Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients
Background. Acute kidney injury (AKI) has long been recognized as a common and important complication of acute pancreatitis (AP). In the study, machine learning (ML) techniques were used to establish predictive models for AKI in AP patients during hospitalization. This is a retrospective review of p...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Gastroenterology Research and Practice |
| Online Access: | http://dx.doi.org/10.1155/2020/3431290 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832563451345502208 |
|---|---|
| author | Cheng Qu Lin Gao Xian-qiang Yu Mei Wei Guo-quan Fang Jianing He Long-xiang Cao Lu Ke Zhi-hui Tong Wei-qin Li |
| author_facet | Cheng Qu Lin Gao Xian-qiang Yu Mei Wei Guo-quan Fang Jianing He Long-xiang Cao Lu Ke Zhi-hui Tong Wei-qin Li |
| author_sort | Cheng Qu |
| collection | DOAJ |
| description | Background. Acute kidney injury (AKI) has long been recognized as a common and important complication of acute pancreatitis (AP). In the study, machine learning (ML) techniques were used to establish predictive models for AKI in AP patients during hospitalization. This is a retrospective review of prospectively collected data of AP patients admitted within one week after the onset of abdominal pain to our department from January 2014 to January 2019. Eighty patients developed AKI after admission (AKI group) and 254 patients did not (non-AKI group) in the hospital. With the provision of additional information such as demographic characteristics or laboratory data, support vector machine (SVM), random forest (RF), classification and regression tree (CART), and extreme gradient boosting (XGBoost) were used to build models of AKI prediction and compared to the predictive performance of the classic model using logistic regression (LR). XGBoost performed best in predicting AKI with an AUC of 91.93% among the machine learning models. The AUC of logistic regression analysis was 87.28%. Present findings suggest that compared to the classical logistic regression model, machine learning models using features that can be easily obtained at admission had a better performance in predicting AKI in the AP patients. |
| format | Article |
| id | doaj-art-bac693fe9571415fa857a2d769b79ad9 |
| institution | Kabale University |
| issn | 1687-6121 1687-630X |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Gastroenterology Research and Practice |
| spelling | doaj-art-bac693fe9571415fa857a2d769b79ad92025-02-03T01:20:09ZengWileyGastroenterology Research and Practice1687-61211687-630X2020-01-01202010.1155/2020/34312903431290Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis PatientsCheng Qu0Lin Gao1Xian-qiang Yu2Mei Wei3Guo-quan Fang4Jianing He5Long-xiang Cao6Lu Ke7Zhi-hui Tong8Wei-qin Li9Surgical Intensive Care Unit (SICU), Department of General Surgery, Jinling Hospital, Medical School of Nanjing University, Nanjing, ChinaSurgical Intensive Care Unit (SICU), Department of General Surgery, Jinling Hospital, Medical School of Nanjing University, Nanjing, ChinaSurgical Intensive Care Unit (SICU), Department of General Surgery, Jinling Clinical Medical College of Southeast University, Nanjing, ChinaSurgical Intensive Care Unit (SICU), Department of General Surgery, Jinling Hospital, Medical School of Nanjing University, Nanjing, ChinaElectrical Engineering School of Southeast University, ChinaInstitute for Hospital Management of Tsinghua University, Shenzhen, ChinaSurgical Intensive Care Unit (SICU), Department of General Surgery, Jinling Hospital, Medical School of Nanjing University, Nanjing, ChinaSurgical Intensive Care Unit (SICU), Department of General Surgery, Jinling Hospital, Medical School of Nanjing University, Nanjing, ChinaSurgical Intensive Care Unit (SICU), Department of General Surgery, Jinling Hospital, Medical School of Nanjing University, Nanjing, ChinaSurgical Intensive Care Unit (SICU), Department of General Surgery, Jinling Hospital, Medical School of Nanjing University, Nanjing, ChinaBackground. Acute kidney injury (AKI) has long been recognized as a common and important complication of acute pancreatitis (AP). In the study, machine learning (ML) techniques were used to establish predictive models for AKI in AP patients during hospitalization. This is a retrospective review of prospectively collected data of AP patients admitted within one week after the onset of abdominal pain to our department from January 2014 to January 2019. Eighty patients developed AKI after admission (AKI group) and 254 patients did not (non-AKI group) in the hospital. With the provision of additional information such as demographic characteristics or laboratory data, support vector machine (SVM), random forest (RF), classification and regression tree (CART), and extreme gradient boosting (XGBoost) were used to build models of AKI prediction and compared to the predictive performance of the classic model using logistic regression (LR). XGBoost performed best in predicting AKI with an AUC of 91.93% among the machine learning models. The AUC of logistic regression analysis was 87.28%. Present findings suggest that compared to the classical logistic regression model, machine learning models using features that can be easily obtained at admission had a better performance in predicting AKI in the AP patients.http://dx.doi.org/10.1155/2020/3431290 |
| spellingShingle | Cheng Qu Lin Gao Xian-qiang Yu Mei Wei Guo-quan Fang Jianing He Long-xiang Cao Lu Ke Zhi-hui Tong Wei-qin Li Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients Gastroenterology Research and Practice |
| title | Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients |
| title_full | Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients |
| title_fullStr | Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients |
| title_full_unstemmed | Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients |
| title_short | Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients |
| title_sort | machine learning models of acute kidney injury prediction in acute pancreatitis patients |
| url | http://dx.doi.org/10.1155/2020/3431290 |
| work_keys_str_mv | AT chengqu machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients AT lingao machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients AT xianqiangyu machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients AT meiwei machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients AT guoquanfang machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients AT jianinghe machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients AT longxiangcao machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients AT luke machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients AT zhihuitong machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients AT weiqinli machinelearningmodelsofacutekidneyinjurypredictioninacutepancreatitispatients |