Support Vector Machine Based Monitoring of Cardio-Cerebrovascular Reserve during Simulated Hemorrhage
Introduction: In the initial phase of hypovolemic shock, mean blood pressure (BP) is maintained by sympathetically mediated vasoconstriction rendering BP monitoring insensitive to detect blood loss early. Late detection can result in reduced tissue oxygenation and eventually cellular death. We hypot...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2018-01-01
|
Series: | Frontiers in Physiology |
Subjects: | |
Online Access: | http://journal.frontiersin.org/article/10.3389/fphys.2017.01057/full |
id |
doaj-70f68b3839bb404389ebeaab5fa0f47b |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Björn J. P. van der Ster Björn J. P. van der Ster Björn J. P. van der Ster Frank C. Bennis Frank C. Bennis Tammo Delhaas Tammo Delhaas Berend E. Westerhof Berend E. Westerhof Berend E. Westerhof Wim J. Stok Wim J. Stok Johannes J. van Lieshout Johannes J. van Lieshout Johannes J. van Lieshout Johannes J. van Lieshout |
spellingShingle |
Björn J. P. van der Ster Björn J. P. van der Ster Björn J. P. van der Ster Frank C. Bennis Frank C. Bennis Tammo Delhaas Tammo Delhaas Berend E. Westerhof Berend E. Westerhof Berend E. Westerhof Wim J. Stok Wim J. Stok Johannes J. van Lieshout Johannes J. van Lieshout Johannes J. van Lieshout Johannes J. van Lieshout Support Vector Machine Based Monitoring of Cardio-Cerebrovascular Reserve during Simulated Hemorrhage Frontiers in Physiology cardiovascular modeling cerebrovascular hypovolemia lower body negative pressure machine learning support vector machine |
author_facet |
Björn J. P. van der Ster Björn J. P. van der Ster Björn J. P. van der Ster Frank C. Bennis Frank C. Bennis Tammo Delhaas Tammo Delhaas Berend E. Westerhof Berend E. Westerhof Berend E. Westerhof Wim J. Stok Wim J. Stok Johannes J. van Lieshout Johannes J. van Lieshout Johannes J. van Lieshout Johannes J. van Lieshout |
author_sort |
Björn J. P. van der Ster |
title |
Support Vector Machine Based Monitoring of Cardio-Cerebrovascular Reserve during Simulated Hemorrhage |
title_short |
Support Vector Machine Based Monitoring of Cardio-Cerebrovascular Reserve during Simulated Hemorrhage |
title_full |
Support Vector Machine Based Monitoring of Cardio-Cerebrovascular Reserve during Simulated Hemorrhage |
title_fullStr |
Support Vector Machine Based Monitoring of Cardio-Cerebrovascular Reserve during Simulated Hemorrhage |
title_full_unstemmed |
Support Vector Machine Based Monitoring of Cardio-Cerebrovascular Reserve during Simulated Hemorrhage |
title_sort |
support vector machine based monitoring of cardio-cerebrovascular reserve during simulated hemorrhage |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Physiology |
issn |
1664-042X |
publishDate |
2018-01-01 |
description |
Introduction: In the initial phase of hypovolemic shock, mean blood pressure (BP) is maintained by sympathetically mediated vasoconstriction rendering BP monitoring insensitive to detect blood loss early. Late detection can result in reduced tissue oxygenation and eventually cellular death. We hypothesized that a machine learning algorithm that interprets currently used and new hemodynamic parameters could facilitate in the detection of impending hypovolemic shock.Method: In 42 (27 female) young [mean (sd): 24 (4) years], healthy subjects central blood volume (CBV) was progressively reduced by application of −50 mmHg lower body negative pressure until the onset of pre-syncope. A support vector machine was trained to classify samples into normovolemia (class 0), initial phase of CBV reduction (class 1) or advanced CBV reduction (class 2). Nine models making use of different features were computed to compare sensitivity and specificity of different non-invasive hemodynamic derived signals. Model features included: volumetric hemodynamic parameters (stroke volume and cardiac output), BP curve dynamics, near-infrared spectroscopy determined cortical brain oxygenation, end-tidal carbon dioxide pressure, thoracic bio-impedance, and middle cerebral artery transcranial Doppler (TCD) blood flow velocity. Model performance was tested by quantifying the predictions with three methods: sensitivity and specificity, absolute error, and quantification of the log odds ratio of class 2 vs. class 0 probability estimates.Results: The combination with maximal sensitivity and specificity for classes 1 and 2 was found for the model comprising volumetric features (class 1: 0.73–0.98 and class 2: 0.56–0.96). Overall lowest model error was found for the models comprising TCD curve hemodynamics. Using probability estimates the best combination of sensitivity for class 1 (0.67) and specificity (0.87) was found for the model that contained the TCD cerebral blood flow velocity derived pulse height. The highest combination for class 2 was found for the model with the volumetric features (0.72 and 0.91).Conclusion: The most sensitive models for the detection of advanced CBV reduction comprised data that describe features from volumetric parameters and from cerebral blood flow velocity hemodynamics. In a validated model of hemorrhage in humans these parameters provide the best indication of the progression of central hypovolemia. |
topic |
cardiovascular modeling cerebrovascular hypovolemia lower body negative pressure machine learning support vector machine |
url |
http://journal.frontiersin.org/article/10.3389/fphys.2017.01057/full |
work_keys_str_mv |
