PortalPublikationenEarly prediction of ventricular peritoneal shunt dependency ...

Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data

Standard

Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data. / Schweingruber, Nils; Bremer, Jan; Wiehe, Anton; Mader, Marius Marc-Daniel; Mayer, Christina; Woo, Marcel Seungsu; Kluge, Stefan; Grensemann, Jörn; Quandt, Fanny; Gempt, Jens; Fischer, Marlene; Thomalla, Götz; Gerloff, Christian; Sauvigny, Jennifer; Czorlich, Patrick.

in: J CLIN MONIT COMPUT, 03.2024.

Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung

Harvard

Schweingruber, N, Bremer, J, Wiehe, A, Mader, MM-D, Mayer, C, Woo, MS, Kluge, S, Grensemann, J, Quandt, F, Gempt, J, Fischer, M, Thomalla, G, Gerloff, C, Sauvigny, J & Czorlich, P 2024, 'Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data', J CLIN MONIT COMPUT. https://doi.org/10.1007/s10877-024-01151-4

APA

Schweingruber, N., Bremer, J., Wiehe, A., Mader, M. M-D., Mayer, C., Woo, M. S., Kluge, S., Grensemann, J., Quandt, F., Gempt, J., Fischer, M., Thomalla, G., Gerloff, C., Sauvigny, J., & Czorlich, P. (2024). Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data. J CLIN MONIT COMPUT. https://doi.org/10.1007/s10877-024-01151-4

Vancouver

Schweingruber N, Bremer J, Wiehe A, Mader MM-D, Mayer C, Woo MS et al. Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data. J CLIN MONIT COMPUT. 2024 Mär. https://doi.org/10.1007/s10877-024-01151-4

Bibtex

@article{0d3b6f4225af4965bb76cd30ca6a8f5b,
title = "Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data",
abstract = "Aneurysmal subarachnoid haemorrhage (aSAH) can lead to complications such as acute hydrocephalic congestion. Treatment of this acute condition often includes establishing an external ventricular drainage (EVD). However, chronic hydrocephalus develops in some patients, who then require placement of a permanent ventriculoperitoneal (VP) shunt. The aim of this study was to employ recurrent neural network (RNN)-based machine learning techniques to identify patients who require VP shunt placement at an early stage. This retrospective single-centre study included all patients who were diagnosed with aSAH and treated in the intensive care unit (ICU) between November 2010 and May 2020 (n = 602). More than 120 parameters were analysed, including routine neurocritical care data, vital signs and blood gas analyses. Various machine learning techniques, including RNNs and gradient boosting machines, were evaluated for their ability to predict VP shunt dependency. VP-shunt dependency could be predicted using an RNN after just one day of ICU stay, with an AUC-ROC of 0.77 (CI: 0.75-0.79). The accuracy of the prediction improved after four days of observation (Day 4: AUC-ROC 0.81, CI: 0.79-0.84). At that point, the accuracy of the prediction was 76% (CI: 75.98-83.09%), with a sensitivity of 85% (CI: 83-88%) and a specificity of 74% (CI: 71-78%). RNN-based machine learning has the potential to predict VP shunt dependency on Day 4 after ictus in aSAH patients using routine data collected in the ICU. The use of machine learning may allow early identification of patients with specific therapeutic needs and accelerate the execution of required procedures.",
author = "Nils Schweingruber and Jan Bremer and Anton Wiehe and Mader, {Marius Marc-Daniel} and Christina Mayer and Woo, {Marcel Seungsu} and Stefan Kluge and J{\"o}rn Grensemann and Fanny Quandt and Jens Gempt and Marlene Fischer and G{\"o}tz Thomalla and Christian Gerloff and Jennifer Sauvigny and Patrick Czorlich",
note = "{\textcopyright} 2024. The Author(s).",
year = "2024",
month = mar,
doi = "10.1007/s10877-024-01151-4",
language = "English",
journal = "J CLIN MONIT COMPUT",
issn = "1387-1307",
publisher = "Springer Netherlands",

