Innovative methods to reduce racial and ethnic disparities in suicide risk prediction

减少自杀风险预测中种族和民族差异的创新方法

基本信息

批准号：
10363191
负责人：
Rebecca Yates Coley
金额：
$ 41.94万
依托单位：
KAISER FOUNDATION RESEARCH INSTITUTE
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：
2022-01-01 至 2025-12-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10363191
关键词：
Address Adopted Adult Age Alaska Native Algorithms American Indians Asian Pacific Islander Black Populations Black race Cessation of life Clinical Clinical Data Complex Data Death Rate Development Differential Diagnosis Emergency department visit Ensure Ethnic Origin Ethnic group Evaluation Event Funding Gender Identity Health system Healthcare Healthcare Systems Hispanic Populations Individual Label Lead Measurement Measures Mental Health Methods Modeling Modification National Institute of Mental Health Not Hispanic or Latino Outcome Outpatients Paper Patient Care Patients Pattern Performance Persons Population Primary Health Care Procedures Psychiatry Race Records Research Research Personnel Risk Risk Factors Sample Size Sampling Self-Injurious Behavior Severity of illness Source Statistical Methods Stratification Subgroup Suicide Suicide attempt Suicide prevention Underserved Population United States Visit Vulnerable Populations Weight Work design health care availability health care service utilization health care settings health disparity high risk improved innovation interest machine learning method machine learning model novel outcome prediction predictive modeling prevent preventive intervention racial and ethnic racial and ethnic disparities random forest recidivism response risk prediction risk prediction model sexual identity simulation social health determinants suicidal behavior suicidal morbidity suicidal risk suicide rate trend

项目摘要

Suicide death rates in the United States have increased 35% since 1999. In 2018, there were over 48,000 suicide deaths, and an estimated 1.4 million adults attempted suicide. In response, health systems are adopting suicide risk prediction models to guide delivery of suicide prevention interventions. Suicide prediction models estimated from health care records may perpetuate current disparities in health care access, quality, and outcomes. Suicide prediction models may not accurately identify high-risk patients from all racial and ethnic groups. Suicide rates vary by race and ethnicity, and both the highest and lowest rates are seen in traditionally underserved populations. Suicide rates are highest among American Indians and Alaskan Natives (22.1 per 100,000 people) and lowest in Asian and Pacific Islander, Black, and Hispanic populations (7.0-7.4 per 100,000 people) compared to 18.0 per 100,000 people for White non-Hispanics. Differences in performance of suicide risk prediction models across racial and ethnic subgroups have three possible sources. First, predictors of suicide risk may be measured with error, and this error may be different for racial and ethnic subgroups. Second, suicide attempts and deaths may be misclassified, and misclassification rates may differ by race and ethnicity. Third, the association between predictors and outcomes may vary by race and ethnicity, i.e., risk modification. Existing methods for estimating prediction models are not designed to address racial and ethnic disparities in performance. Estimation procedures focus on optimizing performance across the entire population, not within subgroups, and performance in less prevalent subgroups has little impact on overall accuracy. While machine learning methods, like random forest, explore interactions between predictors and race or ethnicity, suicide attempt and death are rare events, which limits the information available to identify race- and ethnicity-specific risk factors. There is also insufficient guidance on sample size calculations for prediction studies. We will develop novel statistical methods for random forest models that reduce racial and ethnic disparities in performance of suicide prediction models by addressing gaps in current methods. Aim 1 will develop new procedures for prediction model estimation that maximize predictive performance within racial and ethnic subgroups, rather than maximizing average performance across the entire population. Aim 2 will integrate methods to adjust for differential outcome misclassification in prediction model estimation and evaluation. Aim 3 will design sample size calculations to determine if a study is able to accurately predict outcomes within racial and ethnic subgroups. We will use existing data on suicide risk factors and outcomes for 15 million outpatient mental health, 10 million primary care, and 2 million emergency department visits from the NIMH- funded Mental Health Research Network to implement our methods and estimate suicide prediction models for each setting that accurately identify patients at highest risk of suicide across all races and ethnicities.

自1999年以来，美国的自杀死亡率增加了35%。2018年，自杀人数超过48,000人自杀死亡，估计有 140 万成年人试图自杀。作为回应，卫生系统正在采用自杀风险预测模型来指导自杀预防干预措施的实施。根据医疗保健记录估计的自杀预测模型可能会延续当前医疗保健方面的差异访问、质量和结果。自杀预测模型可能无法准确识别所有患者中的高危患者种族和族裔群体。自杀率因种族和民族而异，最高和最低的自杀率均为见于传统上服务不足的人群。美洲印第安人和阿拉斯加人的自杀率最高本地人（每 10 万人中有 22.1 人），亚洲和太平洋岛民、黑人和西班牙裔人口中最低（每 100,000 人 7.0-7.4），而非西班牙裔白人每 100,000 人为 18.0。不同种族和族裔亚组的自杀风险预测模型的表现存在三个差异：可能的来源。首先，自杀风险的预测因子的测量可能存在误差，而且这个误差可能是不同的对于种族和民族亚群体。其次，自杀未遂和死亡可能被错误分类，并且错误分类率可能因种族和民族而异。三、预测因子与预测因子之间的关联结果可能因种族和民族而异，即风险调整。现有的估计预测模型的方法并不是为了解决种族和民族差异而设计的。表现。估计程序的重点是优化整个群体的表现，而不是内部子组，并且不太常见的子组中的表现对整体准确性影响很小。边机学习方法，如随机森林，探索预测因素与种族或民族、自杀之间的相互作用企图和死亡是罕见事件，这限制了可用于识别特定种族和民族的信息风险因素。对于预测研究的样本量计算也没有足够的指导。我们将为随机森林模型开发新颖的统计方法，以减少种族和民族差异通过解决当前方法的差距来提高自杀预测模型的性能。目标1将开发新的预测模型估计的程序，可最大限度地提高种族和民族内的预测性能子群体，而不是最大化整个群体的平均表现。目标2将整合调整预测模型估计和评估中差异结果错误分类的方法。目的 3 将设计样本量计算以确定研究是否能够准确预测结果种族和民族亚群体。我们将使用 1500 万人自杀风险因素和结果的现有数据 NIMH 门诊心理健康、1000 万人次初级保健和 200 万人次急诊就诊资助心理健康研究网络来实施我们的方法并估计自杀预测模型每个设置都能准确识别所有种族和民族中自杀风险最高的患者。