SCH: A New Computational Framework for Learning from Imbalanced Biomedical Data

SCH：一种从不平衡生物医学数据中学习的新计算框架

• 批准号: 10816630
• 负责人: Ying Cui
• 金额: $ 30万
• 依托单位: UNIVERSITY OF MINNESOTA
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-01 至 2027-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10816630
• 关键词: Adoption; Breast Cancer survivor; Cardiotoxicity; Cardiovascular Diseases; Characteristics; Chronic; Classification; Clinical; Data; Development; Diagnosis; Disease Outcome; Electronic Health Record; Event; Foundations; General Population; Goals; Image; Incidence; Individual; Learning; Morbidity - disease rate; Patients; Solid; Structure; Survival Rate; Time; Treatment Protocols; breast cancer diagnosis; cancer prevention; cardiovascular disorder risk; cardiovascular risk factor; computer framework; electronic health record system; evidence based guidelines; improved; malignant breast neoplasm; mortality; multimodality; point of care; predictive tools; prevent; risk prediction; risk prediction model; success

Advances in cancer prevention, diagnosis, and treatment have dramatically improved long-term survival of those diagnosed with breast cancer. However, this success has been tempered by a parallel increased incidence of chronic conditions in breast cancer survivors, in particular cardiovascular disease (CVD), due at least in part to cardiotoxic treatment regimens. Current evidence-based guidelines for preventing and controlling CVD in breast cancer survivors are broad, and we lack clear guidance for assessing individualized risks of cardiovascular events. Existing CVD risk prediction models focus on the general population and rely only on a limited number of variables. The adoption and integration of electronic health record (EHR) systems has provided a wealth of information about individual characteristics at the point of care, including unstructured clinical narratives, imaging data, and structured clinical variables. However, the real-world EHR data is highly imbalanced including the fraction of patients with CVD outcomes and the uniform distribution of time for the CVD development since BC diagnosis. Our overarching goal is to develop solid computational and theoretical foundations for learning from imbalanced real-world data, with an emphasis on BC-CVD outcome risk prediction. Specifically, we will develop a computational framework for imbalanced classification and imbalanced regression tasks on the CVD risk prediction among BC survivors using multimodal EHR data. The successful implementation of this project would lay a computational foundation for imbalanced learning and can provide more accurate tools for predicting BC CVD outcomes.

预防癌症，诊断和治疗的进步已大大提高了长期生存 那些被诊断为乳腺癌的人。但是，这一成功已通过平行的增加来纠正 乳腺癌幸存者的慢性病发生率，特别是心血管疾病（CVD），应有的 至少部分用于心脏毒性治疗方案。最新的基于证据的预防指南和 控制乳腺癌幸存者中的CVD很广泛，我们缺乏评估的明确指导 心血管事件的个性化风险。现有的CVD风险预测模型集中于一般 人口，仅依靠有限数量的变量。电子的采用和集成 健康记录（EHR）系统提供了有关个人特征的大量信息 护理点，包括非结构化的临床叙述，成像数据和结构化临床变量。 但是，现实世界中的EHR数据高度不平衡，包括CVD患者的比例 自BC诊断以来，结局和CVD开发时间的均匀分布。我们的 总体目标是开发可靠的计算和理论基础来学习 现实世界中的数据不平衡，重点是BC-CVD结果风险预测。具体来说，我们会的 开发一个计算框架，以用于分类不平衡的分类和不平衡的回归任务 CVD使用多模式EHR数据之间的CVD风险预测。成功实施 该项目将为学习不平衡的学习奠定计算基础，并可以提供更准确的 预测BC CVD结果的工具。