Background Existing models have performed poorly when predicting mortality for patients undergoing venovenous extracorporeal membrane oxygenation (VV-ECMO). This study aimed to develop and validate a machine learning (ML)-based prediction model to predict 90-day mortality in patients undergoing VV-ECMO. Methods This study included 368 patients with acute respiratory failure undergoing VV-ECMO from 16 tertiary hospitals across South Korea between 2012 and 2015. The primary outcome was the 90-day mortality after ECMO initiation. The inputs included all available features (n=51) and those from the electronic health record (EHR) systems without preprocessing (n=40). The discriminatory strengths of ML models were evaluated in both internal and external validation sets. The models were compared with conventional models, such as respiratory ECMO survival prediction (RESP) and predicting death for severe acute respiratory distress syndrome on VV-ECMO (PRESERVE). Results Extreme gradient boosting (XGB) (areas under the receiver operating characteristic curve, AUROC 0.82, 95% CI (0.73 to 0.89)) and light gradient boosting (AUROC 0.81 (95% CI 0.71 to 0.88)) models achieved the highest performance using EHR’s and all other available features. The developed models had higher AUROCs (95% CI 0.76 to 0.82) than those of RESP (AUROC 0.66 (95% CI 0.56 to 0.76)) and PRESERVE (AUROC 0.71 (95% CI 0.61 to 0.81)). Additionally, we achieved an AUROC (0.75) for 90-day mortality in external validation in the case of the XGB model, which was higher than that of RESP (0.70) and PRESERVE (0.67) in the same validation dataset. Conclusions ML prediction models outperformed previous mortality risk models. This model may be used to identify patients who are unlikely to benefit from VV-ECMO therapy during patient selection. Data are available on reasonable request. Aggregated data available by request.

中文翻译：

---

监督机器学习模型可预测全国多中心登记处接受静脉体外膜氧合患者的死亡率

背景 现有模型在预测接受静脉体外膜氧合 (VV-ECMO) 的患者死亡率时表现不佳。本研究旨在开发并验证基于机器学习 (ML) 的预测模型，以预测接受 VV-ECMO 患者的 90 天死亡率。方法 本研究纳入了 2012 年至 2015 年间韩国 16 家三级医院接受 VV-ECMO 治疗的 368 名急性呼吸衰竭患者。主要结局是 ECMO 启动后 90 天的死亡率。输入包括所有可用特征 (n=51) 以及来自未经预处理的电子健康记录 (EHR) 系统的特征 (n=40)。机器学习模型的辨别力在内部和外部验证集中进行了评估。该模型与传统模型进行了比较，例如呼吸 ECMO 生存预测 (RESP) 和 VV-ECMO 预测严重急性呼吸窘迫综合征死亡 (PRESERVE)。结果 极端梯度增强 (XGB)（受试者工作特征曲线下面积，AUROC 0.82，95% CI（0.73 至 0.89））和光梯度增强（AUROC 0.81（95% CI 0.71 至 0.88））模型使用以下方法实现了最高性能EHR 和所有其他可用功能。开发模型的 AUROC（95% CI 0.76 至 0.82）高于 RESP（AUROC 0.66（95% CI 0.56 至 0.76））和 PRESERVE（AUROC 0.71（95% CI 0.61 至 0.81））。此外，在 XGB 模型的外部验证中，我们实现了 90 天死亡率的 AUROC (0.75)，高于同一验证数据集中的 RESP (0.70) 和 PRESERVE (0.67)。结论 ML 预测模型优于之前的死亡风险模型。该模型可用于在患者选择过程中识别不太可能从 VV-ECMO 治疗中受益的患者。可根据合理要求提供数据。可根据要求提供汇总数据。