}

RIS

TY - JOUR

T1 - Early prediction of ventricular peritoneal shunt dependency in aneurysmal subarachnoid haemorrhage patients by recurrent neural network-based machine learning using routine intensive care unit data

AU - Schweingruber, Nils

AU - Bremer, Jan

AU - Wiehe, Anton

AU - Mader, Marius Marc-Daniel

AU - Mayer, Christina

AU - Woo, Marcel Seungsu

AU - Kluge, Stefan

AU - Grensemann, Jörn

AU - Quandt, Fanny

AU - Gempt, Jens

AU - Fischer, Marlene

AU - Thomalla, Götz

AU - Gerloff, Christian

AU - Sauvigny, Jennifer

AU - Czorlich, Patrick

N1 - © 2024. The Author(s).

PY - 2024/3

Y1 - 2024/3

N2 - Aneurysmal subarachnoid haemorrhage (aSAH) can lead to complications such as acute hydrocephalic congestion. Treatment of this acute condition often includes establishing an external ventricular drainage (EVD). However, chronic hydrocephalus develops in some patients, who then require placement of a permanent ventriculoperitoneal (VP) shunt. The aim of this study was to employ recurrent neural network (RNN)-based machine learning techniques to identify patients who require VP shunt placement at an early stage. This retrospective single-centre study included all patients who were diagnosed with aSAH and treated in the intensive care unit (ICU) between November 2010 and May 2020 (n = 602). More than 120 parameters were analysed, including routine neurocritical care data, vital signs and blood gas analyses. Various machine learning techniques, including RNNs and gradient boosting machines, were evaluated for their ability to predict VP shunt dependency. VP-shunt dependency could be predicted using an RNN after just one day of ICU stay, with an AUC-ROC of 0.77 (CI: 0.75-0.79). The accuracy of the prediction improved after four days of observation (Day 4: AUC-ROC 0.81, CI: 0.79-0.84). At that point, the accuracy of the prediction was 76% (CI: 75.98-83.09%), with a sensitivity of 85% (CI: 83-88%) and a specificity of 74% (CI: 71-78%). RNN-based machine learning has the potential to predict VP shunt dependency on Day 4 after ictus in aSAH patients using routine data collected in the ICU. The use of machine learning may allow early identification of patients with specific therapeutic needs and accelerate the execution of required procedures.

AB - Aneurysmal subarachnoid haemorrhage (aSAH) can lead to complications such as acute hydrocephalic congestion. Treatment of this acute condition often includes establishing an external ventricular drainage (EVD). However, chronic hydrocephalus develops in some patients, who then require placement of a permanent ventriculoperitoneal (VP) shunt. The aim of this study was to employ recurrent neural network (RNN)-based machine learning techniques to identify patients who require VP shunt placement at an early stage. This retrospective single-centre study included all patients who were diagnosed with aSAH and treated in the intensive care unit (ICU) between November 2010 and May 2020 (n = 602). More than 120 parameters were analysed, including routine neurocritical care data, vital signs and blood gas analyses. Various machine learning techniques, including RNNs and gradient boosting machines, were evaluated for their ability to predict VP shunt dependency. VP-shunt dependency could be predicted using an RNN after just one day of ICU stay, with an AUC-ROC of 0.77 (CI: 0.75-0.79). The accuracy of the prediction improved after four days of observation (Day 4: AUC-ROC 0.81, CI: 0.79-0.84). At that point, the accuracy of the prediction was 76% (CI: 75.98-83.09%), with a sensitivity of 85% (CI: 83-88%) and a specificity of 74% (CI: 71-78%). RNN-based machine learning has the potential to predict VP shunt dependency on Day 4 after ictus in aSAH patients using routine data collected in the ICU. The use of machine learning may allow early identification of patients with specific therapeutic needs and accelerate the execution of required procedures.

U2 - 10.1007/s10877-024-01151-4

DO - 10.1007/s10877-024-01151-4

M3 - SCORING: Journal article

C2 - 38512361

JO - J CLIN MONIT COMPUT

JF - J CLIN MONIT COMPUT

SN - 1387-1307

ER -