Zhang Xiaofei, Xiong Yonghong, Liu Huilan, Liu Qian, Chen Shubin
Department of Gerontology, China Aerospace Science & Industry Corporation 731 hospital, Beijing, People's Republic of China.
Department of Cardiology, Beijing Feng Tai Hospital, Beijing, People's Republic of China.
Int J Gen Med. 2025 Jan 6;18:33-42. doi: 10.2147/IJGM.S489362. eCollection 2025.
The aim of this study was to use five machine learning approaches and logistic regression to design and validate the acute kidney injury (AKI) prediction model for critically ill individuals with cardiogenic shock (CS).
All patients who diagnosed with CS from the MIMIC-IV database, the eICU database, and Zhongnan hospital of Wuhan university were included in this study. Clinical information, including demographics, comorbidities, vital signs, critical illness scores and laboratory tests was retrospectively collected. Five machine learning algorithms (LightGBM, decision tree, XGBoost, random forest, and ensemble model) and one conventional logistic regression were applied for the prediction of AKI in critically ill individuals with CS. ROC curves were generated via python software to assess the overall performance of machine learning algorithms and the SHAP analysis was adopted to reveal the impact of prediction for each feature.
The ensemble model exhibited the best predictive ability (AUC:0.91, 95% CI, 0.88-0.94), followed by random forest (AUC:0.90, 95% CI, 0.86-0.94) and XGBoost (AUC:0.89, 95% CI, 0.84-0.92). While the logistic regression model obtained the worst predictive performance (AUC:0.62, 95% CI, 0.56-0.68). When validated the prediction models with eICU database, the ensemble model exhibited the best predictive ability (AUC:0.92, 95% CI, 0.89-0.96), while the logistic model obtained the worst predictive performance (AUC:0.61, 95% CI, 0.56-0.67). Finally, we verified the prediction models using the data from our hospital and ensemble model still exhibited the best predictive ability (AUC:0.74, 95% CI, 0.62-0.86), while the decision tree model obtained the worst predictive performance (AUC:0.52, 95% CI 0.35-0.70).
Machine learning algorithms could be utilized for the AKI prediction among critically ill CS patients, and exhibit superior predictive performance compared to the conventional logistic regression analysis.
本研究旨在使用五种机器学习方法和逻辑回归来设计和验证针对心源性休克（CS）危重症患者的急性肾损伤（AKI）预测模型。
本研究纳入了来自MIMIC-IV数据库、eICU数据库以及武汉大学中南医院所有诊断为CS的患者。回顾性收集了包括人口统计学、合并症、生命体征、危重症评分和实验室检查在内的临床信息。应用五种机器学习算法（LightGBM、决策树、XGBoost、随机森林和集成模型）以及一种传统逻辑回归方法来预测CS危重症患者的AKI。通过Python软件生成ROC曲线以评估机器学习算法的整体性能，并采用SHAP分析来揭示每个特征对预测的影响。
集成模型表现出最佳的预测能力（AUC：0.91，95%CI，0.88 - 0.94），其次是随机森林（AUC：0.90，95%CI，0.86 - 0.94）和XGBoost（AUC：0.89，95%CI，0.84 - 0.92）。而逻辑回归模型的预测性能最差（AUC：0.62，95%CI，0.56 - 0.68）。当使用eICU数据库验证预测模型时，集成模型表现出最佳的预测能力（AUC：0.92，95%CI，0.89 - 0.96），而逻辑模型的预测性能最差（AUC：0.61，95%CI，0.56 - 0.67）。最后，我们使用我院的数据验证了预测模型，集成模型仍然表现出最佳的预测能力（AUC：0.74，95%CI，0.62 - 0.86），而决策树模型的预测性能最差（AUC：0.52，95%CI 0.35 - 0.70）。
机器学习算法可用于CS危重症患者的AKI预测，并且与传统逻辑回归分析相比表现出卓越的预测性能。
