build and maintain a cohesive and innovative transdisciplinary Center dedicated to advancing suicide prevention. This will be accomplished via the work of our proposed Administrative Core and Methods Core. Our second aim is to conduct four practice-focused research projects that target prediction and prevention of suicidal behaviors in ED and inpatient settings. Our Signature Project (SIG) will implement a previously-develop machine learning prediction algorithm based on electronic health record (EHR) and self-report data collected in the ED and randomly assign the clinicians of 4,000 patients to receive (experimental condition) or not receive (control condition) the predicted probability that their patient will make a suicide attempt after ED discharge. We will test the impact of this intervention on the suicide attempt rate and clinician decision-making. The SIG also will examine clinician acceptability and adherence, prediction model improvement, and the development of treatment optimization rules regarding patients' likelihood of benefiting from hospitalization versus alternative treatments. Our three Exploratory Projects (EXP): (EXP1) will use the SIG prediction model to identify ED patients at risk of suicidal behavior and experimentally test the effectiveness of an enhanced outreach intervention administered in collaboration with a community partner – Samaritans of Boston; (EXP2) will implement and test EHR-based risk algorithms in two inpatient units with a special focus on the use of social determinants of health to improve prediction among under-represented adolescents; and (EXP3) will test a just-in-time adaptive intervention using an innovative micro-randomized trial design to connect at-risk patients with care when needed most. The third aim of the Center is to support education, dissemination, and implementation efforts that will have a significant and sustained effect on suicide prevention.

自杀是全球主要死亡原因之一，也是美国第十大死亡原因。一个主要 自杀预防的一个障碍是，过去发生的尖端科学进步 几十年来尚未转化并实施到临床实践环境中。我们建议 建立一个以实践为基础的自杀研究和预防中心（CSRP）， 制定、部署和评价随时可用和注重部署的干预措施， 改善对有自杀风险者的识别和有效治疗。该中心将是一个合作 麻省总布里格姆（MGB）和哈佛的研究人员、临床医生和利益相关者之间的努力 大学我们的重点是改善自杀相关行为（SRB）的识别和预防 在急诊科（ED）和精神科住院部就诊的患者中。 几十年的研究表明，50%的自杀者是在医疗保健环境中被发现的。 40%的人在死前一年去看过艾德， 从精神病住院患者出院后立即数周。我们的第一个目标是建立和 保持一个有凝聚力和创新的跨学科中心，致力于推进自杀预防。这 将通过我们提议的行政核心和方法核心的工作来完成。我们的第二个目标 是进行四个以实践为重点的研究项目，目标是预测和预防自杀行为 在艾德和住院患者中。我们的签名项目（SIG）将实现一个以前开发的机器学习 基于电子健康记录（EHR）和在艾德收集的自我报告数据的预测算法， 随机分配4，000名患者的临床医生接受（实验条件）或不接受（对照 条件）的预测概率，他们的病人将作出自杀企图后，艾德出院。我们将测试 这种干预对自杀未遂率和临床医生决策的影响。SIG还将 检查临床医生的可接受性和依从性，预测模型的改进，以及 关于患者从住院与替代治疗中获益的可能性的治疗优化规则 治疗。我们的三个探索性项目（EXP）：（EXP 1）将使用SIG预测模型来识别艾德 有自杀行为风险的患者，并通过实验测试加强外展的有效性 与社区伙伴-波士顿撒玛利亚人合作实施干预;（EXP 2）将 在两个住院单位实施和测试基于EHR的风险算法，特别关注社会 健康的决定因素，以改善代表性不足的青少年的预测;和（EXP 3）将测试一个 采用创新的微随机试验设计，及时进行适应性干预，以连接高危患者 在最需要的时候照顾。中心的第三个目标是支持教育、传播和 这将对预防自杀产生重大和持续的影响。