Elizabeth Levy, Dru Claar, Ivan Co, Barry D Fuchs, Jennifer Ginestra, Rachel Kohn, Jakob I McSparron, Bhavik Patel, Gary E Weissman, Meeta Prasad Kerlin, Michael W Sjoding
{"title":"Development and External Validation of a Detection Model to Retrospectively Identify Patients With Acute Respiratory Distress Syndrome.","authors":"Elizabeth Levy, Dru Claar, Ivan Co, Barry D Fuchs, Jennifer Ginestra, Rachel Kohn, Jakob I McSparron, Bhavik Patel, Gary E Weissman, Meeta Prasad Kerlin, Michael W Sjoding","doi":"10.1097/CCM.0000000000006662","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>The aim of this study was to develop and externally validate a machine-learning model that retrospectively identifies patients with acute respiratory distress syndrome (acute respiratory distress syndrome [ARDS]) using electronic health record (EHR) data.</p><p><strong>Design: </strong>In this retrospective cohort study, ARDS was identified via physician-adjudication in three cohorts of patients with hypoxemic respiratory failure (training, internal validation, and external validation). Machine-learning models were trained to classify ARDS using vital signs, respiratory support, laboratory data, medications, chest radiology reports, and clinical notes. The best-performing models were assessed and internally and externally validated using the area under receiver-operating curve (AUROC), area under precision-recall curve, integrated calibration index (ICI), sensitivity, specificity, positive predictive value (PPV), and ARDS timing.</p><p><strong>Patients: </strong>Patients with hypoxemic respiratory failure undergoing mechanical ventilation within two distinct health systems.</p><p><strong>Interventions: </strong>None.</p><p><strong>Measurements and main results: </strong>There were 1,845 patients in the training cohort, 556 in the internal validation cohort, and 199 in the external validation cohort. ARDS prevalence was 19%, 17%, and 31%, respectively. Regularized logistic regression models analyzing structured data (EHR model) and structured data and radiology reports (EHR-radiology model) had the best performance. During internal and external validation, the EHR-radiology model had AUROC of 0.91 (95% CI, 0.88-0.93) and 0.88 (95% CI, 0.87-0.93), respectively. Externally, the ICI was 0.13 (95% CI, 0.08-0.18). At a specified model threshold, sensitivity and specificity were 80% (95% CI, 75%-98%), PPV was 64% (95% CI, 58%-71%), and the model identified patients with a median of 2.2 hours (interquartile range 0.2-18.6) after meeting Berlin ARDS criteria.</p><p><strong>Conclusions: </strong>Machine-learning models analyzing EHR data can retrospectively identify patients with ARDS across different institutions.</p>","PeriodicalId":10765,"journal":{"name":"Critical Care Medicine","volume":" ","pages":""},"PeriodicalIF":7.7000,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Critical Care Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/CCM.0000000000006662","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CRITICAL CARE MEDICINE","Score":null,"Total":0}
引用次数: 0
Abstract
Objective: The aim of this study was to develop and externally validate a machine-learning model that retrospectively identifies patients with acute respiratory distress syndrome (acute respiratory distress syndrome [ARDS]) using electronic health record (EHR) data.
Design: In this retrospective cohort study, ARDS was identified via physician-adjudication in three cohorts of patients with hypoxemic respiratory failure (training, internal validation, and external validation). Machine-learning models were trained to classify ARDS using vital signs, respiratory support, laboratory data, medications, chest radiology reports, and clinical notes. The best-performing models were assessed and internally and externally validated using the area under receiver-operating curve (AUROC), area under precision-recall curve, integrated calibration index (ICI), sensitivity, specificity, positive predictive value (PPV), and ARDS timing.
Patients: Patients with hypoxemic respiratory failure undergoing mechanical ventilation within two distinct health systems.
Interventions: None.
Measurements and main results: There were 1,845 patients in the training cohort, 556 in the internal validation cohort, and 199 in the external validation cohort. ARDS prevalence was 19%, 17%, and 31%, respectively. Regularized logistic regression models analyzing structured data (EHR model) and structured data and radiology reports (EHR-radiology model) had the best performance. During internal and external validation, the EHR-radiology model had AUROC of 0.91 (95% CI, 0.88-0.93) and 0.88 (95% CI, 0.87-0.93), respectively. Externally, the ICI was 0.13 (95% CI, 0.08-0.18). At a specified model threshold, sensitivity and specificity were 80% (95% CI, 75%-98%), PPV was 64% (95% CI, 58%-71%), and the model identified patients with a median of 2.2 hours (interquartile range 0.2-18.6) after meeting Berlin ARDS criteria.
Conclusions: Machine-learning models analyzing EHR data can retrospectively identify patients with ARDS across different institutions.
期刊介绍：
Critical Care Medicine is the premier peer-reviewed, scientific publication in critical care medicine. Directed to those specialists who treat patients in the ICU and CCU, including chest physicians, surgeons, pediatricians, pharmacists/pharmacologists, anesthesiologists, critical care nurses, and other healthcare professionals, Critical Care Medicine covers all aspects of acute and emergency care for the critically ill or injured patient.
Each issue presents critical care practitioners with clinical breakthroughs that lead to better patient care, the latest news on promising research, and advances in equipment and techniques.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
