Lee Joon, Maslove David M
School of Public Health and Health Systems, University of Waterloo, Waterloo, Ontario, Canada
Department of Medicine & Critical Care Program, Queen's University, Kingston, Ontario, Canada.
J Intensive Care Med. 2017 Jan;32(1):38-47. doi: 10.1177/0885066615585951. Epub 2015 May 12.
Severity of illness (SOI) scores are traditionally based on archival data collected from a wide range of clinical settings. Mortality prediction using SOI scores tends to underperform when applied to contemporary cases or those that differ from the case-mix of the original derivation cohorts. We investigated the use of local clinical data captured from hospital electronic medical records (EMRs) to improve the predictive performance of traditional severity of illness scoring.
We conducted a retrospective analysis using data from the Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) database, which contains clinical data from the Beth Israel Deaconess Medical Center in Boston, Massachusetts. A total of 17 490 intensive care unit (ICU) admissions with complete data were included, from 4 different service types: medical ICU, surgical ICU, coronary care unit, and cardiac surgery recovery unit. We developed customized SOI scores trained on data from each service type, using the clinical variables employed in the Simplified Acute Physiology Score (SAPS). In-hospital, 30-day, and 2-year mortality predictions were compared with those obtained from using the original SAPS using the area under the receiver-operating characteristics curve (AUROC) as well as the area under the precision-recall curve (AUPRC). Test performance in different cohorts stratified by severity of organ injury was also evaluated.
Most customized scores (30 of 39) significantly outperformed SAPS with respect to both AUROC and AUPRC. Enhancements over SAPS were greatest for patients undergoing cardiovascular surgery and for prediction of 2-year mortality.
Custom models based on ICU-specific data provided better mortality prediction than traditional SAPS scoring using the same predictor variables. Our local data approach demonstrates the value of electronic data capture in the ICU, of secondary uses of EMR data, and of local customization of SOI scoring.
疾病严重程度（SOI）评分传统上基于从广泛临床环境中收集的存档数据。当将SOI评分用于当代病例或与原始推导队列病例组合不同的病例时，其死亡率预测往往表现不佳。我们研究了利用从医院电子病历（EMR）中获取的本地临床数据来提高传统疾病严重程度评分的预测性能。
我们使用重症监护多参数智能监测II（MIMIC-II）数据库中的数据进行了一项回顾性分析，该数据库包含马萨诸塞州波士顿贝斯以色列女执事医疗中心的临床数据。共纳入了17490例有完整数据的重症监护病房（ICU）入院病例，来自4种不同的服务类型：内科ICU、外科ICU、冠心病监护病房和心脏手术恢复病房。我们使用简化急性生理学评分（SAPS）中使用的临床变量，开发了针对每种服务类型的数据进行训练的定制SOI评分。将院内、30天和2年死亡率预测与使用原始SAPS获得的预测进行比较，使用受试者操作特征曲线下面积（AUROC）以及精确召回率曲线下面积（AUPRC）。还评估了按器官损伤严重程度分层的不同队列中的测试性能。
大多数定制评分（39个中的30个）在AUROC和AUPRC方面均显著优于SAPS。对于接受心血管手术的患者和2年死亡率的预测，相对于SAPS的改进最大。
基于ICU特定数据的定制模型在使用相同预测变量时比传统SAPS评分提供了更好的死亡率预测。我们的本地数据方法证明了ICU中电子数据采集、EMR数据的二次使用以及SOI评分的本地定制的价值。
