Pandey Dinesh, Jahanabadi Hossein, D'Arcy Jack, Doherty Suzanne, Vo Hung, Jones Daryl, Bellomo Rinaldo
Data Analytics Research and Evaluation (DARE) Centre, The University of Melbourne and Austin Hospital, Melbourne, VIC, Australia; Clinical Analytics and Reporting, Performance Reporting and Decision Support, Austin Health, Melbourne, VIC, Australia.
Department of Intensive Care, Austin Health, Heidelberg, Victoria, Australia.
Aust Crit Care. 2025 Mar;38(2):101143. doi: 10.1016/j.aucc.2024.101143. Epub 2024 Dec 5.
The timely identification and transfer of critically ill patients from the emergency department (ED) to the intensive care unit (ICU) is important for patient care and ED workflow practices.
We aimed to develop a predictive model for ICU admission early in the course of an ED presentation.
We extracted retrospective data from the electronic medical record and applied natural language processing and machine learning to information available early in the course of an ED presentation to develop a predictive model for ICU admission.
We studied 484 094 adult (≥18 years old) ED presentations, amongst which direct admission to the ICU occurred in 3955 (0.82%) instances. We trained machine learning in 323 678 ED presentations and performed testing/validation in 160 416 (70 546 for testing and 89 870 for validation). Although the area under the receiver operating characteristics curve was 0.92, the F1 score (0.177) and Matthews correlation coefficient (0.257) suggested substantial imbalance in the dataset. The strongest weighted variables in the predictive model at the 30-min timepoint were ED triage category, arrival via ambulance, quick Sequential Organ Failure Assessment score, baseline heart rate, and the number of inpatient presentations in the prior 12 months. Using a likelihood of ICU admission of more than 75%, for activation of automated ICU referral, we estimated the model would generate 2.7 triggers per day.
The infrequency of ICU admissions as a proportion of ED presentations makes accurate early prediction of admissions challenging. Such triggers are likely to generate a moderate number of false positives.
及时识别危重症患者并将其从急诊科（ED）转运至重症监护病房（ICU）对于患者护理和急诊科工作流程实践至关重要。
我们旨在开发一种在急诊科就诊过程早期预测ICU收治的模型。
我们从电子病历中提取回顾性数据，并将自然语言处理和机器学习应用于急诊科就诊过程早期可得的信息，以开发一种ICU收治预测模型。
我们研究了484094例成年（≥18岁）急诊科就诊病例，其中3955例（0.82%）直接入住ICU。我们在323678例急诊科就诊病例中训练机器学习，并在160416例病例中进行测试/验证（70546例用于测试，89870例用于验证）。尽管受试者操作特征曲线下面积为0.92，但F1分数（0.177）和马修斯相关系数（0.257）表明数据集中存在严重失衡。在30分钟时间点预测模型中权重最强的变量是急诊科分诊类别、救护车送达、快速序贯器官衰竭评估评分、基线心率以及过去12个月内住院就诊次数。使用ICU收治可能性超过75%来启动自动ICU转诊，我们估计该模型每天将产生2.7次触发。
ICU收治占急诊科就诊病例的比例较低，使得准确早期预测收治具有挑战性。此类触发可能会产生一定数量的假阳性。
