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: 10611439
• 负责人: Patrick M. Carter
• 金额: $ 58.64万
• 依托单位: UNIVERSITY OF MICHIGAN AT ANN ARBOR
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-04-15 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10611439
• 关键词: 20 year old; Accident and Emergency department; Address; Admission activity; Adolescent; Affect; African American; African American population; Aggressive behavior; Artificial Intelligence; Behavior; Behavior Therapy; Caucasians; Cause of Death; Clinical; Communities; Computational algorithm; Computer Systems; Criminal Justice; Decision Making; Development; Disadvantaged; Disparity; Dose; Emergency Care; Emergency department visit; Enrollment; Environment; Equilibrium; Event; Feedback; Future; Health; Health Resources; Health Services Accessibility; Heterogeneity; Homicide; Hospitals; Imprisonment; Injury; Intervention; Learning; Link; Longitudinal Studies; Managed Care; Managed Care Programs; Measures; Mental Health; Modality; Outcome; Outcome Assessment; Participant; Patients; Pattern; Performance; Persons; Population; Process; Psychological reinforcement; Public Health; Remote session; Resources; Risk; Risk Behaviors; Sampling; Services; Severities; Standardization; Statistical Models; Symptoms; Telephone; Testing; Text Messaging; Therapeutic Intervention; Time; Transportation; Treatment Efficacy; Treatment Protocols; Urban Community; Variant; Victimization; Violence; Violent injury; Work; Youth; access disparities; arm; artificial intelligence algorithm; automated text message; comparative efficacy; cost; efficacious intervention; experience; gun violence; high risk; improved; inattention; innovation; intervention delivery; learning algorithm; minority children; neighborhood disadvantage; outcome disparities; patient response; personalized medicine; preservation; primary outcome; protective factors; recidivism; remote therapy; secondary outcome; societal costs; socioeconomic disadvantage; substance use; success; telephone delivery; theories; treatment response; treatment strategy; two way texting; video chat; violence prevention; youth violence

Youth violence is a key public health problem. Homicide is a leading cause of death among adolescents (age:14- 20) and disproportionately impacts African-American populations. Urban EDs are a critical opportunity for violence prevention, especially with >600,000 adolescents/year seeking treatment for violence-related injuries. In our longitudinal study of violently-injured adolescents 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 the importance of the problem, strategies to decrease repeat violence after an ED visit have not been well studied. Given our prior work demonstrating that theoretically-based single session ED interventions are efficacious reducing violence among 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 and addressed problems identified in prior multisession interventions (e.g., transportation) with the addition of remote therapy delivery (e.g., phone). While innovative and promising, this S-RTI approach is resource intensive and does not address heterogeneity in treatment responses. By contrast, adaptive treatment strategies allow for “just-in-time” tailoring that provides a balance between too much and not enough intervention and enhances outcomes while reducing the use of costly resources. 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 propose to test two versions of our RTI, a standard RTI condition (S-RTI) comprised of a single ED session followed by 8 remote therapy sessions, and an adaptive RTI version (AI-RTI) optimized by reinforcement learning to step up or down the intensity of treatment between three levels (i.e., remote therapy sessions, automated two- way text messaging, assessment only) based on patient response to daily text message assessments. The specific aims are: 1) To refine and adapt our RTI for delivery using two packages (S-RTI; AI-RTI); 2) To conduct a 3-arm RCT enrolling 900 violently-injured adolescents seeking ED care (age:14-20) to compare the efficacy of S-RTI (n=300), AI-RTI (n=400), and a control condition (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, helpfulness/likability). Primary outcomes (assessed at 4-, 8-, and 12-months) include aggression, victimization, and ED recidivism for violent injury. Secondary outcomes include substance use, mental health symptoms, and criminal justice involvement. As a secondary aim, we will compare resource utilization (i.e., costs/event averted) for the active intervention conditions. Given elevated rates of violence among socio-disadvantaged youth with disparities in access to services, the proposed study has the potential for significant public health impact.

青少年暴力是一个重要的公共卫生问题。凶杀是青少年（14 岁至 14 岁）死亡的主要原因。 20）并对非裔美国人产生了不成比例的影响，城市急诊室是一个重要的机会。 预防暴力，特别是每年有超过 600,000 名青少年因暴力相关伤害而寻求治疗。 在我们对城市急诊室遭受暴力伤害的青少年的纵向研究中，我们发现 2 年内，37% 的青少年返回 对于重复的暴力伤害，59% 的人经历过枪支暴力，38% 的人被捕，1% 的人死亡。 鉴于这个问题的重要性，尚未对急诊就诊后减少重复暴力的策略进行充分研究。 鉴于我们之前的工作证明基于理论的单次急诊干预是有效的 为了减少低风险青少年中的暴力行为，该疗法的应用范围扩大到解决更多问题 多次治疗后问题的严重性并通过包括护理管理而得到加强，代表了潜在的 我们最近的试点是改变高风险暴力伤害青少年的风险轨迹的有效方法。 这种方法 (S-RTI) 受到好评，并解决了之前多次干预中发现的问题 （例如交通）加上远程治疗交付（例如电话）虽然具有创新性和前景， 这种 S-RTI 方法是资源密集型的，并且不能解决治疗反应的异质性。 相比之下，适应性治疗策略允许“及时”调整，在过多的治疗之间提供平衡。 没有足够的干预和改善结果，同时减少昂贵资源的使用。 学习是一个人工智能领域，它允许计算机系统从先前的成功中“学习” 治疗方法，是构建适应性“及时”干预措施的一种有前途的方法。 建议测试我们的 RTI 的两个版本，标准 RTI 条件 (S-RTI) 由单个 ED 会话组成 接下来是 8 次远程治疗课程，以及通过强化学习优化的自适应 RTI 版本 (AI-RTI) 在三个级别之间提高或降低治疗强度（即远程治疗课程、自动两级治疗） 方式短信，仅评估）基于患者对每日短信评估的反应。 具体目标是： 1) 改进和调整我们的 RTI，以便使用两个包（S-RTI；AI-RTI）进行交付； 一项 3 组随机对照试验，招募了 900 名寻求 ED 护理的遭受暴力伤害的青少年（年龄：14-20 岁），以比较以下方法的疗效 S-RTI (n=300)、AI-RTI (n=400) 和控制条件 (n=200)；以及， 3) 评估 AI-RTI 的适应性； 强化学习算法，通过比较前 50% 的参与者与后 50% 的流程变量（例如参与度、 主要结果（在 4 个月、8 个月和 12 个月时评估）包括攻击性、受害性、 暴力伤害累犯的次要结果包括药物使用、心理健康症状和 作为次要目标，我们将比较资源利用率（即避免的成本/事件）。 鉴于社会弱势青年的暴力发生率较高， 鉴于获得服务方面的差异，拟议的研究有可能对公共卫生产生重大影响。