Predicting suicide attempt in youth by integrating EHR, clinical, cognitive and imaging data

通过整合 EHR、临床、认知和影像数据来预测青少年自杀企图

• 批准号: 10038009
• 负责人: Ran Barzilay
• 金额: $ 49.88万
• 依托单位: CHILDREN'S HOSP OF PHILADELPHIA
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-01 至 2022-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10038009
• 关键词: Adolescence; Adolescent; Adopted; Adult; Age; Algorithms; Anxiety; Area; Assessment tool; Behavioral; Cause of Death; Child; Childhood; Classification; Clinical; Cognitive; Complex; Computer software; Computerized Medical Record; Coupled; Data; Data Analytics; Data Set; Depression screen; Development; Electronic Health Record; Engineering; Environment; Evaluation; Familiarity; Feeling suicidal; Frequencies; Guidelines; Gur; Health; Hippocampus (Brain); Hospitals; Image; Individual; Insurance; Intervention; Lead; Machine Learning; Measures; Medical Device; Medical Records; Medical center; Medicine; Memory; Methods; Mission; Modeling; Moods; Neurocognitive; Obsessive compulsive behavior; Odds Ratio; Outcome; Participant; Patients; Pediatric Hospitals; Phenotype; Philadelphia; Policies; Population; Positioning Attribute; Primary Health Care; Primary Prevention; Proxy; Psychiatrist; Psychological Transfer; Psychotic Disorders; Race; Recording of previous events; Reporting; Research; Research Personnel; Resources; Rest; Risk; Risk Factors; Sampling; Source; Subgroup; Suicide; Suicide attempt; Symptoms; System; Teenagers; Testing; Thalamic structure; Thinness; Time; Training; Translating; Universities; Update; Youth; adolescent suicide; aged; base; care providers; clinical care; clinical phenotype; clinical practice; cohort; computerized tools; data resource; deep neural network; depressive symptoms; early adolescence; executive function; expectation; experience; falls; improved; learning progression; machine learning algorithm; machine learning method; meetings; modifiable risk; multidisciplinary; multiple data types; neuroimaging; novel; novel strategies; pediatric patients; prediction algorithm; predictive modeling; prospective; random forest; reducing suicide; routine screening; screening; screening guidelines; social cognition; suicidal adolescent; suicidal morbidity; suicidal risk; suicide rate

Summary. Suicide in youths is a growing health concern, yet current clinical practice falls short of timely identifying youths at risk for suicide attempt (SA). The overarching aim of this research is to use data driven machine learning methods to facilitate primary prevention of youth SAs in primary care pediatric settings. Clinical guidelines recommend screening for depression, considered a proxy for suicide risk, from age 12 in pediatric setting. The proposed study aims at identification of variables (features) that can be collected by early adolescence, and contribute to prediction of SA in later adolescence. This study will leverage the effort that has been invested in previous projects: a study using electronic health records (EHR) to predict SAs and deaths in University of Pittsburgh Medical Center (UPMC) hospitals; and the Philadelphia Neurodevelopmental Cohort (PNC), that included comprehensive phenotyping of ~9,500 youths. These previous efforts will be integrated to develop and optimize SA prediction in youth from the Children’s Hospital of Philadelphia (CHOP) network, from which we have data on ~40,000 who were screened for a history of SA between the years 2014-2018 (n~1500). First, in the CHOP dataset, we will generate predictive models based on UPMC data, test their predictive validity in CHOP youth population, and then develop, optimize, and cross validate these predictive models using CHOP EHR data as a training set (Aim 1). Second, in the PNC dataset, we will use multiple data types (demographic, behavioral, cognitive, imaging) to classify youths with suicide ideation (SI, n~750) and identify features (potentially modifiable) that are indicative of SI and may also point to potential mechanisms underlying youth SI (Aim 2). Lastly, in a subset of 936 youths (49 with SAs) with both CHOP EHR data and research PNC evaluation that was conducted at mean age 11 (T1), ~5 years before SA screening (T2), we will test the validity of models from Aims 1&2, and aim to identify data features that were collected at T1 and can improve/optimize/outperform the prediction of SAs that relies solely on EHR data (Aim 3). The proposed study relies on the expertise of a highly capable multidisciplinary team comprised of Dr. Barzilay (PI), child- adolescent psychiatrist experienced in suicide research and analysis of suicide related phenotypes in PNC data; Dr. Tsui (PI), an expert in machine learning who has developed predictive algorithms of SA and deaths using UPMC data; and collaborators critical for meeting study aims, Dr. Raquel Gur as the lead researcher who established the PNC, Dr. Ruben Gur who developed the PNC neurocognitive assessment tools, and Dr. Oquendo who will provide expertise in suicide prediction research. The team’s access and familiarity with CHOP EHR and PNC data resources, coupled with its interdisciplinary expertise, creates a unique opportunity to identify childhood features that can optimize later adolescent SA prediction. Expected findings can ultimately translate to real world clinical practice, be integrated in EHR, and help flag youths at risk for a SA in a pediatric setting, allowing timely identification and intervention, contributing to the mission of reducing suicide in youth.

