权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Improving Suicide Prediction using NLP-Extracted Social Determinants of Health

使用 NLP 提取的健康社会决定因素改善自杀预测

基本信息

批准号：
10100989
负责人：
HONG YU
金额：
$ 84.14万
依托单位：
UNIVERSITY OF MASSACHUSETTS LOWELL
依托单位国家：
美国
项目类别：
财政年份：
2020
资助国家：
美国
起止时间：
2020-09-01 至 2024-06-30
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10100989
关键词：
Address Age Alcohol consumption Behavior Behavioral Caring Cause of Death Cessation of life Characteristics Clinical Code Data Data Sources Development Diagnosis Economics Electronic Health Record Elements Feeling suicidal Food Goals Guns Health Services Healthcare Healthcare Systems High Prevalence Incidence Individual Inferior Intervention Lead Machine Learning Marital Status Mediating Medical Mental Health Methodology Methods Modeling Natural Language Processing Occupations Outcome Participant Patients Performance Persons Population Post-Traumatic Stress Disorders Predictive Analytics Prevalence Prevention strategy Regression Analysis Research Research Personnel Risk Risk Assessment Risk Factors Source Structure Suicide Suicide prevention Surveys Time Traumatic Brain Injury United States Veterans Vulnerable Populations Work automated algorithm cohort comorbidity deep learning disability drinking health administration health record high risk improved indexing innovation longitudinal analysis next generation novel physical conditioning predictive modeling random forest response social health determinants social integration structured data suicidal behavior suicidal morbidity suicidal risk suicide rate tool unstructured data

项目摘要

Improving Suicide Prediction using NLP-Extracted Social Determinants of Health Suicide is among the leading causes of death worldwide and among United States Veterans in particular. Current methods of risk assessment are limited in their ability to accurately identify patients who are at the highest risk of suicide. The overarching goal of this proposal is to strengthen suicide prediction efforts by gaining a more granular understanding of the association between social determinants of health and suicide risk. Social determinants of health (SDH) refer to the conditions in which people are born, live, work, and age. A number of SDH are known risk factors for suicide. While SDH could be obtained from the structured EHR data, their scope is limited. A recent study has shown that EHR notes contain about 90 times more information about SDH than the structured data. To address this gap, we propose a stepwise approach that leverages the power of EHR and new computational methdologies to explore associations between natural language processing extracted SDH and suicide ideation, attempt and death. This approach is critical to the development of next- generation suicide prevention tools.

使用 NLP 提取的健康社会决定因素改善自杀预测自杀是全球和美国退伍军人死亡的主要原因之一特别的。当前的风险评估方法在准确识别风险方面受到限制。自杀风险最高的患者。该提案的总体目标是通过更细致地了解自杀事件来加强自杀预测工作健康的社会决定因素与自杀风险之间的关联。健康的社会决定因素（SDH）是指人们出生、生活、工作、和年龄。许多 SDH 是已知的自杀危险因素。虽然可以获得SDH 从结构化 EHR 数据来看，它们的范围是有限的。最近的一项研究表明 EHR 指出包含的 SDH 信息比结构化数据多大约 90 倍。为了解决这个问题差距，我们提出了一种逐步的方法，利用 EHR 和新计算的力量探索自然语言处理提取的 SDH 和自杀意念、企图和死亡。这种方法对于下一代的发展至关重要一代自杀预防工具。