Automated machine learning for early prediction of acute kidney injury in acute pancreatitis
Abstract Background Acute kidney injury (AKI) represents a frequent and grave complication associated with acute pancreatitis (AP), substantially elevating both mortality rates and the financial burden of hospitalization. The aim of our study is to construct a predictive model utilizing automated ma...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-01-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-024-02414-5 |
| _version_ | 1827382113239826432 |
|---|---|
| author | Rufa Zhang Minyue Yin Anqi Jiang Shihou Zhang Xiaodan Xu Luojie Liu |
| author_facet | Rufa Zhang Minyue Yin Anqi Jiang Shihou Zhang Xiaodan Xu Luojie Liu |
| author_sort | Rufa Zhang |
| collection | DOAJ |
| description | Abstract Background Acute kidney injury (AKI) represents a frequent and grave complication associated with acute pancreatitis (AP), substantially elevating both mortality rates and the financial burden of hospitalization. The aim of our study is to construct a predictive model utilizing automated machine learning (AutoML) algorithms for the early prediction of AKI in patients with AP. Methods We retrospectively analyzed patients who were diagnosed with AP in our hospital from January 2017 to December 2021. These patients were randomly allocated into a training set and a validation set at a ratio of 7:3. To develop predictive models for each set, we employed the least absolute shrinkage and selection operator (LASSO) algorithm along with AutoML. A nomogram was developed based on multivariate logistic regression analysis outcomes. The model’s efficacy was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Additionally, the performance of the model constructed via AutoML was evaluated using decision curve analysis (DCA), feature importance, SHapley Additive exPlanations (SHAP) plots, and locally interpretable model-agnostic explanations (LIME). Results This study incorporated a total of 437 patients who met the inclusion criteria. Out of these, 313 were assigned to the training cohort and 124 to the validation cohort. In the training and validation cohorts, AKI occurred in 68 (21.7%) and 29(23.4%) patients, respectively. Comparative analysis revealed that the AutoML models exhibited enhanced performance over traditional logistic regression (LR). Furthermore, the deep learning (DL) model demonstrated superior predictive accuracy, evidenced by an area under the ROC curve of 0.963 in the training set and 0.830 in the validation set, surpassing other comparative models. The key variables identified as significant in the DL model within the training dataset included creatinine (Cr), urea (Urea), international normalized ratio (INR), etiology, smoking, alanine aminotransferase (ALT), hypertension, prothrombin time (PT), lactate dehydrogenase (LDH), and diabetes. Conclusion The AutoML model, utilizing DL algorithm, offers considerable clinical significance in the early detection of AKI among patients with AP. |
| first_indexed | 2024-03-08T14:14:51Z |
| format | Article |
| id | doaj.art-2026009444af432e83aa2fc92abd022c |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-03-08T14:14:51Z |
| publishDate | 2024-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-2026009444af432e83aa2fc92abd022c2024-01-14T12:25:41ZengBMCBMC Medical Informatics and Decision Making1472-69472024-01-0124111410.1186/s12911-024-02414-5Automated machine learning for early prediction of acute kidney injury in acute pancreatitisRufa Zhang0Minyue Yin1Anqi Jiang2Shihou Zhang3Xiaodan Xu4Luojie Liu5Department of Gastroenterology, Changshu Hospital Affiliated to Soochow University, Changshu NO.1 People’s HospitalDepartment of Gastroenterology, The First Affiliated Hospital of Soochow UniversityDepartment of Gastroenterology, Changshu Hospital Affiliated to Soochow University, Changshu NO.1 People’s HospitalDepartment of Gastroenterology, Changshu Hospital Affiliated to Soochow University, Changshu NO.1 People’s HospitalDepartment of Gastroenterology, Changshu Hospital Affiliated to Soochow University, Changshu NO.1 People’s HospitalDepartment of Gastroenterology, Changshu Hospital Affiliated to Soochow University, Changshu NO.1 People’s HospitalAbstract Background Acute kidney injury (AKI) represents a frequent and grave complication associated with acute pancreatitis (AP), substantially elevating both mortality rates and the financial burden of hospitalization. The aim of our study is to construct a predictive model utilizing automated machine learning (AutoML) algorithms for the early prediction of AKI in patients with AP. Methods We retrospectively analyzed patients who were diagnosed with AP in our hospital from January 2017 to December 2021. These patients were randomly allocated into a training set and a validation set at a ratio of 7:3. To develop predictive models for each set, we employed the least absolute shrinkage and selection operator (LASSO) algorithm along with AutoML. A nomogram was developed based on multivariate logistic regression analysis outcomes. The model’s efficacy was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Additionally, the performance of the model constructed via AutoML was evaluated using decision curve analysis (DCA), feature importance, SHapley Additive exPlanations (SHAP) plots, and locally interpretable model-agnostic explanations (LIME). Results This study incorporated a total of 437 patients who met the inclusion criteria. Out of these, 313 were assigned to the training cohort and 124 to the validation cohort. In the training and validation cohorts, AKI occurred in 68 (21.7%) and 29(23.4%) patients, respectively. Comparative analysis revealed that the AutoML models exhibited enhanced performance over traditional logistic regression (LR). Furthermore, the deep learning (DL) model demonstrated superior predictive accuracy, evidenced by an area under the ROC curve of 0.963 in the training set and 0.830 in the validation set, surpassing other comparative models. The key variables identified as significant in the DL model within the training dataset included creatinine (Cr), urea (Urea), international normalized ratio (INR), etiology, smoking, alanine aminotransferase (ALT), hypertension, prothrombin time (PT), lactate dehydrogenase (LDH), and diabetes. Conclusion The AutoML model, utilizing DL algorithm, offers considerable clinical significance in the early detection of AKI among patients with AP.https://doi.org/10.1186/s12911-024-02414-5Automated machine learningAcute kidney injuryAcute pancreatitisCreatinineInternational normalized ratioPredictive models |
| spellingShingle | Rufa Zhang Minyue Yin Anqi Jiang Shihou Zhang Xiaodan Xu Luojie Liu Automated machine learning for early prediction of acute kidney injury in acute pancreatitis BMC Medical Informatics and Decision Making Automated machine learning Acute kidney injury Acute pancreatitis Creatinine International normalized ratio Predictive models |
| title | Automated machine learning for early prediction of acute kidney injury in acute pancreatitis |
| title_full | Automated machine learning for early prediction of acute kidney injury in acute pancreatitis |
| title_fullStr | Automated machine learning for early prediction of acute kidney injury in acute pancreatitis |
| title_full_unstemmed | Automated machine learning for early prediction of acute kidney injury in acute pancreatitis |
| title_short | Automated machine learning for early prediction of acute kidney injury in acute pancreatitis |
| title_sort | automated machine learning for early prediction of acute kidney injury in acute pancreatitis |
| topic | Automated machine learning Acute kidney injury Acute pancreatitis Creatinine International normalized ratio Predictive models |
| url | https://doi.org/10.1186/s12911-024-02414-5 |
| work_keys_str_mv | AT rufazhang automatedmachinelearningforearlypredictionofacutekidneyinjuryinacutepancreatitis AT minyueyin automatedmachinelearningforearlypredictionofacutekidneyinjuryinacutepancreatitis AT anqijiang automatedmachinelearningforearlypredictionofacutekidneyinjuryinacutepancreatitis AT shihouzhang automatedmachinelearningforearlypredictionofacutekidneyinjuryinacutepancreatitis AT xiaodanxu automatedmachinelearningforearlypredictionofacutekidneyinjuryinacutepancreatitis AT luojieliu automatedmachinelearningforearlypredictionofacutekidneyinjuryinacutepancreatitis |