概括。青年自杀是一个日益增长的健康问题，但目前的临床实践尚未达到及时 确定有自杀企图风险的年轻人（SA）。这项研究的总体目的是使用数据驱动器 在初级保健小儿环境中促进初级预防青年SA的机器学习方法。 临床指南建议对抑郁症进行筛查，被认为是自杀风险的代理，从12岁开始 小儿环境。拟议的研究旨在识别可以通过早期收集的变量（特征） 青少年，并在后来的青少年中有助于SA的预测。这项研究将利用努力 已投资于以前的项目：一项使用电子健康记录（EHR）的研究来预测SAS和死亡 匹兹堡大学医学中心（UPMC）医院；费城神经发育队列 （PNC），其中包括约9,500名年轻人的全面表型。这些先前的努力将集成到 从费城儿童医院（CHOP）网络中开发和优化SA的预测， 我们有关于〜40,000的数据，他们在2014-2018年之间被筛选了SA的历史 （n〜1500）。首先，在CHOP数据集中，我们将基于UPMC数据生成预测模型，测试他们 CHOP青年人口中的预测有效性，然后发展，优化和交叉验证这些预测性 使用CHOP EHR数据作为训练集的模型（AIM 1）。第二，在PNC数据集中，我们将使用多个数据 类型（人口统计，行为，认知，成像）以自杀想法（SI，N〜750）和 识别指示SI的特征（潜在可修改），也可能指出潜在机制 基础青年SI（AIM 2）。最后，在936名年轻人（49个带有SAS）的子集中 研究PNC评估是在SA筛查前约5年（T2）进行的平均年龄（T1）进行的，我们将 测试AIMS 1和2的模型的有效性，并旨在识别在T1上收集的数据功能，并且可以 改进/优化/优于仅依赖EHR数据的SA的预测（AIM 3）。拟议的研究 依赖于Barzilay博士（PI），Child-的跨学科团队的专业知识 PNC中自杀研究和自杀相关表型的自杀研究和分析中经验丰富的青少年精神科医生 数据;机器学习专家Tsui博士（PI）已经开发了SA和死亡的预测算法 使用UPMC数据；合作者对会议研究目标至关重要，拉奎尔·古尔（Raquel Gur）博士担任首席研究员 建立了PNC，开发PNC神经认知评估工具的Ruben Gur博士和博士 Oquendo将提供自杀预测研究的专业知识。团队的访问和熟悉 CHOW EHR和PNC数据资源，再加上其跨学科专业知识，创造了独特的机会 确定可以优化以后的青少年SA预测的童年特征。预期的发现最终可以 转化为现实世界的临床实践，将EHR整合在一起，并帮助旗帜在儿科中冒着SA的风险 设置，允许及时识别和干预，促进减少青年自杀的使命。

项目成果

Deconstructing the role of the exposome in youth suicidal ideation: Trauma, neighborhood environment, developmental and gender effects.

• DOI: 10.1016/j.ynstr.2021.100314
• 发表时间: 2021-05
• 期刊: Neurobiology of stress
• 影响因子: 5
• 作者: Barzilay R;Moore TM;Calkins ME;Maliackel L;Jones JD;Boyd RC;Warrier V;Benton TD;Oquendo MA;Gur RC;Gur RE
• 通讯作者: Gur RE

Connectome-wide Functional Connectivity Abnormalities in Youth With Obsessive-Compulsive Symptoms.

• DOI: 10.1016/j.bpsc.2021.07.014
• 发表时间: 2022-11
• 期刊: Biological psychiatry. Cognitive neuroscience and neuroimaging
• 作者: Alexander-Bloch AF;Sood R;Shinohara RT;Moore TM;Calkins ME;Chertavian C;Wolf DH;Gur RC;Satterthwaite TD;Gur RE;Barzilay R
• 通讯作者: Barzilay R

Identifying Youth at Risk for Suicidal Thoughts and Behaviors Using the "p" factor in Primary Care: An Exploratory Study.

使用初级保健中的“p”因素识别有自杀想法和行为风险的青少年：一项探索性研究。

• DOI: 10.1080/13811118.2022.2106925
• 发表时间: 2023
• 期刊: Archives of suicide research : official journal of the International Academy for Suicide Research
• 作者: Ruan-Iu,Linda;Rivers,AlannahShelby;Barzilay,Ran;Moore,TylerM;Tien,Allen;Diamond,Guy
• 通讯作者: Diamond,Guy

Association Between Discrimination Stress and Suicidality in Preadolescent Children.

• DOI: 10.1016/j.jaac.2021.08.011
• 发表时间: 2022-05
• 期刊: Journal of the American Academy of Child and Adolescent Psychiatry
• 影响因子: 13.3
• 作者: Argabright ST;Visoki E;Moore TM;Ryan DT;DiDomenico GE;Njoroge WFM;Taylor JH;Guloksuz S;Gur RC;Gur RE;Benton TD;Barzilay R
• 通讯作者: Barzilay R

Evaluation of Attention-Deficit/Hyperactivity Disorder Medications, Externalizing Symptoms, and Suicidality in Children.

• DOI: 10.1001/jamanetworkopen.2021.11342
• 发表时间: 2021-06-01
• 期刊: JAMA network open
• 影响因子: 13.8
• 作者: Shoval G;Visoki E;Moore TM;DiDomenico GE;Argabright ST;Huffnagle NJ;Alexander-Bloch AF;Waller R;Keele L;Benton TD;Gur RE;Barzilay R
• 通讯作者: Barzilay R