Using machine learning to accelerate our understanding of risks for early substance use among child-welfare and community youth

利用机器学习加速我们对儿童福利和社区青少年早期药物使用风险的了解

• 批准号: 10734004
• 负责人: BISTRA DILKINA
• 金额: $ 72.46万
• 依托单位: KAISER FOUNDATION RESEARCH INSTITUTE
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-01 至 2026-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10734004
• 关键词: 18 year old; Acceleration; Accidents; Address; Adolescence; Adolescent; Adoption; Adult; African American; Age; California; Caring; Cessation of life; Child; Child Abuse and Neglect; Child Welfare; Childhood; Clinical; Code; Communities; County; Crime; Criminal Justice; Data; Data Sources; Development; Diagnosis; Disclosure; Documentation; Drug usage; Early Diagnosis; Early Intervention; Early identification; Economics; Electronic Health Record; Eligibility Determination; Family; Geography; Health; Healthcare; Healthcare Systems; Homelessness; Income; Individual; Intervention; Knowledge; Latinx; Machine Learning; Maps; Measures; Medical; Methods; Modeling; Neighborhoods; Parents; Participant; Pathway interactions; Persons; Pharmaceutical Preparations; Population; Predisposition; Prevention; Primary Care; Productivity; Provider; Records; Reporting; Risk; Risk Factors; Sample Size; Sampling; Stratification; Substance Use Disorder; Substance abuse problem; Surveys; Time; Translations; Unemployment; Visit; Vulnerable Populations; Youth; abuse victim; addiction; adolescent substance use; alcohol use initiation; clinical care; clinical decision support; clinical decision-making; clinical predictive model; clinical risk; comparison group; cost; critical period; electronic health record system; ethnic diversity; experience; future implementation; improved; longitudinal dataset; machine learning method; machine learning model; maltreatment; marijuana use; member; multi-racial; neglect; novel strategies; predictive modeling; predictive tools; primary care provider; psychosocial; racial diversity; risk prediction; screening; social; substance abuse prevention; substance misuse; substance use; support tools; translational potential; user-friendly

PROJECT SUMMARY/ABSTRACT The economic toll of substance use/abuse is estimated to be over $740 billion annually as a result of accidents, health care, homelessness, unemployment, and criminal activity. Adolescence is a critical time for intervention, as 90% of adults who meet the criteria for addiction initiate use of alcohol or drugs in adolescence. Yet, prevention efforts have been hindered by minimal substance use screening by primary care providers as well as low rates of disclosure by adolescents in medical settings. These challenges necessitate new approaches to detect key risk factors and enhance screening methods. Importantly, adolescents with experiences of child maltreatment are more susceptible to early substance use and more likely to progress from experimentation to addiction than non-maltreated youth. The accumulating evidence and our preliminary data suggest that the top predictors of early substance use are not relevant for child welfare (CW) youth, requiring new studies of the relevant risk factors for this vulnerable population. The proposed study addresses these gaps by using cutting-edge Machine Learning models to provide vital new evidence regarding risk factors specific to the CW population as well as risks for early substance use that may be common to both CW and non-CW youth. We will use two unique data sources to accomplish this. Our primary data will come from electronic health records (EHR) of Kaiser Permanente Southern California (KPSC) members (estimated sample size of 3.4 million children, 2007-2020). We will use diagnosis codes for maltreatment to indicate the CW sample, a reasonable assumption of referral to child welfare. Risk factors will be obtained from diagnosis codes and abstractable progress notes in the EHR of children and parents as well as county crime and geographic income data. Second, to address the limitations of EHR to capture more detailed psychosocial data, we will use an existing longitudinal dataset of 454 youth, 303 referred from child welfare and 151 in a comparison group (YAP study). Participants were seen at mean ages 11, 13, 15, and 18 years old and are racially/ethnically diverse. Collected data includes measures of child level, parent level, family level, and neighborhood risk factors and CW case records. These two data sources will allow us to: 1) produce critical new knowledge regarding the relevant predictors of early substance use for CW versus non-CW youth and 2) use intensive survey data (YAP) to determine risk factors that are not currently collected in EHR data (KPSC) that may inform the development of new screening questions. Lastly, our predictive model has translational potential to advance screening methods for adolescent substance use risk in pediatric primary care through the use of risk scores integrated into clinical decision support tools. These findings, if implemented in clinical care settings, would allow medical providers to more accurately identify those at risk and trigger stratification into different treatment pathways to prevent substance abuse.

项目概要/摘要 据估计，每年因药物使用/滥用造成的经济损失超过 7,400 亿美元 事故、医疗保健、无家可归、失业和犯罪活动。青春期是一个关键时期 干预，因为 90% 符合成瘾标准的成年人开始使用酒精或药物 青春期。然而，初级保健的最低限度物质使用筛查阻碍了预防工作 提供者以及医疗环境中青少年的披露率较低。这些挑战需要 检测关键风险因素和增强筛查方法的新方法。重要的是，青少年有 虐待儿童的经历更容易受到早期药物使用的影响，并且更有可能发展 从实验到成瘾，与未受虐待的年轻人相比。不断积累的证据和我们的初步 数据表明，早期药物使用的主要预测因素与儿童福利 (CW) 青少年无关， 需要对这一弱势群体的相关风险因素进行新的研究。拟议的研究地址 通过使用尖端的机器学习模型来提供有关风险的重要新证据来弥补这些差距 CW 人群特有的因素以及 CW 人群可能共有的早期药物使用风险 和非 CW 青年。我们将使用两个独特的数据源来完成此任务。我们的主要数据将来自 南加州凯撒医疗机构 (KPSC) 成员的电子健康记录 (EHR)（估计 样本量为 340 万儿童，2007 年至 2020 年）。我们将使用虐待诊断代码来表明 CW 样本，转介至儿童福利的合理假设。危险因素将从诊断中获得 儿童和家长的电子病历以及县犯罪和 地理收入数据。其次，解决 EHR 的局限性，以捕获更详细的心理社会信息 数据，我们将使用现有的纵向数据集，其中包括 454 名青少年、303 名来自儿童福利机构和 151 名青少年 对照组（YAP 研究）。参与者的平均年龄为 11、13、15 和 18 岁， 种族/民族多样化。收集的数据包括儿童水平、父母水平、家庭水平和 邻里风险因素和化学武器案件记录。这两个数据源将使我们能够：1）生成关键数据 关于 CW 与非 CW 青少年早期药物使用相关预测因素的新知识以及 2) 使用强化调查数据 (YAP) 确定当前 EHR 数据 (KPSC) 中未收集的风险因素 这可能会为新筛选问题的开发提供信息。最后，我们的预测模型具有转化性 通过以下方法，有可能推进儿科初级保健中青少年物质使用风险的筛查方法 使用集成到临床决策支持工具中的风险评分。这些发现如果应用于临床护理 设置，将使医疗提供者能够更准确地识别高危人群并触发分层 防止药物滥用的不同治疗途径。