A Computable Electronic Health Record ARDS Classifier and the Association Between the MUC5B Promoter Polymorphism and ARDS in Critically Ill Adults

CHEST critical care Pub Date : 2025-03-18 DOI:10.1016/j.chstcc.2025.100150

V. Eric Kerchberger MD , J. Brennan McNeil BS , Neil Zheng MD , Diana Chang PhD , Carrie M. Rosenberger PhD , Angela J. Rogers MD , Julie A. Bastarache MD , QiPing Feng PhD , Wei-Qi Wei MD, PhD , Lorraine B. Ware MD

{"title":"A Computable Electronic Health Record ARDS Classifier and the Association Between the MUC5B Promoter Polymorphism and ARDS in Critically Ill Adults","authors":"V. Eric Kerchberger MD , J. Brennan McNeil BS , Neil Zheng MD , Diana Chang PhD , Carrie M. Rosenberger PhD , Angela J. Rogers MD , Julie A. Bastarache MD , QiPing Feng PhD , Wei-Qi Wei MD, PhD , Lorraine B. Ware MD","doi":"10.1016/j.chstcc.2025.100150","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Large population-based DNA biobanks linked to electronic health records (EHRs) may provide novel opportunities to identify genetic drivers of ARDS.</div></div><div><h3>Research Question</h3><div>Can a computerized algorithm identify ARDS in a large EHR biobank database, and can this be used to identify ARDS genetic risk factors?</div></div><div><h3>Study Design and Methods</h3><div>We developed a classifier algorithm to identify a diagnosis of ARDS as identified from the electronic health record (EHR-ARDS) using diagnostic billing codes, laboratory test results, and chest radiography report text. The classifier model performance was evaluated against investigator-adjudicated ARDS using standard classification metrics including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the Cohen κ value. After confirming acceptable classifier performance, we evaluated the association between EHR-ARDS and the <em>MUC5B</em> promoter polymorphism rs35705950 in 2 parallel genotyped cohorts: a prospective biomarker cohort of critically ill adults (Validating Acute Lung Injury Biomarkers for Diagnosis [VALID]) and a retrospective cohort from our institution’s de-identified EHR biobank, BioVU.</div></div><div><h3>Results</h3><div>We included 2,795 patients from VALID and 9,025 hospitalized participants from BioVU. EHR-ARDS showed moderate agreement with investigator-adjudicated ARDS (VALID: sensitivity, 0.86; specificity, 0.70; PPV, 0.49; NPV, 0.93; and κ, 0.45; BioVU: sensitivity, 0.94; specificity, 0.81; PPV, 0.66; NPV, 0.97; and κ, 0.67). We observed a significant age-gene interaction effect for EHR-ARDS in VALID: among older patients, rs35705950 was associated with increased EHR-ARDS risk (OR, 1.37; 95% CI, 1.05-1.78; <em>P</em> = .019), whereas among younger patients, this association was absent (OR, 0.92; 95% CI, 0.70-1.21; <em>P</em> = .55). In BioVU, rs35705950 was associated with EHR-ARDS among all participants (OR, 1.20; 95% CI, 1.01-1.43; <em>P</em> = .043); however, this effect did not vary by age.</div></div><div><h3>Interpretation</h3><div>The <em>MUC5B</em> promoter polymorphism was associated with EHR-ARDS in 2 parallel cohorts of at-risk adults. An age-gene effect modification was observed in VALID, whereas BioVU identified a consistent association between <em>MUC5B</em> and EHR-ARDS regardless of age. Our study highlights the potential for EHR biobanks to enable precision medicine ARDS studies.</div></div>","PeriodicalId":93934,"journal":{"name":"CHEST critical care","volume":"3 3","pages":"Article 100150"},"PeriodicalIF":0.0000,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CHEST critical care","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2949788425000231","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Large population-based DNA biobanks linked to electronic health records (EHRs) may provide novel opportunities to identify genetic drivers of ARDS.

Research Question

Can a computerized algorithm identify ARDS in a large EHR biobank database, and can this be used to identify ARDS genetic risk factors?

