Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study
Background. Multiple organ failure (MOF) may lead to an increased mortality rate of moderately severe (MSAP) or severe acute pancreatitis (SAP). This study is aimed to use machine learning to predict the risk of MOF in the course of disease. Methods. Clinical and laboratory features with significant...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Mediators of Inflammation |
| Online Access: | http://dx.doi.org/10.1155/2021/5525118 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832563134054793216 |
|---|---|
| author | Fumin Xu Xiao Chen Chenwenya Li Jing Liu Qiu Qiu Mi He Jingjing Xiao Zhihui Liu Bingjun Ji Dongfeng Chen Kaijun Liu |
| author_facet | Fumin Xu Xiao Chen Chenwenya Li Jing Liu Qiu Qiu Mi He Jingjing Xiao Zhihui Liu Bingjun Ji Dongfeng Chen Kaijun Liu |
| author_sort | Fumin Xu |
| collection | DOAJ |
| description | Background. Multiple organ failure (MOF) may lead to an increased mortality rate of moderately severe (MSAP) or severe acute pancreatitis (SAP). This study is aimed to use machine learning to predict the risk of MOF in the course of disease. Methods. Clinical and laboratory features with significant differences between patients with and without MOF were screened out by univariate analysis. Prediction models were developed for selected features through six machine learning methods. The models were internally validated with a five-fold cross-validation, and a series of optimal feature subsets were generated in corresponding models. A test set was used to evaluate the predictive performance of the six models. Results. 305 (68%) of 455 patients with MSAP or SAP developed MOF. Eighteen features with significant differences between the group with MOF and without it in the training and validation set were used for modeling. Interleukin-6 levels, creatinine levels, and the kinetic time were the three most important features in the optimal feature subsets selected by K-fold cross-validation. The adaptive boosting algorithm (AdaBoost) showed the best predictive performance with the highest AUC value (0.826; 95% confidence interval: 0.740 to 0.888). The sensitivity of AdaBoost (80.49%) and specificity of logistic regression analysis (93.33%) were the best scores among the six models in the test set. Conclusions. A predictive model of MOF complicated by MSAP or SAP was successfully developed based on machine learning. The predictive performance was evaluated by a test set, for which AdaBoost showed a satisfactory predictive performance. The study is registered with the China Clinical Trial Registry (Identifier: ChiCTR1800016079). |
| format | Article |
| id | doaj-art-25d9a873667749adbf11f643bb44a570 |
| institution | Kabale University |
| issn | 0962-9351 1466-1861 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Mediators of Inflammation |
| spelling | doaj-art-25d9a873667749adbf11f643bb44a5702025-02-03T01:20:49ZengWileyMediators of Inflammation0962-93511466-18612021-01-01202110.1155/2021/55251185525118Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort StudyFumin Xu0Xiao Chen1Chenwenya Li2Jing Liu3Qiu Qiu4Mi He5Jingjing Xiao6Zhihui Liu7Bingjun Ji8Dongfeng Chen9Kaijun Liu10Department of Gastroenterology, Daping Hospital, Army Medical University, Chongqing 400042, ChinaDepartment of Nuclear Medicine, Daping Hospital, Army Medical University, Chongqing 400042, ChinaSchool of Basic Medical Sciences, Army Medical University, Chongqing 400038, ChinaCollege of Biomedical Engineering and Imaging Medicine, Army Medical University, Chongqing 400038, ChinaDepartment of Gastroenterology, People’s Hospital of Chongqing Hechuan, Chongqing 401520, ChinaCollege of Biomedical Engineering and Imaging Medicine, Army Medical University, Chongqing 400038, ChinaDepartment of Medical Engineering, Xinqiao Hospital, Army Medical University, Chongqing 400038, ChinaRadiotherapy Center, Sunshine Union Hospital, Weifang, Shandong 261061, ChinaImaging Center, Sunshine Union Hospital, Weifang, 261061 Shandong, ChinaDepartment of Gastroenterology, Daping Hospital, Army Medical University, Chongqing 400042, ChinaDepartment of Gastroenterology, Daping Hospital, Army Medical University, Chongqing 400042, ChinaBackground. Multiple organ failure (MOF) may lead to an increased mortality rate of moderately severe (MSAP) or severe acute pancreatitis (SAP). This study is aimed to use machine learning to predict the risk of MOF in the course of disease. Methods. Clinical and laboratory features with significant differences between patients with and without MOF were screened out by univariate analysis. Prediction models were developed for selected features through six machine learning methods. The models were internally validated with a five-fold cross-validation, and a series of optimal feature subsets were generated in corresponding models. A test set was used to evaluate the predictive performance of the six models. Results. 305 (68%) of 455 patients with MSAP or SAP developed MOF. Eighteen features with significant differences between the group with MOF and without it in the training and validation set were used for modeling. Interleukin-6 levels, creatinine levels, and the kinetic time were the three most important features in the optimal feature subsets selected by K-fold cross-validation. The adaptive boosting algorithm (AdaBoost) showed the best predictive performance with the highest AUC value (0.826; 95% confidence interval: 0.740 to 0.888). The sensitivity of AdaBoost (80.49%) and specificity of logistic regression analysis (93.33%) were the best scores among the six models in the test set. Conclusions. A predictive model of MOF complicated by MSAP or SAP was successfully developed based on machine learning. The predictive performance was evaluated by a test set, for which AdaBoost showed a satisfactory predictive performance. The study is registered with the China Clinical Trial Registry (Identifier: ChiCTR1800016079).http://dx.doi.org/10.1155/2021/5525118 |
| spellingShingle | Fumin Xu Xiao Chen Chenwenya Li Jing Liu Qiu Qiu Mi He Jingjing Xiao Zhihui Liu Bingjun Ji Dongfeng Chen Kaijun Liu Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study Mediators of Inflammation |
| title | Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study |
| title_full | Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study |
| title_fullStr | Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study |
| title_full_unstemmed | Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study |
| title_short | Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study |
| title_sort | prediction of multiple organ failure complicated by moderately severe or severe acute pancreatitis based on machine learning a multicenter cohort study |
| url | http://dx.doi.org/10.1155/2021/5525118 |
| work_keys_str_mv | AT fuminxu predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT xiaochen predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT chenwenyali predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT jingliu predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT qiuqiu predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT mihe predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT jingjingxiao predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT zhihuiliu predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT bingjunji predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT dongfengchen predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy AT kaijunliu predictionofmultipleorganfailurecomplicatedbymoderatelysevereorsevereacutepancreatitisbasedonmachinelearningamulticentercohortstudy |