Karasneh Reema, Al-Azzam Sayer, Alzoubi Karem H, Araydah Mohammad, Rahhal Dania, Al-Azzam Yamin, Kharaba Zelal, Kabbaha Suad, Aldeyab Mamoon A
Department of Basic Medical Sciences, Faculty of Medicine, Yarmouk University, Irbid, Jordan.
Department of Clinical Pharmacy, Faculty of Pharmacy, Jordan University of Science and Technology, Irbid, Jordan.
Rev Recent Clin Trials. 2025 Jun 18. doi: 10.2174/0115748871348585250604065542.
Accurate mortality prediction in intensive care units (ICUs) is essential for enhancing patient outcomes and optimizing healthcare resource allocation. Traditional scoring systems, such as APACHE, APACHE II, and SAPS, have limitations in handling complex, high- -dimensional ICU data. In this study, multiple machine learning models were compared to establish an efficacious predictive model for mortality tailored explicitly to the Jordanian population and to explicate factors strongly associated with mortality.
This study was conducted as a single-center, retrospective cohort investigation, and the XGBoost machine learning algorithm was used to develop a novel ICU mortality prediction model. The model aimed to achieve superior prediction accuracy using a diverse set of readily available clinical data, including demographics, comorbidities, laboratory results, and medication groups. Model performance was evaluated against alternative machine learning algorithms, including logistic regression, conventionally employed in traditional scoring systems.
Comparative analysis revealed that the XGBoost model performed better than other scoring systems, manifesting heightened accuracy (87.91%), sensitivity (92.88%), and Area Under the Receiver-Operating Characteristic Curve (AUC-ROC) Score/Curve (94.29%). Notably, the patient's length of hospital stays, albumin levels, and urea levels emerged as the most substantial predictors for ICU mortality, each exhibiting respective SHAP values of 0.5, 0.41, and 0.37.
A locally adapted ICU mortality prediction model was developed, underscoring the pivotal role of predictors such as hospital stay duration, albumin, and urea levels in predicting patient outcomes. The heightened accuracy and sensitivity of the XGBoost model signify its potential as an invaluable tool in the critical task of mortality prediction within the Jordanian ICU context.
重症监护病房（ICU）中准确的死亡率预测对于改善患者预后和优化医疗资源分配至关重要。传统的评分系统，如急性生理与慢性健康状况评分系统（APACHE）、APACHE II和简化急性生理学评分（SAPS），在处理复杂的高维ICU数据方面存在局限性。在本研究中，对多个机器学习模型进行了比较，以建立一个专门针对约旦人群的有效死亡率预测模型，并阐明与死亡率密切相关的因素。
本研究作为单中心回顾性队列研究进行，使用XGBoost机器学习算法开发了一种新型ICU死亡率预测模型。该模型旨在利用包括人口统计学、合并症、实验室检查结果和药物组在内的各种现成临床数据实现更高的预测准确性。针对传统评分系统中常用的替代机器学习算法（包括逻辑回归）评估模型性能。
对比分析表明，XGBoost模型的表现优于其他评分系统，具有更高的准确性（87.91%）、敏感性（92.88%）和受试者工作特征曲线下面积（AUC-ROC）评分/曲线（94.29%）。值得注意的是，患者的住院时间、白蛋白水平和尿素水平成为ICU死亡率的最重要预测因素，各自的SHAP值分别为0.5、0.41和0.37。
开发了一个适用于当地的ICU死亡率预测模型，强调了住院时间、白蛋白和尿素水平等预测因素在预测患者预后方面的关键作用。XGBoost模型更高的准确性和敏感性表明其在约旦ICU环境下死亡率预测这一关键任务中作为宝贵工具的潜力。
