Extracting RDoC Constructs from EHR through Natural Language Processing to Predict Suicide in Youth

通过自然语言处理从 EHR 中提取 RDoC 结构来预测青少年自杀

基本信息

批准号：
10689244
负责人：
NEAL D. RYAN
金额：
$ 22.04万
依托单位：
CHILDREN'S HOSP OF PHILADELPHIA
依托单位国家：
美国
项目类别：
财政年份：
2022
资助国家：
美国
起止时间：
2022-09-01 至 2024-08-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10689244
关键词：
Address Adolescence Adolescent Affect Age Anhedonia Anxiety Disorders Arousal Black race Cause of Death Childhood Classification Clinical Collaborations Data Data Analytics Data Collection Data Set Depressed mood Diagnosis Diagnostic Electronic Health Record Elements Evaluation Research Exhibits Feeling suicidal Future Gender Goals Hospitals Intervention Investments Knowledge Language Machine Learning Measures Medical center Mental Depression Mental Health Modeling Natural Language Processing Negative Valence Outcome Patients Pediatric Hospitals Performance Philadelphia Positive Valence Psychiatry Publishing Race Recording of previous events Research Research Domain Criteria Resources Risk Estimate Risk Factors Severities Site Sleep Sleeplessness Subgroup Suicide Suicide attempt System Testing Text Translating Universities Wakefulness Work Youth child depression clinical practice cognitive system deep learning deep neural network demographics electronic structure experience gender minority improved innovation large datasets machine learning prediction novel risk prediction sociodemographics statistics structured data suicidal behavior suicidal risk suicide attempter suicide model suicide rate tool unstructured data

项目摘要

PROJECT SUMMARY/ABSTRACT Suicide ranks as the second most frequent cause of death in adolescence, and the rate of suicide among adolescents has continued to increase. Despite 50 years of research and efforts, the prediction of suicide and suicidal thoughts and behaviors (STBs) remains difficult. Recent studies indicate that electronic health record (EHR) data analytics can help predict the risk of STB. The Research Domain Criteria (RDoC) provides a framework to probe transdiagnostic domains reflecting the positive valence, the negative valence, and the sleep-wakefulness element insomnia within the arousal and regulatory domain. These three RDoC constructs have shown strong association with depression and anxiety disorders. However, there exists a knowledge gap regarding the relationship and impact of RDoC measures extracted from EHR on youth suicide attempts (SAs). Given significant changes in positive affect and cognitive systems during childhood and adolescence, our overall goal is to assess the RDoC positive valence, the negative valence, and the sleep-wakefulness element insomnia in youth with STBs using machine learning and deep learning based natural language processing of EHR data. This study will leverage the effort and resources that have been invested in previous projects from two sites: a study on SA prediction using natural language processing and machine learning from EHR data (n=7,670 youths) in the University of Pittsburgh Medical Center (UPMC) hospitals; and the data collection for SA study in the Children’s Hospital of Philadelphia (CHOP) with 567,091youths (n=3,125 attempters). The specific aims are to 1) develop and validate extraction of summary variables from EHR using deep neural network language models for the positive valence, the negative valence, and the sleep-wakefulness element insomnia within the arousal and regulatory domain; 2) compare performance of the ML models developed in Aim 1 to extract the RDoC positive and negative valence and insomnia from EHR with traditional NLP approaches; and 3) test utility of the RDoC positive and negative valence and insomnia in prediction of suicidal behaviors. This proposed study, if successful, is the first steps towards other RDoC domains and constructs extracted from EHR on youth SAs and translating the obtained models to clinical settings. Dr. Tsui (CHOP) and Dr. Ryan (UPMC) have a long history of collaboration in mental health studies using ML and NLP and have strong experience in serving as PIs in various studies. Overall, our study has a potential to advance the field of SA prediction that facilitates timely intervention and ultimately reduces youth suicides.

项目概要/摘要自杀是青春期第二常见的死亡原因，自杀率尽管经过 50 年的研究和努力，青少年自杀率仍在持续增加。最近，自杀以及自杀想法和行为（STB）的预测仍然很困难。研究表明，电子健康记录 (EHR) 数据分析可以帮助预测以下疾病的风险 STB。研究领域标准（RDoC）提供了一个探索跨诊断的框架。反映正价、负价和睡眠-觉醒的域这三个 RDoC 结构具有唤醒和调节领域内的失眠元素。与抑郁症和焦虑症有很强的相关性。关于从 EHR 中提取的 RDoC 措施的关系和影响的知识差距鉴于积极情感和认知的显着变化。儿童和青少年时期的系统，我们的总体目标是评估 RDoC 的积极性 STB 青少年失眠的效价、负价和睡眠-觉醒因素使用基于机器学习和深度学习的自然语言处理 EHR 数据。这项研究将利用之前项目中投入的精力和资源来自两个站点：使用自然语言处理和机器进行 SA 预测的研究从匹兹堡大学医学中心 (UPMC) 的 EHR 数据（n=7,670 名青少年）学习医院；以及费城儿童医院 (CHOP) 的 SA 研究数据收集与 567,091 名年轻人（n=3,125 名尝试者）合作，具体目标是 1) 开发和验证。使用深度神经网络语言模型从 EHR 中提取摘要变量正价、负价以及睡眠-觉醒元素失眠 2) 比较目标 1 中开发的 ML 模型的性能用传统NLP从EHR中提取RDoC正负价和失眠方法；3) 测试 RDoC 正价和负价与失眠的效用这项拟议的研究如果成功，将是迈向自杀行为的第一步。从青年 SA 的 EHR 中提取的其他 RDoC 域和结构，并将 Tsui 博士（CHOP）和 Ryan 博士（UPMC）将模型应用于临床有着悠久的历史。使用 ML 和 NLP 进行心理健康研究合作，并在以下方面拥有丰富的经验总的来说，我们的研究有潜力推动 SA 领域的发展。有助于及时干预并最终减少青少年自杀的预测。