Using Re-inforcement Learning to Automatically Adapt a Remote Therapy Intervention (RTI) for Reducing Adolescent Violence Involvement

使用强化学习自动调整远程治疗干预 (RTI)，以减少青少年暴力参与

• 批准号: 10834339
• 负责人: Patrick M. Carter
• 金额: $ 49.69万
• 依托单位: UNIVERSITY OF MICHIGAN AT ANN ARBOR
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10834339
• 关键词: Accident and Emergency department; Address; Administrative Supplement; Adolescent; Affect; African American; African American population; Aggressive behavior; Algorithms; Artificial Intelligence; Behavior Therapy; Cause of Death; Clinical; Clinical Trials; Computer Systems; Criminal Justice; Disadvantaged; Electronics; Emergency Care; Emergency department visit; Enrollment; Equilibrium; Funding; Goals; Health Services Accessibility; Heterogeneity; Homicide; Injury; Intervention; Learning; Managed Care; Mental Health; Outcome; Population; Process; Psychological reinforcement; Public Health; Remote session; Research; Resources; Risk; Sampling; Severities; Site; Surveys; Symptoms; Telephone; Testing; Text Messaging; Therapeutic Intervention; Time; Transportation; Urban Community; Victimization; Violence; Violent injury; Work; Youth; access disparities; arm; artificial intelligence algorithm; assault; comparative efficacy; coronavirus disease; cost; efficacious intervention; experience; gun violence; health disparity; high risk; innovation; intervention delivery; patient response; preservation; primary outcome; recidivism; recruit; remote therapy; secondary outcome; stem; substance use; success; treatment response; violence prevention

Homicide is a leading cause of death for adolescents (age:14-24), disproportionately impacting African-American populations. Urban EDs are a critical opportunity for violence prevention, with >600,000 adolescents/year seeking treatment for violence-related injuries. In our study of violently-injured youth in urban EDs, we found that within 2-years, 37% returned for a repeat violent injury, 59% experienced firearm violence, 38% were arrested, and 1% died. Despite this, strategies to decrease repeat violence after an ED visit have not been well studied. Given our work demonstrating that single session ED interventions are efficacious reducing violence in lower risk adolescents, the application of this therapy, expanded to address greater problem severity over multiple sessions and enhanced by including care management, represents a potentially efficacious approach for altering risk trajectories of higher-risk violently-injured adolescents. Our recent pilot of this approach (S-RTI) was well received, addressing problems identified in prior multisession interventions (e.g., transportation) with the addition of remote therapy (e.g., phone). While innovative/promising, this S-RTI approach is resource intensive and does not address heterogeneity in treatment responses. By contrast, adaptive strategies allow for “just-in-time” tailoring that provides a balance between too much and not enough intervention and enhances outcomes while reducing cost. Reinforcement learning is an artificial intelligence domain that allows computer systems to “learn” from the success of prior treatments and is a promising approach to constructing adaptive “just-in-time” interventions. For this study, we are testing two versions of an RTI, a standard RTI condition (S-RTI) comprised of a single ED session followed by 5 remote sessions, and an adaptive RTI version (AI-RTI) optimized by reinforcement learning to step up/down the intensity of treatment between three levels (i.e., remote therapy, electronic bot messaging, assessment only) based on patient response to daily survey assessments. The original study aims were: 1) To refine/adapt our RTI for delivery using two packages (S-RTI; AI-RTI); 2) To conduct a 3- arm RCT enrolling 750 violently-injured adolescents seeking ED care (age:14-24) to compare efficacy of S-RTI (n=250), AI-RTI (n=300), and control (n=200); and, 3) To evaluate adaptability of the AI-RTI RL algorithm by comparing the first 50% of enrollees to the second 50% on process variables (e.g., engagement). Primary outcomes (6-, 12-months) include aggression and victimization. Secondary outcomes include ED recidivism for violent injury, substance use, mental health symptoms, and criminal justice involvement. While the current study holds promise for addressing elevated rates of violence, as well as key health disparities, among socio- disadvantaged youth, the clinical trial has experienced challenges stemming from COVID. This request for supplemental administrative funds is focused on adding a clinical recruitment site (to the currently enrolling sites), as well as clinical and research staff to avoid reducing scientific scope and to enhance the project’s ability to achieve the original study aims/goals, preserving the potential for high public health impact reducing violence.

凶杀是青少年（14-24岁）死亡的主要原因，对非洲裔美国人的影响不成比例。 人口。城市教育机构是预防暴力的重要机会，每年有超过60万青少年参加 寻求暴力相关伤害的治疗在我们对城市急诊室暴力伤害青少年的研究中，我们发现， 在2年内，37%的人因重复暴力伤害而返回，59%的人经历过枪支暴力，38%的人被捕， 1%死亡。尽管如此，减少艾德访视后重复暴力的策略尚未得到很好的研究。 鉴于我们的工作表明，单次艾德干预是有效的， 风险青少年，这种疗法的应用，扩大到解决更严重的问题，超过多个 会议和加强包括护理管理，代表了一个潜在的有效方法，改变 高风险暴力伤害青少年的风险轨迹。我们最近的试点这种方法（S-RTI）是很好的 收到，解决在以前的多个会议干预中发现的问题（例如，运输）， 远程治疗（例如，电话）。虽然具有创新性/前景，但这种S-RTI方法是资源密集型的， 没有解决治疗反应的异质性。相比之下，适应性策略允许“及时” 量体裁衣，在干预过多和干预不足之间提供平衡， 降低成本。强化学习是一个人工智能领域，它允许计算机系统“学习” 是一种很有前途的构建适应性“及时”的方法。 干预措施。在这项研究中，我们测试了两个版本的RTI，标准RTI条件（S-RTI）包括 单个艾德会话后接5个远程会话，自适应RTI版本（AI-RTI）通过以下方式优化： 强化学习以在三个级别之间逐步提高/降低治疗强度（即，远程治疗， 电子机器人消息传送，仅评估）基于患者对日常调查评估的响应。原始 研究的目的是：1）改进/调整我们的RTI，使用两个包（S-RTI; AI-RTI）交付; 2）进行3- 一项随机对照试验，纳入了750名寻求艾德护理的暴力伤害青少年（年龄：14-24岁），以比较S-RTI的疗效 （n=250）、AI-RTI（n=300）和对照（n=200）;以及，3）通过以下方式评估AI-RTI RL算法的适应性： 将前50%的加入者与后50%的加入者在过程变量上进行比较（例如，订婚）。初级 结果（6个月，12个月）包括攻击和受害。次要结局包括艾德复发， 暴力伤害，物质使用，心理健康症状和刑事司法参与。虽然目前的研究 有希望解决暴力率上升的问题，以及社会和经济发展中的主要健康差距， 由于是弱势青年，临床试验经历了COVID带来的挑战。本建议书征询文件 补充行政资金的重点是增加一个临床招募中心（到目前招募的中心）， 以及临床和研究人员，以避免减少科学范围，并提高项目的能力， 实现最初的研究目的/目标，保持减少暴力对公共卫生产生重大影响的潜力。