Gao Wenpeng, Wang Junsong, Zhou Lang, Luo Qingquan, Lao Yonghua, Lyu Haijin, Guo Shengwen
Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou, Guangdong, 510640, PR China.
Department of Electric Power Engineering, School of Electric Power Engineering, South China University of Technology, Guangzhou, Guangdong, 510640, PR China.
Comput Biol Med. 2022 Jan;140:105097. doi: 10.1016/j.compbiomed.2021.105097. Epub 2021 Nov 30.
To predict acute kidney injury (AKI) in a large intensive care unit (ICU) database.
A total of 30,020 ICU admissions with 17,222 AKI episodes were extracted from the Medical Information Mart from Intensive Care (MIMIC)-III database. These were randomly divided into a training set and an independent testing set in a ratio of 4:1. Data pertaining to demographics, admission information, vital signs, laboratory tests, critical illness scores, medications, comorbidities, and intervention measures were collected. Logistic regression, random forest, LightGBM, XGBoost, and an ensemble model was used for early prediction of AKI occurrence and important feature extraction. The SHAP analysis was adopted to reveal the impact of prediction for each feature.
The ensemble model had the best overall performance for predicting AKI before 24 h, 48 h and 72 h. The F values were 0.915, 0.893, and 0.878, respectively. AUCs were 0.923, 0.903, and 0.895, respectively.
Based on readily available electronic medical record (EMR) data, gradient boosting decision tree models are highly accurate at early AKI prediction in critically ill patients.
在一个大型重症监护病房（ICU）数据库中预测急性肾损伤（AKI）。
从重症监护医学信息集市（MIMIC）-III数据库中提取了30020例ICU入院病例，其中有17222例AKI发作。这些病例以4:1的比例随机分为训练集和独立测试集。收集了有关人口统计学、入院信息、生命体征、实验室检查、危重病评分、药物治疗、合并症和干预措施的数据。使用逻辑回归、随机森林、LightGBM、XGBoost和一个集成模型对AKI的发生进行早期预测并提取重要特征。采用SHAP分析来揭示每个特征对预测的影响。
集成模型在预测24小时、48小时和72小时前的AKI方面具有最佳的整体性能。F值分别为0.915、0.893和0.878。AUC分别为0.923、0.903和0.895。
基于现成的电子病历（EMR）数据，梯度提升决策树模型在危重病患者早期AKI预测方面具有高度准确性。
