Wisniewski Alex M, Wang Xin-Qun, Sutherland Grant, Rotar Evan P, Strobel Raymond J, Young Andrew, Norman Anthony V, Beller Jared, Quader Mohammed, Teman Nicholas R
Division of Cardiac Surgery, University of Virginia, Charlottesville, Va.
Department of Public Health Sciences, University of Virginia School of Medicine, Charlottesville, Va.
J Thorac Cardiovasc Surg. 2024 Nov 16. doi: 10.1016/j.jtcvs.2024.11.009.
Intensive care unit length of stay (ICU LOS) accounts for a large percentage of inpatient cost after cardiac surgery. The Society of Thoracic Surgeons risk calculator predicts total LOS but does not discriminate between ICU and non-ICU time. We sought to develop a predictive model of prolonged ICU LOS.
Adult patients undergoing Society of Thoracic Surgeons index operations within a regional collaborative (2014-2021) were included. Prolonged ICU LOS was defined as ICU care for ≥72 hours postoperatively. A logistic regression model was used to develop a prediction model for the prolonged ICU LOS with prespecified risk factors identified from our previous single-center study. Internal prediction model validation was determined by bootstrapping resampling method. The prediction model performance was assessed by measures of discrimination and calibration.
We identified 37,519 patients that met inclusion criteria with 11,801 (31.5%) patients experiencing prolonged ICU stay. From the logistic regression model, there were significant associations between prolonged ICU LOS and all pre-specified factors except sleep apnea (all P < .05). Model for End-Stage Liver Disease, preoperative intra-aortic balloon pump use, and procedure types were the most significant predictors of prolonged ICU LOS (all P < .0001). Our prediction model had not only a good discrimination power (bootstrapped-corrected C-index = 0.71) but also excellent calibration (bootstrapped-corrected mean absolute error = 0.005).
Prolonged ICU stay after cardiac surgery can be predicted with good predictive accuracy using preoperative data and may aid in patient counseling and resource allocation. Through use of a state-wide database, the application of this model may extend to other practices.
重症监护病房住院时间（ICU LOS）在心脏手术后的住院费用中占很大比例。胸外科医师协会风险计算器可预测总住院时间，但无法区分ICU和非ICU时间。我们试图开发一种预测ICU LOS延长的模型。
纳入在区域协作范围内（2014 - 2021年）接受胸外科医师协会指数手术的成年患者。延长的ICU LOS定义为术后ICU护理≥72小时。使用逻辑回归模型，根据我们之前的单中心研究确定的预先设定的风险因素，开发预测延长ICU LOS的模型。通过自抽样重采样方法进行内部预测模型验证。通过辨别力和校准度评估预测模型的性能。
我们确定了37519名符合纳入标准的患者，其中11801名（31.5%）患者经历了延长的ICU住院时间。从逻辑回归模型来看，除睡眠呼吸暂停外，延长的ICU LOS与所有预先设定的因素之间均存在显著关联（所有P < 0.05）。终末期肝病模型、术前主动脉内球囊泵的使用和手术类型是延长ICU LOS的最显著预测因素（所有P < 0.0001）。我们的预测模型不仅具有良好的辨别力（自抽样校正C指数 = 0.71），而且校准度极佳（自抽样校正平均绝对误差 = 0.005）。
使用术前数据可以很好地预测心脏手术后延长的ICU住院时间，这可能有助于患者咨询和资源分配。通过使用全州范围的数据库，该模型的应用可能会扩展到其他医疗机构。
