Prediction of Acute Kidney Injury for Critically Ill Cardiogenic Shock Patients with Machine Learning Algorithms
Xiaofei Zhang,1,* Yonghong Xiong,2,* Huilan Liu,3 Qian Liu,4 Shubin Chen5 1Department of Gerontology, China Aerospace Science & Industry Corporation 731 hospital, Beijing, People’s Republic of China; 2Department of Cardiology, Beijing Feng Tai Hospital, Beijing, People’s Republic...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2025-01-01
|
| Series: | International Journal of General Medicine |
| Subjects: | |
| Online Access: | https://www.dovepress.com/prediction-of-acute-kidney-injury-for-critically-ill-cardiogenic-shock-peer-reviewed-fulltext-article-IJGM |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555982890565632 |
|---|---|
| author | Zhang X Xiong Y Liu H Liu Q Chen S |
| author_facet | Zhang X Xiong Y Liu H Liu Q Chen S |
| author_sort | Zhang X |
| collection | DOAJ |
| description | Xiaofei Zhang,1,* Yonghong Xiong,2,* Huilan Liu,3 Qian Liu,4 Shubin Chen5 1Department of Gerontology, China Aerospace Science & Industry Corporation 731 hospital, Beijing, People’s Republic of China; 2Department of Cardiology, Beijing Feng Tai Hospital, Beijing, People’s Republic of China; 3Department of Nephrology, Zhongnan Hospital of Wuhan University, Wuhan, People’s Republic of China; 4Department of Cardiology, Wuhan Children’s Hospital, Tongji Medical College, Huazhong University of Science & Technology, Wuhan, People’s Republic of China; 5Department of Intensive Care Unit, China Aerospace Science & Industry Corporation 731 hospital, Beijing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Qian Liu, Department of Cardiology, Wuhan Children’s Hospital, Tongji Medical College, Huazhong University of Science & Technology, No. 100 of Xianggang Road, Jiangan District, Wuhan, 430015, People’s Republic of China, Tel +86027-82433350, Email qian_liu1124@126.com Shubin Chen, Department of Intensive Care Unit, China Aerospace Science & Industry Corporation 731 hospital, No. 3 Zhen Gang Nan Li, Yun Gang Town, Feng Tai District, Beijing, 100074, People’s Republic of China, Tel +86010-68374065, Email 18610074016@163.comBackground: 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).Methods: 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.Results: 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).Conclusion: 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.Keywords: cardiogenic shock, acute kidney injury, MIMIC database, prediction model, machine learning |
| format | Article |
| id | doaj-art-79a055c51aa34d31b32c0620b6ff6034 |
| institution | Kabale University |
| issn | 1178-7074 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Dove Medical Press |
| record_format | Article |
| series | International Journal of General Medicine |
| spelling | doaj-art-79a055c51aa34d31b32c0620b6ff60342025-01-07T16:42:40ZengDove Medical PressInternational Journal of General Medicine1178-70742025-01-01Volume 18334298972Prediction of Acute Kidney Injury for Critically Ill Cardiogenic Shock Patients with Machine Learning AlgorithmsZhang XXiong YLiu HLiu QChen SXiaofei Zhang,1,* Yonghong Xiong,2,* Huilan Liu,3 Qian Liu,4 Shubin Chen5 1Department of Gerontology, China Aerospace Science & Industry Corporation 731 hospital, Beijing, People’s Republic of China; 2Department of Cardiology, Beijing Feng Tai Hospital, Beijing, People’s Republic of China; 3Department of Nephrology, Zhongnan Hospital of Wuhan University, Wuhan, People’s Republic of China; 4Department of Cardiology, Wuhan Children’s Hospital, Tongji Medical College, Huazhong University of Science & Technology, Wuhan, People’s Republic of China; 5Department of Intensive Care Unit, China Aerospace Science & Industry Corporation 731 hospital, Beijing, People’s Republic of China*These authors contributed equally to this workCorrespondence: Qian Liu, Department of Cardiology, Wuhan Children’s Hospital, Tongji Medical College, Huazhong University of Science & Technology, No. 100 of Xianggang Road, Jiangan District, Wuhan, 430015, People’s Republic of China, Tel +86027-82433350, Email qian_liu1124@126.com Shubin Chen, Department of Intensive Care Unit, China Aerospace Science & Industry Corporation 731 hospital, No. 3 Zhen Gang Nan Li, Yun Gang Town, Feng Tai District, Beijing, 100074, People’s Republic of China, Tel +86010-68374065, Email 18610074016@163.comBackground: 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).Methods: 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.Results: 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).Conclusion: 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.Keywords: cardiogenic shock, acute kidney injury, MIMIC database, prediction model, machine learninghttps://www.dovepress.com/prediction-of-acute-kidney-injury-for-critically-ill-cardiogenic-shock-peer-reviewed-fulltext-article-IJGMcardiogenic shockacute kidney injurymimic databaseprediction modelmachine learning |
| spellingShingle | Zhang X Xiong Y Liu H Liu Q Chen S Prediction of Acute Kidney Injury for Critically Ill Cardiogenic Shock Patients with Machine Learning Algorithms International Journal of General Medicine cardiogenic shock acute kidney injury mimic database prediction model machine learning |
| title | Prediction of Acute Kidney Injury for Critically Ill Cardiogenic Shock Patients with Machine Learning Algorithms |
| title_full | Prediction of Acute Kidney Injury for Critically Ill Cardiogenic Shock Patients with Machine Learning Algorithms |
| title_fullStr | Prediction of Acute Kidney Injury for Critically Ill Cardiogenic Shock Patients with Machine Learning Algorithms |
| title_full_unstemmed | Prediction of Acute Kidney Injury for Critically Ill Cardiogenic Shock Patients with Machine Learning Algorithms |
| title_short | Prediction of Acute Kidney Injury for Critically Ill Cardiogenic Shock Patients with Machine Learning Algorithms |
| title_sort | prediction of acute kidney injury for critically ill cardiogenic shock patients with machine learning algorithms |
| topic | cardiogenic shock acute kidney injury mimic database prediction model machine learning |
| url | https://www.dovepress.com/prediction-of-acute-kidney-injury-for-critically-ill-cardiogenic-shock-peer-reviewed-fulltext-article-IJGM |
| work_keys_str_mv | AT zhangx predictionofacutekidneyinjuryforcriticallyillcardiogenicshockpatientswithmachinelearningalgorithms AT xiongy predictionofacutekidneyinjuryforcriticallyillcardiogenicshockpatientswithmachinelearningalgorithms AT liuh predictionofacutekidneyinjuryforcriticallyillcardiogenicshockpatientswithmachinelearningalgorithms AT liuq predictionofacutekidneyinjuryforcriticallyillcardiogenicshockpatientswithmachinelearningalgorithms AT chens predictionofacutekidneyinjuryforcriticallyillcardiogenicshockpatientswithmachinelearningalgorithms |