Predictive Modeling of Long-Term Care Needs in Traumatic Brain Injury Patients Using Machine Learning
Background: Traumatic brain injury (TBI) research often focuses on mortality rates or functional recovery, yet the critical need for long-term care among patients dependent on institutional or Respiratory Care Ward (RCW) support remains underexplored. This study aims to address this gap by employing...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/1/20 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549243017330688 |
|---|---|
| author | Tee-Tau Eric Nyam Kuan-Chi Tu Nai-Ching Chen Che-Chuan Wang Chung-Feng Liu Ching-Lung Kuo Jen-Chieh Liao |
| author_facet | Tee-Tau Eric Nyam Kuan-Chi Tu Nai-Ching Chen Che-Chuan Wang Chung-Feng Liu Ching-Lung Kuo Jen-Chieh Liao |
| author_sort | Tee-Tau Eric Nyam |
| collection | DOAJ |
| description | Background: Traumatic brain injury (TBI) research often focuses on mortality rates or functional recovery, yet the critical need for long-term care among patients dependent on institutional or Respiratory Care Ward (RCW) support remains underexplored. This study aims to address this gap by employing machine learning techniques to develop and validate predictive models that analyze the prognosis of this patient population. Method: Retrospective data from electronic medical records at Chi Mei Medical Center, encompassing 2020 TBI patients admitted to the ICU between January 2016 and December 2021, were collected. A total of 44 features were included, utilizing four machine learning models and various feature combinations based on clinical significance and Spearman correlation coefficients. Predictive performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve and validated with the DeLong test and SHAP (SHapley Additive exPlanations) analysis. Result: Notably, 236 patients (11.68%) were transferred to long-term care centers. XGBoost with 27 features achieved the highest AUC (0.823), followed by Random Forest with 11 features (0.817), and LightGBM with 44 features (0.813). The DeLong test revealed no significant differences among the best predictive models under various feature combinations. SHAP analysis illustrated a similar distribution of feature importance for the top 11 features in XGBoost, with 27 features, and Random Forest with 11 features. Conclusions: Random Forest, with an 11-feature combination, provided clinically meaningful predictive capability, offering early insights into long-term care trends for TBI patients. This model supports proactive planning for institutional or RCW resources, addressing a critical yet often overlooked aspect of TBI care. |
| format | Article |
| id | doaj-art-03844f95bb6742eca879a5952c7a8563 |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-03844f95bb6742eca879a5952c7a85632025-01-10T13:16:28ZengMDPI AGDiagnostics2075-44182024-12-011512010.3390/diagnostics15010020Predictive Modeling of Long-Term Care Needs in Traumatic Brain Injury Patients Using Machine LearningTee-Tau Eric Nyam0Kuan-Chi Tu1Nai-Ching Chen2Che-Chuan Wang3Chung-Feng Liu4Ching-Lung Kuo5Jen-Chieh Liao6Department of Neurosurgery, Chi Mei Medical Center, Tainan 711, TaiwanDepartment of Neurosurgery, Chi Mei Medical Center, Tainan 711, TaiwanDepartment of Nursing, Chi Mei Medical Center, Tainan 711, TaiwanDepartment of Neurosurgery, Chi Mei Medical Center, Tainan 711, TaiwanDepartment of Medical Research, Chi Mei Medical Center, Tainan 711, TaiwanDepartment of Neurosurgery, Chi Mei Medical Center, Tainan 711, TaiwanDepartment of Neurosurgery, ChiaLi Chi Mei Medical Hospital, Tainan 722, TaiwanBackground: Traumatic brain injury (TBI) research often focuses on mortality rates or functional recovery, yet the critical need for long-term care among patients dependent on institutional or Respiratory Care Ward (RCW) support remains underexplored. This study aims to address this gap by employing machine learning techniques to develop and validate predictive models that analyze the prognosis of this patient population. Method: Retrospective data from electronic medical records at Chi Mei Medical Center, encompassing 2020 TBI patients admitted to the ICU between January 2016 and December 2021, were collected. A total of 44 features were included, utilizing four machine learning models and various feature combinations based on clinical significance and Spearman correlation coefficients. Predictive performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve and validated with the DeLong test and SHAP (SHapley Additive exPlanations) analysis. Result: Notably, 236 patients (11.68%) were transferred to long-term care centers. XGBoost with 27 features achieved the highest AUC (0.823), followed by Random Forest with 11 features (0.817), and LightGBM with 44 features (0.813). The DeLong test revealed no significant differences among the best predictive models under various feature combinations. SHAP analysis illustrated a similar distribution of feature importance for the top 11 features in XGBoost, with 27 features, and Random Forest with 11 features. Conclusions: Random Forest, with an 11-feature combination, provided clinically meaningful predictive capability, offering early insights into long-term care trends for TBI patients. This model supports proactive planning for institutional or RCW resources, addressing a critical yet often overlooked aspect of TBI care.https://www.mdpi.com/2075-4418/15/1/20traumatic brain injurylong-term caremachine learning modelspredictive analysisRandom ForestSHAP analysis |
| spellingShingle | Tee-Tau Eric Nyam Kuan-Chi Tu Nai-Ching Chen Che-Chuan Wang Chung-Feng Liu Ching-Lung Kuo Jen-Chieh Liao Predictive Modeling of Long-Term Care Needs in Traumatic Brain Injury Patients Using Machine Learning Diagnostics traumatic brain injury long-term care machine learning models predictive analysis Random Forest SHAP analysis |
| title | Predictive Modeling of Long-Term Care Needs in Traumatic Brain Injury Patients Using Machine Learning |
| title_full | Predictive Modeling of Long-Term Care Needs in Traumatic Brain Injury Patients Using Machine Learning |
| title_fullStr | Predictive Modeling of Long-Term Care Needs in Traumatic Brain Injury Patients Using Machine Learning |
| title_full_unstemmed | Predictive Modeling of Long-Term Care Needs in Traumatic Brain Injury Patients Using Machine Learning |
| title_short | Predictive Modeling of Long-Term Care Needs in Traumatic Brain Injury Patients Using Machine Learning |
| title_sort | predictive modeling of long term care needs in traumatic brain injury patients using machine learning |
| topic | traumatic brain injury long-term care machine learning models predictive analysis Random Forest SHAP analysis |
| url | https://www.mdpi.com/2075-4418/15/1/20 |
| work_keys_str_mv | AT teetauericnyam predictivemodelingoflongtermcareneedsintraumaticbraininjurypatientsusingmachinelearning AT kuanchitu predictivemodelingoflongtermcareneedsintraumaticbraininjurypatientsusingmachinelearning AT naichingchen predictivemodelingoflongtermcareneedsintraumaticbraininjurypatientsusingmachinelearning AT chechuanwang predictivemodelingoflongtermcareneedsintraumaticbraininjurypatientsusingmachinelearning AT chungfengliu predictivemodelingoflongtermcareneedsintraumaticbraininjurypatientsusingmachinelearning AT chinglungkuo predictivemodelingoflongtermcareneedsintraumaticbraininjurypatientsusingmachinelearning AT jenchiehliao predictivemodelingoflongtermcareneedsintraumaticbraininjurypatientsusingmachinelearning |