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.

青年暴力是一个关键的公共卫生问题。凶杀是青少年（14- 18岁）死亡的主要原因。 20)对非裔美国人的影响尤为严重。城市ED是一个关键的机会， 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寻求治疗。 在我们对城市急诊室暴力伤害青少年的纵向研究中，我们发现，在2年内，37%的人返回 对于重复暴力伤害，59%的人经历过枪支暴力，38%被捕，1%死亡。尽管 由于这一问题的重要性，减少艾德就诊后再次发生暴力的战略尚未得到充分研究。 鉴于我们先前的工作表明，基于理论的单次艾德干预是有效的 减少低风险青少年中的暴力，这种疗法的应用，扩大到解决更大的 多个会话的问题严重性，并通过包括护理管理来增强，代表了一种潜在的 改变高风险暴力伤害青少年的风险轨迹的有效方法。我们最近的飞行员 这种方法（S-RTI）受到了广泛的欢迎，并解决了以前多次干预中发现的问题 (e.g.,运输）加上远程治疗递送（例如，电话）。虽然创新和有前途， 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。通过 相比之下，适应性治疗策略允许“及时”调整， 没有足够的干预和提高成果，同时减少使用昂贵的资源。加固 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”。 这是一种很有前途的方法来构建适应性的“及时”干预措施。在这项研究中，我们 我建议测试两个版本的RTI，一个标准的RTI条件（S-RTI）由一个单一的艾德会话 随后是8个远程治疗会话，以及通过强化学习优化的自适应RTI版本（AI-RTI） 为了在三个水平之间逐步提高或降低治疗强度（即，远程治疗，自动化的两个- 短信方式，仅评估），基于患者对每日短信评估的反应。的 具体目标是：1）改进和调整我们的RTI，使用两个包（S-RTI; AI-RTI）交付; 2）进行 一项3组随机对照试验，纳入900名寻求艾德护理的暴力伤害青少年（年龄：14-20岁），以比较 S-RTI（n=300）、AI-RTI（n=400）和对照条件（n=200）;以及3）评价AI-RTI的适应性 RL算法，通过比较前50%的登记者与后50%的登记者对过程变量（例如，参与， 乐于助人/讨人喜欢）。主要结果（在4个月、8个月和12个月时评估）包括攻击、受害、 以及暴力伤害的艾德累犯次要结果包括物质使用，心理健康症状， 刑事司法介入。作为次要目标，我们将比较资源利用率（即，费用/避免的事件） 积极干预的条件。鉴于社会弱势青年的暴力行为发生率上升， 由于在获得服务方面存在差距，拟议的研究有可能对公共卫生产生重大影响。