Machine Learning Prediction of 1-Year Mortality and Recurrence after Ischemic Stroke Using Enriched EHR data

使用丰富的 EHR 数据对缺血性中风后 1 年死亡率和复发进行机器学习预测

• 批准号: 10658513
• 负责人: Vida Abedi
• 金额: $ 73.08万
• 依托单位: PENNSYLVANIA STATE UNIV HERSHEY MED CTR
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-11 至 2027-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10658513
• 关键词: Address; Area Under Curve; Artificial Intelligence; Caring; Cause of Death; Cessation of life; Characteristics; Clinical; Clinical Data; Communities; Complex; Creativeness; Data; Data Element; Data Set; Death Rate; Discrimination; Disease Management; Electronic Health Record; Evaluation; Foundations; Health; Health system; Healthcare; Healthcare Systems; Individual; Ischemic Stroke; Low Income Population; Measures; Modeling; Multicenter Studies; Output; Patient Care; Patients; Pennsylvania; Performance; Persons; Population; Predictive Value; Prevention; Publishing; Race; Recurrence; Registries; Reporting; Research; Research Personnel; Resource Allocation; Resources; Risk; Rural; Sample Size; Screening procedure; Secondary Prevention; Specificity; Standardization; Stroke; Subgroup; Time; Validation; Variant; algorithmic bias; burden of illness; cohort; data harmonization; data integration; data modeling; data quality; density; design; disability; electronic health data; experience; high risk; implicit bias; improved; improved outcome; insight; machine learning model; machine learning prediction; model development; mortality; mortality risk; novel; novel strategies; post stroke; predictive modeling; prognostic model; prospective; public health relevance; risk stratification; role model; rural area; sex; social health determinants; stroke model; stroke patient; trait; trend; urban area

Machine Learning Prediction of 1-Year Mortality and Recurrence after Ischemic Stroke Using Enriched EHR data PROJECT SUMMARY / ABSTRACT Stroke is the leading cause of death and disability worldwide. It has been estimated that the 1-year risk of death and recurrence after a stroke is around 15% and 10%, respectively. Furthermore, a recent report from the Global Burden of Diseases (GBD) has shown a substantial increase in the annual number of strokes and secondary deaths, especially in low-income groups. Recurrent strokes, with an increasing trend, have a higher rate of death and disability. Thus, it is imperative to identify at-risk patients for recurrence and death for proper and timely evaluation, resource allocation, and targeted prevention. The investigators’ recently published review indicates that ─the multiple clinical scores developed for predicting stroke recurrence have only limited clinical utility. Similarly, current stroke prognostic models vary widely in quality; prediction models of post-stroke mortality are limited by their validation cohort size, breadth of clinical variables, and overall usefulness. The investigators have recently developed machine learning-based models of post-stroke all-cause mortality and recurrence using electronic health records (EHR) data. Despite promising results, our current pilot predictive models are limited to a single health system and may have inadequate generalizability due to implicit bias. This proposal seeks to expand and improve predictive models through the creative use of vetted EHR data for ischemic stroke patients from three large and different health systems (Penn State Health, Geisinger, and Johns Hopkins), caring for more than eight million people in rural and urban areas. This project will further explore the predictive value of social determinants of health (SDoH) when added to the clinical data. The investigators propose an integrative approach to design parameter-optimized and interpretable models, leveraging enriched EHR to identify the risk of ischemic stroke recurrence and all-cause mortality. Aim 1: Standardize EHR-based data across health care centers to identify clusters of ischemic stroke patients with common traits. Aim 2: Develop optimal interpretable ensemble models to predict 1-year mortality and recurrence after an ischemic stroke. Aim 3: Validate, prospectively and externally, ensemble models for 1-year mortality and stroke recurrence. This proposal includes model development with internal, external, and temporal validation and lays the foundation for an impact study to provide evidence of clinical utility. The investigators envision that this study will lead to EHR-based screening tools that can flag high-risk stroke patients for more targeted secondary prevention.

使用机器学习预测缺血性中风后 1 年死亡率和复发率 丰富的 EHR 数据 项目概要/摘要 中风是全世界死亡和残疾的主要原因。据估计，1年的风险 中风后死亡和复发率分别约为 15% 和 10%。此外，最近的一份报告显示 全球疾病负担（GBD）显示每年中风和中风的人数大幅增加 继发性死亡，尤其是低收入群体。复发性中风有增加的趋势，发病率较高 死亡率和残疾率。因此，必须识别有复发和死亡风险的患者，以采取适当的措施 及时评估、配置资源、针对性预防。研究人员最近发表的评论 表明 ─ 为预测中风复发而开发的多种临床评分仅具有有限的临床意义 公用事业。同样，当前的中风预后模型在质量上也存在很大差异。中风后死亡率的预测模型 受到验证队列规模、临床变量的广度和整体有用性的限制。调查人员 最近开发了基于机器学习的中风后全因死亡率和复发模型 电子健康记录 (EHR) 数据。尽管结果令人鼓舞，但我们当前的试点预测模型仍然有限 仅限于单一卫生系统，并且由于隐性偏见，可能没有足够的普遍性。 该提案旨在通过创造性地使用经过审查的 EHR 数据来扩展和改进预测模型 来自三个大型不同卫生系统（宾夕法尼亚州立大学卫生系统、Geisinger 和 约翰·霍普金斯大学），为农村和城市地区超过 800 万人提供护理。本项目将进一步探索 添加到临床数据后的健康社会决定因素 (SDoH) 的预测价值。调查人员 提出一种综合方法来设计参数优化和可解释的模型，利用丰富的 EHR 用于确定缺血性中风复发和全因死亡率的风险。目标 1：标准化基于 EHR 的 跨医疗保健中心的数据来识别具有共同特征的缺血性中风患者群。目的 2：开发最佳可解释的整体模型来预测缺血后 1 年死亡率和复发 中风。目标 3：前瞻性和外部验证 1 年死亡率和中风的整体模型 复发。 该提案包括具有内部、外部和时间验证的模型开发，并奠定了 影响研究的基础，以提供临床实用性的证据。研究人员预计这项研究将 基于 EHR 的筛查工具可以标记高风险中风患者，以进行更有针对性的二级预防。