Fair risk profiles and predictive models for outcomes of obstructive sleep apnea through electronic medical record data

通过电子病历数据对阻塞性睡眠呼吸暂停结果进行公平的风险概况和预测模型

基本信息

批准号：
10678108
负责人：
Victor Borza
金额：
$ 3.28万
依托单位：
VANDERBILT 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：
2023-06-01 至 2026-05-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10678108
关键词：
Accounting Acute Address Affect Age Algorithms Asian population COVID-19 Cardiovascular Diseases Characteristics Chronic Classification Clinical Clinical Data Computer Models Computerized Medical Record Computing Methodologies Continuous Positive Airway Pressure Data Data Set Dementia Diabetic Nephropathy Diagnosis Disease Disparity Drowsy Driving Ethnic Origin Exhibits Foundations Functional disorder Future Gender Geographic Locations Grant Individual Intervention Intuition Investigation Machine Learning Measurement Metabolic syndrome Methods Modeling Modernization Obstructive Sleep Apnea Operative Surgical Procedures Outcome Outcomes Research Patient Care Patients Pattern Performance Persons Phenotype Physicians Population Prevalence Process Questionnaires Race Recommendation Research Research Ethics Resources Risk Severities Sleep Apnea Syndromes Socioeconomic Status Subgroup Symptoms Testing Time Translating Vehicle crash Woman benefit sharing career clinical practice clinically actionable comorbidity compliance behavior demographics improved individual patient insight machine learning classifier machine learning prediction model building neuropsychiatric disorder outcome disparities patient screening predictive modeling risk prediction skills treatment effect treatment guidelines treatment response treatment strategy

项目摘要

PROJECT SUMMARY Obstructive sleep apnea (OSA) is a sleep-related breathing disorder associated with major co-morbidities and is estimated to affect nearly one billion people worldwide. Moreover, there are differences in prevalence, diagnosis rates, and co-morbid outcomes for OSA based on the demographics of a patient, such as age, race, and gender. The diversity of the clinical manifestations, objective measurements, and outcomes – the phenotype – of OSA underscores the opportunity for predictive models to improve care of patients with OSA. Predicting future (i.e. 5- year post-diagnosis) risks of OSA co-morbid outcomes and predicting how different treatments for OSA affect these risks can help clinicians and patients choose the best treatment strategies. Current OSA outcomes research has key limitations. Prior studies have characterized groups of OSA patients that exhibit similar characteristics, referred to as sub-phenotypes of OSA. However, these studies have been limited by analyzing relatively few variables obtainable from questionnaires. To address this limitation, we will use rich longitudinal electronic medical records (EMR) data to characterize OSA sub-phenotypes and to predict OSA outcome risks for individual patients. To extract insights from EMR data, we will leverage modern computational methods based in machine learning (ML). A second major limitation of existing OSA research is worse predictive model performance for some groups. Model biases have real-world negative implications. The ubiquitous STOP-BANG questionnaire used to screen patients for further OSA testing performs worse for women and Asian individuals, leading to potential delayed, under-, or misdiagnosis of OSA in these groups. To address this limitation, this proposed project will assess and mitigate biases present in our predictive models. To better understand patient factors associated with OSA outcomes, this project has two aims. In Aim 1 clustering methods will be applied to identify groups of OSA patients who share similar sub-phenotypes according to combinations of clinical features and objective measurements present in EMR data. Then, sub- phenotypes will be compared by the rates at which they exhibit different OSA outcomes, providing intuition into potential underlying pathophysiologic differences. In Aim 2, ML classifiers will be applied to build and validate algorithmically fair predictive models for future OSA outcome risks as well as effects of OSA treatments. Patient- specific factors that are consistently associated with differences in OSA outcome risks through Aims 1 and 2 will provide both personalized insights into treatment options and stronger evidence of underlying pathophysiology worthy of further investigation.

项目概要阻塞性睡眠呼吸暂停 (OSA) 是一种与睡眠相关的呼吸障碍，与主要并发症相关，据估计影响全球近十亿人此外，患病率和诊断也存在差异。基于患者人口统计数据（例如年龄、种族和性别）的 OSA 发生率和共病结果。 OSA 临床表现、客观测量和结果（表型）的多样性强调了预测模型改善 OSA 患者护理的机会（即 5- 诊断后一年）OSA 共病结果的风险并预测 OSA 的不同治疗方法如何影响这些风险可以帮助新人和患者选择最佳的治疗策略。目前的 OSA 结局研究存在重大局限性，之前的研究对 OSA 患者群体进行了表征。表现出相似特征的，称为 OSA 亚表型。通过分析从问卷中获得的相对较少的变量来解决这一限制。使用丰富的纵向电子病历 (EMR) 数据来表征 OSA 亚表型并预测为了从 EMR 数据中获取见解，我们将利用现代技术。基于机器学习 (ML) 的计算方法是现有 OSA 研究的第二个主要局限性。对于某些群体来说，较差的预测模型表现会产生现实世界的负面影响。用于筛选患者进行进一步 OSA 测试的无处不在的 STOP-BANG 问卷对女性来说效果较差和亚洲人，导致这些群体中 OSA 的诊断可能延迟、诊断不足或误诊。鉴于这一限制，该拟议项目将评估并减轻我们的预测模型中存在的偏差。为了更好地了解与 OSA 结果相关的患者因素，该项目有两个目标 1。聚类方法将用于识别具有相似亚表型的 OSA 患者组根据 EMR 数据中存在的临床特征和客观测量的组合，然后进行细分。表型将通过它们表现出不同 OSA 结果的比率进行比较，从而提供对在目标 2 中，将应用 ML 分类器来构建和验证潜在的病理生理差异。针对未来 OSA 结果风险以及 OSA 治疗效果的算法公平预测模型。通过目标 1 和 2 与 OSA 结果风险差异一致相关的特定因素将提供对治疗方案的个性化见解和潜在病理生理学的更有力证据值得进一步调查。