Leveraging electronic health records to identify risky alcohol use prior to surgery

利用电子健康记录在手术前识别危险的饮酒情况

• 批准号: 10213578
• 负责人: Anne Christie Fernandez
• 金额: $ 19.91万
• 依托单位: UNIVERSITY OF MICHIGAN AT ANN ARBOR
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-10 至 2022-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10213578
• 关键词: Accounting; Address; Adverse event; Agreement; Alcohol abuse; Alcohol consumption; Alcohol withdrawal syndrome; Alcohols; Algorithms; Biological Markers; Classification; Clinic; Clinical; Clinical Data; Clinical Research; Code; Collaborations; Communities; Community Health; Computer Assisted; Consumption; Data; Data Collection; Data Element; Data Set; Early identification; Electronic Health Record; Evaluation; Event; Foundations; Funding; Future; Guidelines; Health; Health Expenditures; Health Services Accessibility; Hospitals; Individual; Institutes; International Classification of Disease Codes; Intervention; Intervention Studies; Label; Lead; Length of Stay; Link; Machine Learning; Measures; Methodology; Methods; Natural Language Processing; Operative Surgical Procedures; Opioid; Outcome; Outcome Study; Patients; Pharmaceutical Preparations; Phase; Phenotype; Postoperative Period; Precision Health; Research; Research Support; Risk; Risk Factors; Severities; Structure; Surgical complication; Testing; Time; Training; Work; alcohol abstinence; alcohol intervention; alcohol risk; alcohol screening; alcohol use disorder; base; care episode; clinical application; cohort; computable phenotypes; computerized tools; cost; direct application; early alcohol use; experience; health care service; high risk; hospital readmission; implementation research; improved; innovation; knowledge base; longitudinal analysis; mortality; novel; phosphatidylethanol; predictive test; prevent; prospective; structured data; surgery outcome; surgical risk; tool; unstructured data

Project Summary/Abstract Patients who consume more than two drinks a day prior to elective surgery are at increased risk of experiencing a myriad of surgical complications, readmissions, and prolonged hospital stays. Fortunately, short-term pre-operative abstinence from alcohol mitigates many surgical risks, and carefully timed interventions can prevent complications and alcohol withdrawal syndrome. However, implementation of pre- operative alcohol interventions requires accurate identification of patients with risky alcohol use at least four weeks prior to surgery. Pre-operative clinics frequently fail to screen for alcohol use or do so too close to the surgery date to allow time for intervention. Electronic health records (EHRs) offer an unprecedented amount of accessible clinical data that can be leveraged to identify risky alcohol use early in the surgical episode of care. Innovative methods are needed to identify data elements and create algorithms to capture risky alcohol use from structured and unstructured EHR data. Natural language processing (NLP) and other machine learning (ML)-based approaches are best suited to extract and analyze alcohol-related clinical narratives, and to synthesize heterogeneous alcohol-related data through computer-assisted methods. The proposed study will leverage EHR data to identify and characterize risky alcohol use among surgical patients to identify cohorts who could benefit from pre-operative alcohol intervention. The study aims are to: 1) develop an electronic, automated computable phenotype to classify risky alcohol use prior to surgery using NLP and ML; 2) validate the algorithm through prospective data collection; and 3) longitudinally evaluate the association between risky alcohol use phenotypes and adverse surgical outcomes including complications and hospital readmissions. Innovative applications of NLP and ML will support evaluation of unstructured EHR data (e.g. clinical notes) and will enable integration of heterogeneous alcohol use data to create the computable phenotype. The aims will be achieved through collaboration of experts in key clinical domains and advanced methodologies. This study will create and validate the first alcohol-specific phenotype-based algorithm for surgical patients, which will support future clinical applications and research into alcohol-related surgical interventions and health outcomes. Study outcomes are expected to have immediate value for identifying cohorts for future implementation research and lead to a new clinical tool for surgical clinics.

项目概要/摘要 择期手术前每天饮酒超过两杯的患者发生以下疾病的风险增加 经历了无数的手术并发症、再入院和长期住院。幸运的是， 术前短期戒酒可以减轻许多手术风险，并且要仔细安排时间 干预措施可以预防并发症和酒精戒断综合症。然而，实施预 有效的酒精干预措施需要准确识别至少有四次饮酒危险的患者 手术前几周。术前诊所经常无法筛查饮酒情况，或者筛查的距离太近。 手术日期以便有时间进行干预。电子健康记录 (EHR) 提供了前所未有的数量 可获得的临床数据可用于在手术护理早期识别危险的饮酒情况。 需要创新方法来识别数据元素并创建算法来捕获危险的饮酒情况 来自结构化和非结构化 EHR 数据。自然语言处理 (NLP) 和其他机器学习 基于 (ML) 的方法最适合提取和分析与酒精相关的临床叙述，并 通过计算机辅助方法合成异构酒精相关数据。拟议的研究将 利用 EHR 数据来识别和描述手术患者中的危险饮酒情况，以确定队列 谁可以从术前酒精干预中受益。该研究的目的是：1）开发一种电子、 使用 NLP 和 ML 自动计算表型，对手术前的危险饮酒进行分类； 2）验证 通过前瞻性数据收集的算法； 3）纵向评估风险之间的关联 饮酒表型和不良手术结果，包括并发症和再入院。 NLP 和 ML 的创新应用将支持非结构化 EHR 数据（例如临床记录）的评估 并将能够整合异质酒精使用数据以创建可计算的表型。目标 将通过关键临床领域的专家和先进方法的合作来实现。这 研究将为手术患者创建并验证第一个基于酒精特异性表型的算法，该算法 将支持未来与酒精相关的手术干预和健康的临床应用和研究 结果。研究结果预计将对确定未来的队列具有直接价值 实施研究并为外科诊所带来新的临床工具。

项目成果

Automated-detection of risky alcohol use prior to surgery using natural language processing.

使用自然语言处理在手术前自动检测有风险的饮酒情况。

• 发表时间: 2024-01
• 作者: Vydiswaran, V G Vinod;Strayhorn, Asher;Weber, Katherine;Stevens, Haley;Mellinger, Jessica;Winder, G Scott;Fernandez, Anne C
• 通讯作者: Fernandez, Anne C