Predicting Hemodynamic Failure Development in PICU Using Machine Learning Techniques
The present work aims to identify the predictors of hemodynamic failure (HF) developed during pediatric intensive care unit (PICU) stay testing a set of machine learning techniques (MLTs), comparing their ability to predict the outcome of interest. The study involved patients admitted to PICUs betwe...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/7/1299 |
| _version_ | 1827687668569341952 |
|---|---|
| author | Rosanna I. Comoretto Danila Azzolina Angela Amigoni Giorgia Stoppa Federica Todino Andrea Wolfler Dario Gregori on behalf of the TIPNet Study Group |
| author_facet | Rosanna I. Comoretto Danila Azzolina Angela Amigoni Giorgia Stoppa Federica Todino Andrea Wolfler Dario Gregori on behalf of the TIPNet Study Group |
| author_sort | Rosanna I. Comoretto |
| collection | DOAJ |
| description | The present work aims to identify the predictors of hemodynamic failure (HF) developed during pediatric intensive care unit (PICU) stay testing a set of machine learning techniques (MLTs), comparing their ability to predict the outcome of interest. The study involved patients admitted to PICUs between 2010 and 2020. Data were extracted from the Italian Network of Pediatric Intensive Care Units (TIPNet) registry. The algorithms considered were generalized linear model (GLM), recursive partition tree (RPART), random forest (RF), neural networks models, and extreme gradient boosting (XGB). Since the outcome is rare, upsampling and downsampling algorithms have been applied for imbalance control. For each approach, the main performance measures were reported. Among an overall sample of 29,494 subjects, only 399 developed HF during the PICU stay. The median age was about two years, and the male gender was the most prevalent. The XGB algorithm outperformed other MLTs in predicting HF development, with a median ROC measure of 0.780 (IQR 0.770–0.793). PIM 3, age, and base excess were found to be the strongest predictors of outcome. The present work provides insights for the prediction of HF development during PICU stay using machine-learning algorithms. |
| first_indexed | 2024-03-10T09:42:14Z |
| format | Article |
| id | doaj.art-943cb8fedd7d4482b4b8ea04d27dde30 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T09:42:14Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-943cb8fedd7d4482b4b8ea04d27dde302023-11-22T03:35:53ZengMDPI AGDiagnostics2075-44182021-07-01117129910.3390/diagnostics11071299Predicting Hemodynamic Failure Development in PICU Using Machine Learning TechniquesRosanna I. Comoretto0Danila Azzolina1Angela Amigoni2Giorgia Stoppa3Federica Todino4Andrea Wolfler5Dario Gregori6on behalf of the TIPNet Study GroupUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyPediatric Intensive Care Unit, Department of Women’s and Children’s Health, University Hospital of Padua, Via Giustiniani 2, 35128 Padova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyDepartment of Anaesthesia, Gaslini Hospital, 16147 Genova, ItalyUnit of Biostatistics, Epidemiology and Public Health, Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padova, 35131 Padova, ItalyThe present work aims to identify the predictors of hemodynamic failure (HF) developed during pediatric intensive care unit (PICU) stay testing a set of machine learning techniques (MLTs), comparing their ability to predict the outcome of interest. The study involved patients admitted to PICUs between 2010 and 2020. Data were extracted from the Italian Network of Pediatric Intensive Care Units (TIPNet) registry. The algorithms considered were generalized linear model (GLM), recursive partition tree (RPART), random forest (RF), neural networks models, and extreme gradient boosting (XGB). Since the outcome is rare, upsampling and downsampling algorithms have been applied for imbalance control. For each approach, the main performance measures were reported. Among an overall sample of 29,494 subjects, only 399 developed HF during the PICU stay. The median age was about two years, and the male gender was the most prevalent. The XGB algorithm outperformed other MLTs in predicting HF development, with a median ROC measure of 0.780 (IQR 0.770–0.793). PIM 3, age, and base excess were found to be the strongest predictors of outcome. The present work provides insights for the prediction of HF development during PICU stay using machine-learning algorithms.https://www.mdpi.com/2075-4418/11/7/1299machine learning techniqueshemodynamic failurePICUimbalance managementoutcome prediction |
| spellingShingle | Rosanna I. Comoretto Danila Azzolina Angela Amigoni Giorgia Stoppa Federica Todino Andrea Wolfler Dario Gregori on behalf of the TIPNet Study Group Predicting Hemodynamic Failure Development in PICU Using Machine Learning Techniques Diagnostics machine learning techniques hemodynamic failure PICU imbalance management outcome prediction |
| title | Predicting Hemodynamic Failure Development in PICU Using Machine Learning Techniques |
| title_full | Predicting Hemodynamic Failure Development in PICU Using Machine Learning Techniques |
| title_fullStr | Predicting Hemodynamic Failure Development in PICU Using Machine Learning Techniques |
| title_full_unstemmed | Predicting Hemodynamic Failure Development in PICU Using Machine Learning Techniques |
| title_short | Predicting Hemodynamic Failure Development in PICU Using Machine Learning Techniques |
| title_sort | predicting hemodynamic failure development in picu using machine learning techniques |
| topic | machine learning techniques hemodynamic failure PICU imbalance management outcome prediction |
| url | https://www.mdpi.com/2075-4418/11/7/1299 |
| work_keys_str_mv | AT rosannaicomoretto predictinghemodynamicfailuredevelopmentinpicuusingmachinelearningtechniques AT danilaazzolina predictinghemodynamicfailuredevelopmentinpicuusingmachinelearningtechniques AT angelaamigoni predictinghemodynamicfailuredevelopmentinpicuusingmachinelearningtechniques AT giorgiastoppa predictinghemodynamicfailuredevelopmentinpicuusingmachinelearningtechniques AT federicatodino predictinghemodynamicfailuredevelopmentinpicuusingmachinelearningtechniques AT andreawolfler predictinghemodynamicfailuredevelopmentinpicuusingmachinelearningtechniques AT dariogregori predictinghemodynamicfailuredevelopmentinpicuusingmachinelearningtechniques AT onbehalfofthetipnetstudygroup predictinghemodynamicfailuredevelopmentinpicuusingmachinelearningtechniques |