Machine learning in the prediction of cardiac surgery associated acute kidney injury with early postoperative biomarkers
PurposeTo establish novel prediction models for predicting acute kidney injury (AKI) after cardiac surgery based on early postoperative biomarkers.Patients and methodsThis study enrolled patients who underwent cardiac surgery in a Chinese tertiary cardiac center and consisted of a discovery cohort (...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-02-01
|
| Series: | Frontiers in Surgery |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fsurg.2023.1048431/full |
| _version_ | 1811170398474076160 |
|---|---|
| author | Rui Fan Rui Fan Wei Qin Hao Zhang Lichun Guan Wuwei Wang Jian Li Wen Chen Fuhua Huang Hang Zhang Xin Chen Xin Chen |
| author_facet | Rui Fan Rui Fan Wei Qin Hao Zhang Lichun Guan Wuwei Wang Jian Li Wen Chen Fuhua Huang Hang Zhang Xin Chen Xin Chen |
| author_sort | Rui Fan |
| collection | DOAJ |
| description | PurposeTo establish novel prediction models for predicting acute kidney injury (AKI) after cardiac surgery based on early postoperative biomarkers.Patients and methodsThis study enrolled patients who underwent cardiac surgery in a Chinese tertiary cardiac center and consisted of a discovery cohort (n = 452, from November 2018 to June 2019) and a validation cohort (n = 326, from December 2019 to May 2020). 43 biomarkers were screened using the least absolute shrinkage and selection operator and logistic regression to construct a nomogram model. Three tree-based machine learning models were also established: eXtreme Gradient Boosting (XGBoost), random forest (RF) and deep forest (DF). Model performance was accessed using area under the receiver operating characteristic curve (AUC). AKI was defined according to the Kidney Disease Improving Global Outcomes criteria.ResultsFive biomarkers were identified as independent predictors of AKI and were included in the nomogram: soluble ST2 (sST2), N terminal pro-brain natriuretic peptide (NT-proBNP), heart-type fatty acid binding protein (H-FABP), lactic dehydrogenase (LDH), and uric acid (UA). In the validation cohort, the nomogram achieved good discrimination, with AUC of 0.834. The machine learning models also exhibited adequate discrimination, with AUC of 0.856, 0.850, and 0.836 for DF, RF, and XGBoost, respectively. Both nomogram and machine learning models had well calibrated. The AUC of sST2, NT-proBNP, H-FABP, LDH, and UA to discriminate AKI were 0.670, 0.713, 0.725, 0.704, and 0.749, respectively. In addition, all of these biomarkers were significantly correlated with AKI after adjusting clinical confounders (odds ratio and 95% confidence interval of the third vs. the first tertile: sST2, 3.55 [2.34–5.49], NT-proBNP, 5.50 [3.54–8.71], H-FABP, 6.64 [4.11–11.06], LDH, 7.47 [4.54–12.64], and UA, 8.93 [5.46–15.06]).ConclusionOur study provides a series of novel predictive models and five biomarkers for enhancing the risk stratification of AKI after cardiac surgery. |
| first_indexed | 2024-04-10T16:56:06Z |
| format | Article |
| id | doaj.art-2798e2d58b8d49b0b8a14c5cbe9e7d81 |
| institution | Directory Open Access Journal |
| issn | 2296-875X |
| language | English |
| last_indexed | 2024-04-10T16:56:06Z |
| publishDate | 2023-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Surgery |
| spelling | doaj.art-2798e2d58b8d49b0b8a14c5cbe9e7d812023-02-07T06:24:41ZengFrontiers Media S.A.Frontiers in Surgery2296-875X2023-02-011010.3389/fsurg.2023.10484311048431Machine learning in the prediction of cardiac surgery associated acute kidney injury with early postoperative biomarkersRui Fan0Rui Fan1Wei Qin2Hao Zhang3Lichun Guan4Wuwei Wang5Jian Li6Wen Chen7Fuhua Huang8Hang Zhang9Xin Chen10Xin Chen11School of Medicine, Southeast University, Nanjing, ChinaDepartment of Thoracic and Cardiovascular Surgery, Nanjing First Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Thoracic and Cardiovascular Surgery, Nanjing First Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Nephrology, Nanjing First Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Thoracic Surgery, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Thoracic and Cardiovascular Surgery, Nanjing First Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Thoracic and Cardiovascular Surgery, Nanjing First Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Thoracic and Cardiovascular Surgery, Nanjing First Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Thoracic and Cardiovascular Surgery, Nanjing First Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Thoracic Surgery, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaSchool of Medicine, Southeast University, Nanjing, ChinaDepartment of Thoracic and Cardiovascular Surgery, Nanjing First Hospital, Nanjing Medical University, Nanjing, ChinaPurposeTo establish novel prediction models for predicting acute kidney injury (AKI) after cardiac surgery based on early postoperative biomarkers.Patients and methodsThis study enrolled patients who underwent cardiac surgery in a Chinese tertiary cardiac center and consisted of a discovery cohort (n = 452, from November 2018 to June 2019) and a validation cohort (n = 326, from December 2019 to May 2020). 