Churpek Matthew M, Carey Kyle A, Snyder Ashley, Winslow Christopher J, Gilbert Emily, Shah Nirav S, Patterson Brian W, Afshar Majid, Weiss Alan, Amin Devendra N, Rhodes Deborah J, Edelson Dana P
Department of Medicine, University of Wisconsin-Madison, Madison, WI.
Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI.
Crit Care Explor. 2025 Mar 26;7(4):e1232. doi: 10.1097/CCE.0000000000001232. eCollection 2025 Apr 1.
Early detection of clinical deterioration using machine-learning early warning scores may improve outcomes. However, most implemented scores were developed using logistic regression, only underwent retrospective validation, and were not tested in important subgroups.
The objective of our multicenter retrospective and prospective observational study was to develop and prospectively validate a gradient-boosted machine model (eCARTv5) for identifying clinical deterioration on the wards.
All adult patients admitted to the inpatient medical-surgical wards at seven hospitals in three health systems for model development (2006-2022).
All adult patients admitted to the inpatient medical-surgical wards and at 21 hospitals from three health systems for retrospective (2009-2023) and prospective (2023-2024) external validation.
Predictor variables (demographics, vital signs, documentation, and laboratory values) were used in a gradient-boosted trees algorithm to predict ICU transfer or death in the next 24 hours. The developed model (eCARTv5) was compared with the Modified Early Warning Score (MEWS), the National Early Warning Score (NEWS), and eCARTv2 using the area under the receiver operating characteristic curve (AUROC).
The development cohort included 901,491 admissions, the retrospective validation cohort included 1,769,461 admissions, and the prospective validation cohort included 205,946 admissions. In retrospective validation, eCARTv5 had the highest AUROC (0.834; 95% CI, 0.834-0.835), followed by eCARTv2 (0.775 [95% CI, 0.775-0.776]), NEWS (0.766 [95% CI, 0.766-0.767]), and MEWS (0.704 [95% CI, 0.703-0.704]). eCARTv5's performance remained high (AUROC ≥0.80) across a range of patient demographics, clinical conditions, and during prospective validation.
We developed eCARTv5, which performed better than eCARTv2, NEWS, and MEWS retrospectively, prospectively, and across a range of subgroups. These results served as the foundation for Food and Drug Administration clearance for its use in identifying deterioration in hospitalized ward patients.
使用机器学习早期预警评分来早期发现临床病情恶化可能会改善治疗结果。然而，大多数已实施的评分是使用逻辑回归开发的，仅经过回顾性验证，且未在重要亚组中进行测试。
我们多中心回顾性和前瞻性观察性研究的目的是开发并前瞻性验证一种梯度提升机器模型（eCARTv5），用于识别病房中的临床病情恶化。
来自三个医疗系统的七家医院的内科和外科住院病房收治的所有成年患者用于模型开发（2006 - 2022年）。
来自三个医疗系统的21家医院的内科和外科住院病房收治的所有成年患者用于回顾性（2009 - 2023年）和前瞻性（2023 - 2024年）外部验证。
预测变量（人口统计学、生命体征、病历记录和实验室值）用于梯度提升树算法，以预测未来24小时内的重症监护病房（ICU）转入或死亡情况。使用受试者操作特征曲线下面积（AUROC）将开发的模型（eCARTv5）与改良早期预警评分（MEWS）、国家早期预警评分（NEWS）和eCARTv2进行比较。
开发队列包括901,491例入院患者，回顾性验证队列包括1,769,461例入院患者，前瞻性验证队列包括205,946例入院患者。在回顾性验证中，eCARTv5的AUROC最高（0.834；95%可信区间，0.834 - 0.835），其次是eCARTv2（0.775 [95%可信区间，0.775 - 0.776]）、NEWS（0.766 [95%可信区间，0.766 - 0.767]）和MEWS（0.704 [95%可信区间，0.703 - 0.704]）。在一系列患者人口统计学、临床状况以及前瞻性验证期间，eCARTv5的性能保持较高（AUROC≥0.80）。
我们开发了eCARTv5，其在回顾性、前瞻性以及一系列亚组中的表现均优于eCARTv2、NEWS和MEWS。这些结果为美国食品药品监督管理局批准其用于识别住院病房患者的病情恶化奠定了基础。
