Oh Wonsuk, Veshtaj Marinela, Sawant Ashwin, Agrawal Pulkit, Gomez Hernando, Suarez-Farinas Mayte, Oropello John, Kohli-Seth Roopa, Kashani Kianoush, Kellum John A, Nadkarni Girish, Sakhuja Ankit
Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Division of Data-Driven and Digital Medicine, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Crit Care. 2025 May 26;29(1):212. doi: 10.1186/s13054-025-05457-w.
Major Adverse Kidney Events within 30 days (MAKE30) is an important patient-centered outcome for assessing the impact of acute kidney injury (AKI). Existing prediction models for MAKE30 are static and overlook dynamic changes in clinical status. We introduce ORAKLE, a novel deep-learning model that utilizes evolving time-series data to predict MAKE30, enabling personalized, patient-centered approaches to AKI management and outcome improvement.
We conducted a retrospective study using three publicly available critical care databases: MIMIC-IV as the development cohort, and SiCdb and eICU-CRD as external validation cohorts. Patients with sepsis-3 criteria who developed AKI within 48 h of intensive care unit admission were identified. Our primary outcome was MAKE30, defined as a composite of death, new dialysis or persistent kidney dysfunction within 30 days of ICU admission. We developed ORAKLE using Dynamic DeepHit framework for time-series survival analysis and its performance against Cox and XGBoost models. We further assessed model calibration using Brier score.
We analyzed 16,671 patients from MIMIC-IV, 2665 from SICdb, and 11,447 from eICU-CRD. ORAKLE outperformed the XGBoost and Cox models in predicting MAKE30, achieving AUROCs of 0.84 (95% CI: 0.83-0.86) vs. 0.81 (95% CI: 0.79-0.83) vs. 0.80 (95% CI: 0.78-0.82) in MIMIC-IV internal test set, 0.83 (95% CI: 0.81-0.85) vs. 0.80 (95% CI: 0.78-0.83) vs. 0.79 (95% CI: 0.77-0.81) in SICdb, and 0.85 (95% CI: 0.84-0.85) vs. 0.83 (95% CI: 0.83-0.84) vs. 0.81 (95% CI: 0.80-0.82) in eICU-CRD. The AUPRC values for ORAKLE were also significantly better than that of XGBoost and Cox models. The Brier score for ORAKLE was 0.21 across the internal test set, SICdb, and eICU-CRD, suggesting good calibration.
ORAKLE is a robust deep-learning model for predicting MAKE30 in critically ill patients with AKI that utilizes evolving time series data. By incorporating dynamically changing time series features, the model captures the evolving nature of kidney injury, treatment effects, and patient trajectories more accurately. This innovation facilitates tailored risk assessments and identifies varying treatment responses, laying the groundwork for more personalized and effective management approaches.
30天内重大不良肾脏事件（MAKE30）是评估急性肾损伤（AKI）影响的一项重要的以患者为中心的结局指标。现有的MAKE30预测模型是静态的，忽略了临床状态的动态变化。我们引入了ORAKLE，这是一种新型深度学习模型，它利用不断变化的时间序列数据来预测MAKE30，从而实现以患者为中心的个性化AKI管理方法并改善结局。
我们使用三个公开可用的重症监护数据库进行了一项回顾性研究：将MIMIC-IV作为开发队列，将SiCdb和eICU-CRD作为外部验证队列。确定在重症监护病房入院48小时内发生AKI且符合脓毒症-3标准的患者。我们的主要结局是MAKE30，定义为重症监护病房入院30天内死亡、开始新的透析或持续存在肾功能不全的综合情况。我们使用动态DeepHit框架进行时间序列生存分析来开发ORAKLE，并将其与Cox模型和XGBoost模型的性能进行比较。我们还使用Brier评分进一步评估模型校准情况。
我们分析了来自MIMIC-IV的16671例患者、来自SICdb的2665例患者和来自eICU-CRD的11447例患者。在预测MAKE30方面，ORAKLE优于XGBoost模型和Cox模型，在MIMIC-IV内部测试集中的曲线下面积（AUROC）分别为0.84（95%CI：0.83 - 0.86）、0.81（95%CI：0.79 - 0.83）、0.80（95%CI：0.78 - 0.82）；在SICdb中的AUROC分别为0.83（95%CI：0.81 - 0.85）、0.80（95%CI：0.78 - 0.83）、0.79（95%CI：0.77 - 0.81）；在eICU-CRD中的AUROC分别为0.85（95%CI：0.84 - 0.85）、0.83（95%CI：0.83 - 0.84）、0.81（95%CI：0.80 - 0.82）。ORAKLE的曲线下精确率（AUPRC）值也显著优于XGBoost模型和Cox模型。在内部测试集、SICdb和eICU-CRD中，ORAKLE的Brier评分为0.21，表明校准良好。
ORAKLE是一种强大的深度学习模型，用于预测患有AKI的重症患者的MAKE30，它利用不断变化的时间序列数据。通过纳入动态变化的时间序列特征，该模型更准确地捕捉了肾损伤的演变性质、治疗效果和患者轨迹。这一创新有助于进行针对性的风险评估，并识别不同的治疗反应，为更个性化和有效的管理方法奠定基础。