43 biomarkers were screened using the least absolute shrinkage and selection operator and logistic regression to construct a nomogram model. Three tree-based machine learning models were also established: eXtreme Gradient Boosting (XGBoost), random forest (RF) and deep forest (DF). Model performance was accessed using area under the receiver operating characteristic curve (AUC). AKI was defined according to the Kidney Disease Improving Global Outcomes criteria.ResultsFive biomarkers were identified as independent predictors of AKI and were included in the nomogram: soluble ST2 (sST2), N terminal pro-brain natriuretic peptide (NT-proBNP), heart-type fatty acid binding protein (H-FABP), lactic dehydrogenase (LDH), and uric acid (UA). In the validation cohort, the nomogram achieved good discrimination, with AUC of 0.834. The machine learning models also exhibited adequate discrimination, with AUC of 0.856, 0.850, and 0.836 for DF, RF, and XGBoost, respectively. Both nomogram and machine learning models had well calibrated. The AUC of sST2, NT-proBNP, H-FABP, LDH, and UA to discriminate AKI were 0.670, 0.713, 0.725, 0.704, and 0.749, respectively. In addition, all of these biomarkers were significantly correlated with AKI after adjusting clinical confounders (odds ratio and 95% confidence interval of the third vs. the first tertile: sST2, 3.55 [2.34–5.49], NT-proBNP, 5.50 [3.54–8.71], H-FABP, 6.64 [4.11–11.06], LDH, 7.47 [4.54–12.64], and UA, 8.93 [5.46–15.06]).ConclusionOur study provides a series of novel predictive models and five biomarkers for enhancing the risk stratification of AKI after cardiac surgery.https://www.frontiersin.org/articles/10.3389/fsurg.2023.1048431/fullacute kidney injurycardiac surgerybiomarkernomogrammachine learningrandom forest |
| spellingShingle | Rui Fan Rui Fan Wei Qin Hao Zhang Lichun Guan Wuwei Wang Jian Li Wen Chen Fuhua Huang Hang Zhang Xin Chen Xin Chen Machine learning in the prediction of cardiac surgery associated acute kidney injury with early postoperative biomarkers Frontiers in Surgery acute kidney injury cardiac surgery biomarker nomogram machine learning random forest |
| title | Machine learning in the prediction of cardiac surgery associated acute kidney injury with early postoperative biomarkers |
| title_full | Machine learning in the prediction of cardiac surgery associated acute kidney injury with early postoperative biomarkers |
| title_fullStr | Machine learning in the prediction of cardiac surgery associated acute kidney injury with early postoperative biomarkers |
| title_full_unstemmed | Machine learning in the prediction of cardiac surgery associated acute kidney injury with early postoperative biomarkers |
| title_short | Machine learning in the prediction of cardiac surgery associated acute kidney injury with early postoperative biomarkers |
| title_sort | machine learning in the prediction of cardiac surgery associated acute kidney injury with early postoperative biomarkers |
| topic | acute kidney injury cardiac surgery biomarker nomogram machine learning random forest |
| url | https://www.frontiersin.org/articles/10.3389/fsurg.2023.1048431/full |
| work_keys_str_mv | AT ruifan machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT ruifan machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT weiqin machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT haozhang machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT lichunguan machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT wuweiwang machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT jianli machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT wenchen machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT fuhuahuang machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT hangzhang machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT xinchen machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers AT xinchen machinelearninginthepredictionofcardiacsurgeryassociatedacutekidneyinjurywithearlypostoperativebiomarkers |