Characterizing neuroimaging 'brain-behavior' model performance bias in rural populations

表征农村人口神经影像“大脑行为”模型的表现偏差

基本信息

批准号：
10752053
负责人：
Brendan Adkinson
金额：
$ 3.26万
依托单位：
YALE UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-09-01 至 2026-08-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10752053
关键词：
Adolescent Affect Age Algorithms Area Attention Behavior Brain Clinical Cognition Cognitive Cognitive deficits Complex Data Data Collection Data Set Development Diagnosis Emerging Technologies Ensure Equity Exclusion Face Functional Magnetic Resonance Imaging Geographic Locations Geography Healthcare Human Individual Learning Machine Learning Measures Mental Health Mental disorders Modeling Modernization Moods Nature Outcome Participant Pattern Performance Physicians Population Psychiatry Research Rest Rural Rural Population Sampling Sampling Studies Scientist Site Symptoms Techniques Technology Testing Training Translations Treatment outcome Underrepresented Populations United States Validation brain based brain behavior career clinical decision-making cognitive development cognitive task connectome connectome based predictive modeling developmental disease disparity reduction health disparity machine learning model metropolitan model design neuroimaging novel predictive modeling prevent psychiatric symptom rural area rural health disparities rural patients rural residence tool treatment choice urban area urban residence verbal virtual

项目摘要

PROJECT SUMMARY Nearly one-fifth of the Unites States population resides in a rural region, and approximately one-fifth of those residents suffers from a mental illness. While these rates of mental illness are similar to urban areas, individuals living in rural regions face a disproportionate burden of negative psychiatric outcomes. Modern advances in psychiatric research have focused on using machine learning and human neuroimaging to predict diagnoses and treatment outcomes. However, recent evidence suggests that machine learning models themselves may drive health disparities through performance bias. Specifically, clinical decision-making models created in majority populations may not perform as well in populations that were underrepresented during the creation of the model (e.g., poorer likelihood of choosing the correct treatment if patients are rural). Given that virtually all neuroimaging ‘brain-behavior’ predictive models in psychiatry research are generated from data collected in highly populated metropolitan areas, this study will evaluate ‘brain-behavior’ models for performance bias in rural populations. It will also investigate means of eliminating this bias that creates further health disparities in rural populations. In Aim 1, I will use neuroimaging data from 9,811 individuals in the Adolescent Brain and Cognitive Development Study to create a ‘brain-behavior’ predictive model of cognition. In Aim 2, I will evaluate this model for urban-rural performance bias and pursue strategies to reduce model bias. This study will have important implications for understanding how algorithms in healthcare drive health disparities and how we can reduce these disparities by designing models that perform equitably within underrepresented populations.

项目概要近五分之一的美国人口居住在农村地区，其中约五分之一居住在农村地区居民患有精神疾病，虽然这些精神疾病的发生率与城市地区相似，但个人。生活在农村地区的人面临着不成比例的负面精神疾病负担。精神病学研究重点是使用机器学习和人类神经影像来预测诊断然而，最近的证据表明机器学习模型本身可能具体来说，通过绩效偏差来推动健康差异。大多数人群在创建过程中代表性不足的人群中可能表现不佳模型（例如，如果患者来自农村，则选择正确治疗的可能性较小）。精神病学研究中的神经影像“大脑行为”预测模型是根据收集的数据生成的在人口稠密的大都市地区，这项研究将评估农村地区表现偏差的“大脑行为”模型它还将研究消除这种造成农村进一步健康差距的偏见的方法。在目标 1 中，我将使用来自 9,811 个人的青少年大脑和认知神经影像数据。创建“大脑行为”认知预测模型的开发研究在目标 2 中，我将评估该模型。针对城乡绩效偏差并寻求减少模型偏差的策略本研究将具有重要意义。对于理解医疗保健中的算法如何驱动健康差异以及我们如何减少健康差异的影响通过设计在代表性不足的人群中公平执行的模型来消除这些差异。