Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis
Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divide...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/12/11/1930 |
| _version_ | 1797464848695558144 |
|---|---|
| author | Chenyan Yu Yao Li Minyue Yin Jingwen Gao Liting Xi Jiaxi Lin Lu Liu Huixian Zhang Airong Wu Chunfang Xu Xiaolin Liu Yue Wang Jinzhou Zhu |
| author_facet | Chenyan Yu Yao Li Minyue Yin Jingwen Gao Liting Xi Jiaxi Lin Lu Liu Huixian Zhang Airong Wu Chunfang Xu Xiaolin Liu Yue Wang Jinzhou Zhu |
| author_sort | Chenyan Yu |
| collection | DOAJ |
| description | Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H<sub>2</sub>O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). Results: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application. |
| first_indexed | 2024-03-09T18:13:59Z |
| format | Article |
| id | doaj.art-9d4bc37de0aa4d629523783c0b33303f |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-09T18:13:59Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-9d4bc37de0aa4d629523783c0b33303f2023-11-24T08:54:40ZengMDPI AGJournal of Personalized Medicine2075-44262022-11-011211193010.3390/jpm12111930Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic CirrhosisChenyan Yu0Yao Li1Minyue Yin2Jingwen Gao3Liting Xi4Jiaxi Lin5Lu Liu6Huixian Zhang7Airong Wu8Chunfang Xu9Xiaolin Liu10Yue Wang11Jinzhou Zhu12Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Gastroenterology, Dushu Lake Hospital Affiliated to Soochow University, Suzhou 215000, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaDepartment of Hepatology, The Fifth People’s Hospital of Suzhou, Suzhou 215000, ChinaDepartment of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou 215006, ChinaObjective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H<sub>2</sub>O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). Results: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application.https://www.mdpi.com/2075-4426/12/11/1930non-cholestatic cirrhosisautomated machine learningshapley additive explanationpartial dependence plotslocal interpretable model agnostic explanation |
| spellingShingle | Chenyan Yu Yao Li Minyue Yin Jingwen Gao Liting Xi Jiaxi Lin Lu Liu Huixian Zhang Airong Wu Chunfang Xu Xiaolin Liu Yue Wang Jinzhou Zhu Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis Journal of Personalized Medicine non-cholestatic cirrhosis automated machine learning shapley additive explanation partial dependence plots local interpretable model agnostic explanation |
| title | Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis |
| title_full | Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis |
| title_fullStr | Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis |
| title_full_unstemmed | Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis |
| title_short | Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis |
| title_sort | automated machine learning in predicting 30 day mortality in patients with non cholestatic cirrhosis |
| topic | non-cholestatic cirrhosis automated machine learning shapley additive explanation partial dependence plots local interpretable model agnostic explanation |
| url | https://www.mdpi.com/2075-4426/12/11/1930 |
| work_keys_str_mv | AT chenyanyu automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT yaoli automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT minyueyin automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT jingwengao automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT litingxi automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT jiaxilin automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT luliu automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT huixianzhang automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT airongwu automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT chunfangxu automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT xiaolinliu automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT yuewang automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis AT jinzhouzhu automatedmachinelearninginpredicting30daymortalityinpatientswithnoncholestaticcirrhosis |