AT bjornjpvanderster supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT bjornjpvanderster supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT bjornjpvanderster supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT frankcbennis supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT frankcbennis supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT tammodelhaas supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT tammodelhaas supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT berendewesterhof supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT berendewesterhof supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT berendewesterhof supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT wimjstok supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT wimjstok supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT johannesjvanlieshout supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT johannesjvanlieshout supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT johannesjvanlieshout supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage AT johannesjvanlieshout supportvectormachinebasedmonitoringofcardiocerebrovascularreserveduringsimulatedhemorrhage |
_version_ |
1716796727914135552 |
spelling |
doaj-70f68b3839bb404389ebeaab5fa0f47b2020-11-24T20:53:38ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2018-01-01810.3389/fphys.2017.01057308047Support Vector Machine Based Monitoring of Cardio-Cerebrovascular Reserve during Simulated HemorrhageBjörn J. P. van der Ster0Björn J. P. van der Ster1Björn J. P. van der Ster2Frank C. Bennis3Frank C. Bennis4Tammo Delhaas5Tammo Delhaas6Berend E. Westerhof7Berend E. Westerhof8Berend E. Westerhof9Wim J. Stok10Wim J. Stok11Johannes J. van Lieshout12Johannes J. van Lieshout13Johannes J. van Lieshout14Johannes J. van Lieshout15Department of Internal Medicine, Academic Medical Center, University of Amsterdam, Amsterdam, NetherlandsDepartment of Medical Biology, Academic Medical Center, University of Amsterdam, Amsterdam, NetherlandsLaboratory for Clinical Cardiovascular Physiology, Center for Heart Failure Research, Academic Medical Center, Amsterdam, NetherlandsDepartment of Biomedical Engineering, Maastricht University, Maastricht, NetherlandsMHeNS School for Mental Health and Neuroscience, Maastricht University, Maastricht, NetherlandsDepartment of Biomedical Engineering, Maastricht University, Maastricht, NetherlandsCARIM School for Cardiovascular Diseases, Maastricht University, Maastricht, NetherlandsDepartment of Medical Biology, Academic Medical Center, University of Amsterdam, Amsterdam, NetherlandsLaboratory for Clinical Cardiovascular Physiology, Center for Heart Failure Research, Academic Medical Center, Amsterdam, NetherlandsDepartment of Pulmonary Diseases, Institute for Cardiovascular Research, ICaR-VU, VU University Medical Center, Amsterdam, NetherlandsDepartment of Medical Biology, Academic Medical Center, University of Amsterdam, Amsterdam, NetherlandsLaboratory for Clinical Cardiovascular Physiology, Center for Heart Failure Research, Academic Medical Center, Amsterdam, NetherlandsDepartment of Internal Medicine, Academic Medical Center, University of Amsterdam, Amsterdam, NetherlandsDepartment of Medical Biology, Academic Medical Center, University of Amsterdam, Amsterdam, NetherlandsLaboratory for Clinical Cardiovascular Physiology, Center for Heart Failure Research, Academic Medical Center, Amsterdam, NetherlandsMRC/Arthritis Research UK Centre for Musculoskeletal Ageing Research, School of Life Sciences, The Medical School, University of Nottingham Medical School, Queen's Medical Centre, Nottingham, United KingdomIntroduction: In the initial phase of hypovolemic shock, mean blood pressure (BP) is maintained by sympathetically mediated vasoconstriction rendering BP monitoring insensitive to detect blood loss early. Late detection can result in reduced tissue oxygenation and eventually cellular death. We hypothesized that a machine learning algorithm that interprets currently used and new hemodynamic parameters could facilitate in the detection of impending hypovolemic shock.Method: In 42 (27 female) young [mean (sd): 24 (4) years], healthy subjects central blood volume (CBV) was progressively reduced by application of −50 mmHg lower body negative pressure until the onset of pre-syncope. A support vector machine was trained to classify samples into normovolemia (class 0), initial phase of CBV reduction (class 1) or advanced CBV reduction (class 2). Nine models making use of different features were computed to compare sensitivity and specificity of different non-invasive hemodynamic derived signals. Model features included: volumetric hemodynamic parameters (stroke volume and cardiac output), BP curve dynamics, near-infrared spectroscopy determined cortical brain oxygenation, end-tidal carbon dioxide pressure, thoracic bio-impedance, and middle cerebral artery transcranial Doppler (TCD) blood flow velocity. Model performance was tested by quantifying the predictions with three methods: sensitivity and specificity, absolute error, and quantification of the log odds ratio of class 2 vs. class 0 probability estimates.Results: The combination with maximal sensitivity and specificity for classes 1 and 2 was found for the model comprising volumetric features (class 1: 0.73–0.98 and class 2: 0.56–0.96). Overall lowest model error was found for the models comprising TCD curve hemodynamics. Using probability estimates the best combination of sensitivity for class 1 (0.67) and specificity (0.87) was found for the model that contained the TCD cerebral blood flow velocity derived pulse height. The highest combination for class 2 was found for the model with the volumetric features (0.72 and 0.91).Conclusion: The most sensitive models for the detection of advanced CBV reduction comprised data that describe features from volumetric parameters and from cerebral blood flow velocity hemodynamics. In a validated model of hemorrhage in humans these parameters provide the best indication of the progression of central hypovolemia.http://journal.frontiersin.org/article/10.3389/fphys.2017.01057/fullcardiovascular modelingcerebrovascularhypovolemialower body negative pressuremachine learningsupport vector machine |