Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients
<bold>Structured Abstract—Objective</bold>: Abnormal elevation of intracranial pressure (ICP) can cause dangerous or even fatal outcomes. The early detection of high intracranial pressure events can be crucial in saving lives in an intensive care unit (ICU). Despite many appli...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Translational Engineering in Health and Medicine |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9786851/ |
| _version_ | 1818547011749675008 |
|---|---|
| author | Guochang Ye Vignesh Balasubramanian John K-J. Li Mehmet Kaya |
| author_facet | Guochang Ye Vignesh Balasubramanian John K-J. Li Mehmet Kaya |
| author_sort | Guochang Ye |
| collection | DOAJ |
| description | <bold>Structured Abstract—Objective</bold>: Abnormal elevation of intracranial pressure (ICP) can cause dangerous or even fatal outcomes. The early detection of high intracranial pressure events can be crucial in saving lives in an intensive care unit (ICU). Despite many applications of machine learning (ML) techniques related to clinical diagnosis, ML applications for continuous ICP detection or short-term predictions have been rarely reported. This study proposes an efficient method of applying an artificial recurrent neural network on the early prediction of ICP evaluation continuously for TBI patients. <bold>Methods</bold>: After ICP data preprocessing, the learning model is generated for thirteen patients to continuously predict the ICP signal occurrence and classify events for the upcoming 10 minutes by inputting the previous 20-minutes of the ICP signal. <bold>Results</bold>: As the overall model performance, the average accuracy is 94.62%, the average sensitivity is 74.91%, the average specificity is 94.83%, and the average root mean square error is approximately 2.18 mmHg. <bold>Conclusion</bold>: This research addresses a significant clinical problem with the management of traumatic brain injury patients. The machine learning model data enables early prediction of ICP continuously in a real-time fashion, which is crucial for appropriate clinical interventions. The results show that our machine learning-based model has high adaptive performance, accuracy, and efficiency. |
| first_indexed | 2024-12-12T08:00:54Z |
| format | Article |
| id | doaj.art-28373d62eb6a4b5cbba7dc98d567ef7f |
| institution | Directory Open Access Journal |
| issn | 2168-2372 |
| language | English |
| last_indexed | 2024-12-12T08:00:54Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Translational Engineering in Health and Medicine |
| spelling | doaj.art-28373d62eb6a4b5cbba7dc98d567ef7f2022-12-22T00:32:08ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722022-01-01101810.1109/JTEHM.2022.31798749786851Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury PatientsGuochang Ye0https://orcid.org/0000-0002-1185-7267Vignesh Balasubramanian1https://orcid.org/0000-0002-1601-0268John K-J. Li2Mehmet Kaya3https://orcid.org/0000-0002-0252-9755Department of Biomedical and Chemical Engineering and Sciences, Florida Institute of Technology, Melbourne, FL, USADepartment of Biomedical and Chemical Engineering and Sciences, Florida Institute of Technology, Melbourne, FL, USADepartment of Biomedical Engineering, Rutgers University, New Brunswick, NJ, USADepartment of Biomedical and Chemical Engineering and Sciences, Florida Institute of Technology, Melbourne, FL, USA<bold>Structured Abstract—Objective</bold>: Abnormal elevation of intracranial pressure (ICP) can cause dangerous or even fatal outcomes. The early detection of high intracranial pressure events can be crucial in saving lives in an intensive care unit (ICU). Despite many applications of machine learning (ML) techniques related to clinical diagnosis, ML applications for continuous ICP detection or short-term predictions have been rarely reported. This study proposes an efficient method of applying an artificial recurrent neural network on the early prediction of ICP evaluation continuously for TBI patients. <bold>Methods</bold>: After ICP data preprocessing, the learning model is generated for thirteen patients to continuously predict the ICP signal occurrence and classify events for the upcoming 10 minutes by inputting the previous 20-minutes of the ICP signal. <bold>Results</bold>: As the overall model performance, the average accuracy is 94.62%, the average sensitivity is 74.91%, the average specificity is 94.83%, and the average root mean square error is approximately 2.18 mmHg. <bold>Conclusion</bold>: This research addresses a significant clinical problem with the management of traumatic brain injury patients. The machine learning model data enables early prediction of ICP continuously in a real-time fashion, which is crucial for appropriate clinical interventions. The results show that our machine learning-based model has high adaptive performance, accuracy, and efficiency.https://ieeexplore.ieee.org/document/9786851/Computer-assisted decision makingintracranial pressureintracranial hypertensionmachine learningtraumatic brain injury |
| spellingShingle | Guochang Ye Vignesh Balasubramanian John K-J. Li Mehmet Kaya Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients IEEE Journal of Translational Engineering in Health and Medicine Computer-assisted decision making intracranial pressure intracranial hypertension machine learning traumatic brain injury |
| title | Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients |
| title_full | Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients |
| title_fullStr | Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients |
| title_full_unstemmed | Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients |
| title_short | Machine Learning-Based Continuous Intracranial Pressure Prediction for Traumatic Injury Patients |
| title_sort | machine learning based continuous intracranial pressure prediction for traumatic injury patients |
| topic | Computer-assisted decision making intracranial pressure intracranial hypertension machine learning traumatic brain injury |
| url | https://ieeexplore.ieee.org/document/9786851/ |
| work_keys_str_mv | AT guochangye machinelearningbasedcontinuousintracranialpressurepredictionfortraumaticinjurypatients AT vigneshbalasubramanian machinelearningbasedcontinuousintracranialpressurepredictionfortraumaticinjurypatients AT johnkjli machinelearningbasedcontinuousintracranialpressurepredictionfortraumaticinjurypatients AT mehmetkaya machinelearningbasedcontinuousintracranialpressurepredictionfortraumaticinjurypatients |