SCH: ChangeGradients: Promoting Adolescent Health Behavior Change with Clinically Integrated Sample-Efficient Policy Gradient Methods

SCH：ChangeGradients：通过临床整合的样本有效政策梯度方法促进青少年健康行为改变

• 批准号: 10532143
• 负责人: ELIZABETH M OZER
• 金额: $ 23.11万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-12-13 至 2024-11-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10532143
• 关键词: Adolescent; Adolescent Behavior; Alcohol consumption; Behavior; Behavior Therapy; Behavioral; Clinic; Clinical; Complement; Computer software; Data; Development; Environment; Ethnic Origin; Feedback; Foundations; Generations; Health; Health Personnel; Health behavior; Health behavior change; Home; Individual; Intervention; Investigation; Learning; Link; Machine Learning; Malignant Neoplasms; Methods; Modeling; Outcome; Outpatients; Patient Recruitments; Pediatrics; Policies; Population Heterogeneity; Portal System; Positioning Attribute; Preventive; Preventive healthcare; Psychological reinforcement; Public Health; Research; Research Personnel; Risk; Risk Behaviors; Risk Factors; Sampling; Screening procedure; Self Efficacy; Shapes; Social Environment; Structure; System; Tablets; Visit; Work; adolescent health; adolescent health outcomes; adolescent patient; behavior change; behavioral health; behavioral outcome; binge drinking; clinical practice; computer infrastructure; dashboard; design; digital; electronic health record system; field study; health care quality; health information technology; healthy lifestyle; improved; innovation; laptop; learned behavior; next generation; patient portal; pediatric department; prevent; primary care clinic; social cognitive theory; sociodemographics; substance use; underage drinking; virtual; virtual environment; virtual world; young adult

Because the majority of adolescent health problems are amenable to behavioral intervention and most adolescents visit a healthcare provider once a year, hea lth behavior change interventions linked to clinic- based health information technologies hold significant promise for improving healthcare quality and subsequent behavioral health outcomes for adolescents. Recognizing the potential to leverage advances in machine learning and virtual narrative environments, the field of health behavior change is now well- positioned to design health behavior change systems that extend the reach of clinicians to realize significant impacts on behavior change for adolescent preventive health. With a focus on risky behaviors and an emphasis on alcohol use, the project has two specific aims: (1) design, develop, and iteratively refine a policy-based reinforcement learning behavior change system for preventive adolescent health, and (2) investigate the impact of a clinically integrated sample-efficient policy gradient-based behavior change system on adolescent behavior. The project w ill culminate w ith an investigation of the behavioral effects of the CHANGEGRADIENTS system using adolescent patients recruited from two outpatient primary care clinics within the UCSF Department of Pediatrics: Mt. Zion Pediatrics and the Adolescent/Young Adult Clinic. It is hypothesized that adolescents who interact with CHANGEGRADIENTS with reduce number of days of alcohol use, reduce binge drinking, and increase self-efficacy to engage in healthy behavior a nd avoid risky substance use. It is anticipated that CHANGEGRADIENTS will provide a testbed for a broad range of health behavior change research and serve as the foundation for next-generation personalized preventive healthcare through computationally-enabled behavior change that is designed to be tightly integrated into clinical practice workflow. By taking advantage of the high degree of adaptive interactivity offered by its personalized behavior change environment, CHANGEGRADIENTS holds significant potential for creating compelling interactions that promote self-efficacy and engagement in healthy lifestyle behaviors to prevent cancer through improving cancer-related behaviors and risk factors. REL EVAN CE (Se e in stru cti ons): The proposed research will develop and field test an innovative computationally-enabled personalized behavior change model that will provide a testbed for a broad range of health behavior change research and is designed to be integrated into clinical practice. With adaptive interactivity, CHANGEGRADIENTS holds significant potential for creating compelling interactions that promote self-efficacy and engagement in healthy lifestyle behaviors to prevent cancer through improving cancer-related behaviors and risk factors .

因为大多数青少年健康问题都可以通过行为干预来解决，并且大多数 青少年每年去看一次医疗保健提供者，健康行为改变干预措施与临床相关 基于健康信息技术的医疗保健质量和 青少年随后的行为健康结果。认识到利用先进技术的潜力 机器学习和虚拟叙事环境，健康行为改变领域现在已经很成熟了 旨在设计健康行为改变系统，扩大临床医生的影响范围，以实现 对青少年预防性健康的行为改变产生重大影响。 该项目重点关注危险行为并强调饮酒，有两个具体目标：(1) 设计、开发和迭代完善基于策略的强化学习行为改变系统 预防性青少年健康，以及 (2) 调查临床综合样本有效政策的影响 基于梯度的青少年行为行为改变系统。该项目将在 使用招募的青少年患者调查 CHANGEGRADIENTS 系统的行为影响 来自 UCSF 儿科内的两个门诊初级保健诊所：Mt. Zion 儿科和 青少年/年轻人诊所。据推测，与变化梯度相互作用的青少年 减少饮酒天数，减少酗酒，并提高参与活动的自我效能 健康行为并避免使用危险物质。 预计 CHANGEGRADIENTS 将为广泛的健康行为改变提供一个测试平台 研究并通过以下方式作为下一代个性化预防保健的基础 通过计算实现的行为改变旨在紧密融入临床实践 工作流程。通过利用其个性化提供的高度自适应交互性 行为改变环境，CHANGEGRADIENTS 具有创造引人注目的巨大潜力 促进自我效能和参与健康生活方式行为以预防癌症的互动 通过改善癌症相关行为和危险因素。 REL EVAN CE（参见说明）： 拟议的研究将开发并现场测试一种创新的计算支持的个性化 行为改变模型将为广泛的健康行为改变研究提供测试平台 并旨在融入临床实践。通过自适应交互，CHANGEGRADIENTS 保持 创造引人注目的互动以促进自我效能和参与的巨大潜力 健康的生活方式通过改善癌症相关行为和危险因素来预防癌症。