Study Design and Methods

We developed a classifier algorithm to identify a diagnosis of ARDS as identified from the electronic health record (EHR-ARDS) using diagnostic billing codes, laboratory test results, and chest radiography report text. The classifier model performance was evaluated against investigator-adjudicated ARDS using standard classification metrics including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the Cohen κ value. After confirming acceptable classifier performance, we evaluated the association between EHR-ARDS and the MUC5B promoter polymorphism rs35705950 in 2 parallel genotyped cohorts: a prospective biomarker cohort of critically ill adults (Validating Acute Lung Injury Biomarkers for Diagnosis [VALID]) and a retrospective cohort from our institution’s de-identified EHR biobank, BioVU.

Results

We included 2,795 patients from VALID and 9,025 hospitalized participants from BioVU. EHR-ARDS showed moderate agreement with investigator-adjudicated ARDS (VALID: sensitivity, 0.86; specificity, 0.70; PPV, 0.49; NPV, 0.93; and κ, 0.45; BioVU: sensitivity, 0.94; specificity, 0.81; PPV, 0.66; NPV, 0.97; and κ, 0.67). We observed a significant age-gene interaction effect for EHR-ARDS in VALID: among older patients, rs35705950 was associated with increased EHR-ARDS risk (OR, 1.37; 95% CI, 1.05-1.78; P = .019), whereas among younger patients, this association was absent (OR, 0.92; 95% CI, 0.70-1.21; P = .55). In BioVU, rs35705950 was associated with EHR-ARDS among all participants (OR, 1.20; 95% CI, 1.01-1.43; P = .043); however, this effect did not vary by age.

Interpretation

The MUC5B promoter polymorphism was associated with EHR-ARDS in 2 parallel cohorts of at-risk adults. An age-gene effect modification was observed in VALID, whereas BioVU identified a consistent association between MUC5B and EHR-ARDS regardless of age. Our study highlights the potential for EHR biobanks to enable precision medicine ARDS studies.

查看原文本刊更多论文

可计算电子健康记录ARDS分类器及MUC5B启动子多态性与危重成人ARDS的关系

与电子健康记录（EHRs）相关的大型人群DNA生物库可能为识别ARDS的遗传驱动因素提供新的机会。研究问题：计算机算法能否在大型EHR生物库数据库中识别ARDS，能否用于识别ARDS遗传风险因素？研究设计和方法我们开发了一种分类算法，通过使用诊断账单代码、实验室检查结果和胸片报告文本，从电子健康记录（EHR-ARDS）中识别ARDS诊断。根据研究者判定的ARDS，使用包括敏感性、特异性、阳性预测值（PPV）、阴性预测值（NPV）和Cohen κ值在内的标准分类指标对分类器模型的性能进行评估。在确认了可接受的分类器性能后，我们在两个平行的基因分型队列中评估了EHR- ards与MUC5B启动子多态性rs35705950之间的关系：一个是危重成人的前瞻性生物标志物队列（验证急性肺损伤生物标志物诊断[VALID]），另一个是来自我们机构去鉴定的EHR生物库BioVU的回顾性队列。结果我们纳入了来自VALID的2795名患者和来自BioVU的9025名住院患者。EHR-ARDS与研究者判定的ARDS中度一致(有效：敏感性，0.86；特异性,0.70;PPV 0.49;NPV, 0.93;κ为0.45；BioVU：灵敏度0.94；特异性,0.81;PPV 0.66;NPV, 0.97;κ为0.67)。我们观察到VALID患者EHR-ARDS存在显著的年龄-基因相互作用效应：在老年患者中，rs35705950与EHR-ARDS风险增加相关(OR, 1.37；95% ci, 1.05-1.78；P = 0.019)，而在年轻患者中，这种关联不存在(OR, 0.92；95% ci, 0.70-1.21；P = 0.55)。在BioVU中，rs35705950与所有参与者的EHR-ARDS相关(OR, 1.20；95% ci, 1.01-1.43；P = .043)；然而，这种影响并不因年龄而异。MUC5B启动子多态性在两个平行队列的高危成人中与EHR-ARDS相关。在VALID中观察到年龄基因效应的改变，而BioVU则发现MUC5B与EHR-ARDS之间存在一致的关联，而与年龄无关。我们的研究强调了电子病历生物库在精确医学ARDS研究中的潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

CHEST critical care Critical Care and Intensive Care Medicine, Pulmonary and Respiratory Medicine

自引率

0.00%

发文量