AE2Vec: Medical concept embedding and time-series analysis for automated adverse event detection

AE2Vec：用于自动不良事件检测的医学概念嵌入和时间序列分析

• 批准号: 10751964
• 负责人: Steven Tran
• 金额: $ 4.66万
• 依托单位: NORTHWESTERN UNIVERSITY AT CHICAGO
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10751964
• 关键词: Address; Adoption; Adverse drug event; Adverse event; Algorithms; Award; Cancer Patient; Clinical; Code; Complex; Consumption; Couples; Data; Data Analyses; Detection; Development; Devices; Diagnosis; Dimensions; Disease; Electronic Health Record; Event; Explosion; Fellowship; Goals; Graph; Health Care Costs; Healthcare; Human; Immune checkpoint inhibitor; International Classification of Diseases; Intervention; Label; Laboratories; Length of Stay; Manuals; Maps; Medical; Medical History; Methods; Mining; Nature; Neighborhoods; Outcome; Patient Care; Patient-Focused Outcomes; Patients; Pattern; Pharmaceutical Preparations; Phenotype; Physicians; Population; Procedures; Recording of previous events; Reporting; Research; Risk Factors; Series; Site; Techniques; Testing; Time; Time Series Analysis; Work; Writing; automated analysis; biomedical informatics; body system; career networking; checkpoint therapy; cohort; disease diagnosis; disease phenotype; experience; immune-related adverse events; improved; informatics tool; interest; machine learning algorithm; mortality; novel; prognostication; skills; text searching; time use; vector

7. Project Summary/Abstract Adverse events pose a significant challenge to medical interventions (drugs, devices, others) with an estimated 2.3 million cases of adverse drug events between 1969-2002. Adverse events are responsible for longer hospital stay, higher healthcare costs, and higher mortality. There is a clear need for adverse event surveillance, but the standards of manual chart review and voluntary reporting are time-consuming and unsustainable. Voluntary reporting also misses most adverse event cases. The widespread adoption of electronic health records (EHRs) captures medical data for the majority of US patients and presents an opportunity for sustainable adverse event surveillance via automated strategies. However, there are two barriers to automating adverse event surveillance. First, adverse events are poorly represented by International Classification of Disease (ICD) diagnosis codes. This has inhibited efforts to use simple rules-based code or flag/trigger approaches, while complex and high-performing text-mining approaches are thwarted by the difficulty of adapting them to other healthcare sites and large data networks for wider surveillance. Second, temporal information in the EHR inherent to adverse event timing and sequencing is challenging to capture. The challenges to existing approaches include – treatment of related medical concepts as independent entities, the rapid explosion of data inhibiting scaling to large numbers of medical concepts, and human interpretability. Our overarching goal is to expand on existing biomedical informatics tools to better capture adverse events and more comprehensively represent the full patient medical trajectory to identify archetypes of adverse event development. We will pilot these methods for cancer patients undergoing immune checkpoint inhibitor (ICI) therapy. In Specific Aim 1, we will incorporate medical concept embedding and clustering methods to draw a “map” of disease, segmented into “neighborhoods” labeled for the conditions they describe, including adverse events. In Specific Aim 2, we will test a novel method for tracking patient trajectories on a map of disease and hypothesize that we can identify archetypal patient trajectories that have different clinical outcomes using time-series clustering. This work addresses gaps in EHR-based phenotyping and adverse event surveillance. It has the potential to inform risk factor identification, prediction of adverse event development, and prognostication of patient outcomes, as well as lay a crucial stepping-stone for further progression of EHR-based phenotyping in biomedical informatics. This fellowship award will enable me to develop my skills in biomedical informatics methods, integrate clinical perspective into my research, hone my writing and presentation skills, and expand my professional network. At the conclusion of this award, I will have made strides towards becoming an independent physician-informaticist, fusing clinical experience and informatics tools to improve patient care.

7. 项目总结/摘要 不良事件对医疗干预（药物、设备等）构成重大挑战，预计 1969 年至 2002 年间，发生了 230 万例药物不良事件。不良事件导致住院时间延长。 住院时间、更高的医疗费用和更高的死亡率显然需要进行不良事件监测，但 手动图表审查和自愿报告的标准既耗时又不可持续。 报告还遗漏了大多数不良事件案例。电子健康记录 (EHR) 的广泛采用。 捕获大多数美国患者的医疗数据，并为可持续不良事件提供机会 然而，自动化不良事件监测存在两个障碍。 首先，国际疾病分类（ICD）诊断无法很好地反映不良事件 这阻碍了使用简单的基于规则的代码或标志/触发方法的努力，同时又复杂且复杂。 高性能文本挖掘方法因难以适应其他医疗保健网站而受到阻碍 其次，电子病历中不良事件固有的时间信息。 事件时序和顺序很难捕捉，现有方法面临的挑战包括： 将相关医学概念视为独立实体，数据的快速爆炸抑制了扩展 我们的首要目标是扩展现有的医学概念和人类可解释性。 生物医学信息学工具可以更好地捕获不良事件并更全面地代表 我们将试点完整的患者医疗轨迹，以确定不良事件发展的原型。 在具体目标 1 中，我们将介绍针对接受免疫检查点抑制剂 (ICI) 治疗的癌症患者的方法。 医学概念嵌入和聚类方法绘制疾病“地图”，细分为 在特定目标 2 中，我们将根据其描述的情况（包括不良事件）标记“社区”。 测试一种在我们可以识别的疾病和陷阱地图上跟踪患者轨迹的新方法 使用时间序列聚类具有不同临床结果的原型患者轨迹。 解决基于电子病历的表型分析和不良事件监测方面的差距，它有可能提供信息。 危险因素识别、不良事件发展预测和患者预后 结果，并为基于 EHR 的表型分析的进一步发展奠定了重要的基石 该奖学金将使我能够发展我在生物医学信息学方面的技能。 方法，将临床观点融入我的研究，磨练我的写作和演讲技巧，并扩展 在这个奖项结束时，我将在成为一名专业人士方面取得长足进步。 独立的医师信息学家，融合临床经验和信息学工具来改善患者护理。