Yeh Yu-Chang, Kuo Yu-Ting, Kuo Kuang-Cheng, Cheng Yi-Wei, Liu Ding-Shan, Lai Feipei, Kuo Lu-Cheng, Lee Tai-Ju, Chan Wing-Sum, Chiu Ching-Tang, Tsai Ming-Tao, Chao Anne, Chou Nai-Kuan, Yu Chong-Jen, Ku Shih-Chi
Department of Anesthesiology, National Taiwan University Hospital, No 7, Chung Shan South Road, Taipei, Taiwan.
Taiwan AI Labs, Taipei, Taiwan.
BMC Med Inform Decis Mak. 2024 Dec 18;24(1):394. doi: 10.1186/s12911-024-02807-6.
We aimed to develop and validate models for predicting intensive care unit (ICU) mortality of critically ill adult patients as early as upon ICU admission.
Combined data of 79,657 admissions from two teaching hospitals' ICU databases were used to train and validate the machine learning models to predict ICU mortality upon ICU admission and at 24 h after ICU admission by using logistic regression, gradient boosted trees (GBT), and deep learning algorithms.
In the testing dataset for the admission models, the ICU mortality rate was 7%, and 38.4% of patients were discharged alive or dead within 1 day of ICU admission. The area under the receiver operating characteristic curve (0.856, 95% CI 0.845-0.867) and area under the precision-recall curve (0.331, 95% CI 0.323-0.339) were the highest for the admission GBT model. The ICU mortality rate was 17.4% in the 24-hour testing dataset, and the performance was the highest for the 24-hour GBT model.
The ADM models can provide crucial information on ICU mortality as early as upon ICU admission. 24 H models can be used to improve the prediction of ICU mortality for patients discharged more than 1 day after ICU admission.
我们旨在开发并验证能够尽早预测危重症成年患者入住重症监护病房（ICU）后死亡率的模型，即在患者入住ICU时进行预测。
利用两家教学医院ICU数据库中79,657例入院患者的合并数据，通过逻辑回归、梯度提升树（GBT）和深度学习算法来训练和验证机器学习模型，以预测患者入住ICU时及入住ICU 24小时后的死亡率。
在入院模型的测试数据集中，ICU死亡率为7%，38.4%的患者在入住ICU 1天内出院或死亡。入院GBT模型的受试者工作特征曲线下面积（0.856，95%CI 0.845 - 0.867）和精确召回率曲线下面积（0.331，95%CI 0.323 - 0.339）最高。在24小时测试数据集中，ICU死亡率为17.4%，24小时GBT模型的性能最高。
入院模型能够在患者入住ICU时就提供有关ICU死亡率的关键信息。24小时模型可用于改善对入住ICU 1天以上出院患者的ICU死亡率预测。
