A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection
Objective Machine learning methods may have better or comparable predictive ability than traditional analysis. We explore machine learning methods to predict the likelihood of acute kidney injury after liver cancer resection. Methods This is a secondary analysis cohort study. We reviewed data from p...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2020-02-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/8583.pdf |
| _version_ | 1797419843882844160 |
|---|---|
| author | Lei Lei Ying Wang Qiong Xue Jianhua Tong Cheng-Mao Zhou Jian-Jun Yang |
| author_facet | Lei Lei Ying Wang Qiong Xue Jianhua Tong Cheng-Mao Zhou Jian-Jun Yang |
| author_sort | Lei Lei |
| collection | DOAJ |
| description | Objective Machine learning methods may have better or comparable predictive ability than traditional analysis. We explore machine learning methods to predict the likelihood of acute kidney injury after liver cancer resection. Methods This is a secondary analysis cohort study. We reviewed data from patients who had undergone resection of primary hepatocellular carcinoma between January 2008 and October 2015. Results The analysis included 1,173 hepatectomy patients, 77 (6.6%) of whom had AKI and 1,096 (93.4%) who did not. The importance matrix for the Gbdt algorithm model shows that age, cholesterol, tumor size, surgery duration and PLT were the five most important parameters. Figure 1 shows that Age, tumor size and surgery duration had weak positive correlations with AKI. Cholesterol and PLT also had weak negative correlations with AKI. The models constructed by the four machine learning algorithms in the training group were compared. Among the four machine learning algorithms, random forest and gbm had the highest accuracy, 0.989 and 0.970 respectively. The precision of four of the five algorithms was 1, random forest being the exception. Among the test group, gbm had the highest accuracy (0.932). Random forest and gbm had the highest precision, both being 0.333. The AUC values for the four algorithms were: Gbdt (0.772), gbm (0.725), forest (0.662) and DecisionTree (0.628). Conclusions Machine learning technology can predict acute kidney injury after hepatectomy. Age, cholesterol, tumor size, surgery duration and PLT influence the likelihood and development of postoperative acute kidney injury. |
| first_indexed | 2024-03-09T06:54:05Z |
| format | Article |
| id | doaj.art-5807fbd1b159469e9c8a27153880b77e |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:54:05Z |
| publishDate | 2020-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-5807fbd1b159469e9c8a27153880b77e2023-12-03T10:14:09ZengPeerJ Inc.PeerJ2167-83592020-02-018e858310.7717/peerj.8583A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resectionLei Lei0Ying Wang1Qiong Xue2Jianhua Tong3Cheng-Mao Zhou4Jian-Jun Yang5Department of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, ChinaDepartment of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, ChinaDepartment of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, ChinaDepartment of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, ChinaDepartment of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, ChinaDepartment of Anesthesiology, Pain and Perioperative Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, ChinaObjective Machine learning methods may have better or comparable predictive ability than traditional analysis. We explore machine learning methods to predict the likelihood of acute kidney injury after liver cancer resection. Methods This is a secondary analysis cohort study. We reviewed data from patients who had undergone resection of primary hepatocellular carcinoma between January 2008 and October 2015. Results The analysis included 1,173 hepatectomy patients, 77 (6.6%) of whom had AKI and 1,096 (93.4%) who did not. The importance matrix for the Gbdt algorithm model shows that age, cholesterol, tumor size, surgery duration and PLT were the five most important parameters. Figure 1 shows that Age, tumor size and surgery duration had weak positive correlations with AKI. Cholesterol and PLT also had weak negative correlations with AKI. The models constructed by the four machine learning algorithms in the training group were compared. Among the four machine learning algorithms, random forest and gbm had the highest accuracy, 0.989 and 0.970 respectively. The precision of four of the five algorithms was 1, random forest being the exception. Among the test group, gbm had the highest accuracy (0.932). Random forest and gbm had the highest precision, both being 0.333. The AUC values for the four algorithms were: Gbdt (0.772), gbm (0.725), forest (0.662) and DecisionTree (0.628). Conclusions Machine learning technology can predict acute kidney injury after hepatectomy. Age, cholesterol, tumor size, surgery duration and PLT influence the likelihood and development of postoperative acute kidney injury.https://peerj.com/articles/8583.pdfMachine learningAKIHepatectomyPostoperativeSecondary analysis |
| spellingShingle | Lei Lei Ying Wang Qiong Xue Jianhua Tong Cheng-Mao Zhou Jian-Jun Yang A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection PeerJ Machine learning AKI Hepatectomy Postoperative Secondary analysis |
| title | A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection |
| title_full | A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection |
| title_fullStr | A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection |
| title_full_unstemmed | A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection |
| title_short | A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection |
| title_sort | comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection |
| topic | Machine learning AKI Hepatectomy Postoperative Secondary analysis |
| url | https://peerj.com/articles/8583.pdf |
| work_keys_str_mv | AT leilei acomparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT yingwang acomparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT qiongxue acomparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT jianhuatong acomparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT chengmaozhou acomparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT jianjunyang acomparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT leilei comparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT yingwang comparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT qiongxue comparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT jianhuatong comparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT chengmaozhou comparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection AT jianjunyang comparativestudyofmachinelearningalgorithmsforpredictingacutekidneyinjuryafterlivercancerresection |