Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Dec 16;166(1):504.
doi: 10.1007/s00701-024-06375-6.

Exploration of simultaneous transients between cerebral hemodynamics and the autonomic nervous system using windowed time-lagged cross-correlation matrices: a CENTER-TBI study

Agnieszka Uryga  1 , Cyprian Mataczyński  2 , Adam I Pelah  3 , Małgorzata Burzyńska  4 , Chiara Robba  5   6 , Marek Czosnyka  3 ; CENTER-TBI high-resolution sub-study participants and investigators
Collaborators, Affiliations

Exploration of simultaneous transients between cerebral hemodynamics and the autonomic nervous system using windowed time-lagged cross-correlation matrices: a CENTER-TBI study

Agnieszka Uryga et al. Acta Neurochir (Wien). .

Abstract

Background: Traumatic brain injury (TBI) can significantly disrupt autonomic nervous system (ANS) regulation, increasing the risk for secondary complications, hemodynamic instability, and adverse outcome. This retrospective study evaluated windowed time-lagged cross-correlation (WTLCC) matrices for describing cerebral hemodynamics-ANS interactions to predict outcome, enabling identifying high-risk patients who may benefit from enhanced monitoring to prevent complications.

Methods: The first experiment aimed to predict short-term outcome using WTLCC-based convolution neural network models on the Wroclaw University Hospital (WUH) database (Ptraining = 31 with 1,079 matrices, Pval = 16 with 573 matrices). The second experiment predicted long-term outcome, training on the CENTER-TBI database (Ptraining = 100 with 17,062 matrices) and validating on WUH (Pval = 47 with 6,220 matrices). Cerebral hemodynamics was characterized using intracranial pressure (ICP), cerebral perfusion pressure (CPP), pressure reactivity index (PRx), while ANS metrics included low-to-high-frequency heart rate variability (LF/HF) and baroreflex sensitivity (BRS) over 72 h. Short-term outcome at WUH was assessed using the Glasgow Outcome Scale (GOS) at discharge. Long-term outcome was evaluated at 3 months at WUH and 6 months at CENTER-TBI using GOS and GOS-Extended, respectively. The XGBoost model was used to compare performance of WTLCC-based model and averaged neuromonitoring parameters, adjusted for age, Glasgow Coma Scale, major extracranial injury, and pupil reactivity in outcome prediction.

Results: For short-term outcome prediction, the best-performing WTLCC-based model used ICP-LF/HF matrices. It had an area under the curve (AUC) of 0.80, vs. 0.71 for averages of ANS and cerebral hemodynamics metrics, adjusted for clinical metadata. For long-term outcome prediction, the best-score WTLCC-based model used ICP-LF/HF matrices. It had an AUC of 0.63, vs. 0.66 for adjusted neuromonitoring parameters.

Conclusions: Among all neuromonitoring parameters, ICP and LF/HF signals were the most effective in generating the WTLCC matrices. WTLCC-based model outperformed adjusted neuromonitoring parameters in short-term but had moderate utility in long-term outcome prediction.

Keywords: Autonomic nervous system; Brain–heart coupling; Machine learning; Traumatic brain injury.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: The CENTER-TBI study (European Commission Grant 602150) was conducted in accordance with all relevant laws of the European Union that are directly applicable or of direct effects and all relevant laws of the country where the recruiting sites were located, including but not limited to, the relevant privacy and data protection laws and regulations (the “Privacy Law”), the relevant laws and regulations on the use of human materials, and all relevant guidance relating to clinical studies from time to time in force, including but not limited to, the ICH Harmonized Tripartite Guideline for Good Clinical Practice (CPMP/ICH/135/95) (“ICH GCP”) and the World Medical Association Declaration of Helsinki entitled “Ethical Principles for Medical Research Involving Human Subjects.” Informed consent by the patients and/or the legal representative/next of kin was obtained, according to the local legislations, for all patients recruited in the Core Dataset of CENTER-TBI and documented in the e-CRF. Ethical approval was obtained for each recruiting site from the appropriate local ethics committee, and the full list of approvals is available on the website: https://www.center-tbi.eu/project/ethical-approval . The retrospective analysis of data recorded at Wroclaw University Hospital (WUH) was approved by the bioethical committee of WUH (approval KB-133/2023). All volunteers were required to provide written consent before entering the study. The data were fully anonymised, and no data protection issues were involved. Consent for publication: The manuscript has not been submitted elsewhere or published elsewhere in whole or in part. Some of the results have been accepted as poster presentations for the 2024 meeting of the International NeuroTrauma Society (INTS) conference, which took place in September 2024 in Cambridge, UK. Figure 1 was created in BioRender.com. Competing interests: Prof. Robba received fees for lectures from Massimo and GE. Prof. Czosnyka has a financial interest in a part of the intensive care monitoring (ICM +) licensing fee.

Figures

Fig. 1
Fig. 1
Study design. The aim of the first experiment (‘WTLCC utility’) was to investigate to the utility of windowed time-lag cross-correlation (WTLCC) matrices, which describe cerebral hemodynamics-autonomic nervous system (ANS) interactions for predicting short-term outcome. For cerebral hemodynamics parameters, intracranial pressure (ICP), cerebral perfusion pressure (CPP), pressure reactivity index (PRx) were used, and baroreflex sensitivity (BRS) and low-to-high component ratio of heart rate variability (LF/HF) were used as ANS metrics. This experiment was performed exclusively on the Wroclaw University Hospital (WUH) database. The second experiment (‘WTLCC generalizability’) aimed to evaluate the utility of WTLCC matrices for predicting long-term outcome in a larger, external database of TBI patients. For this purpose, the CENTER-TBI database was used for training, and the WUH database was used for validation
Fig. 2
Fig. 2
An examplary time series of cerebral hemodynamics parameters: intracranial pressure (ICP), cerebral perfusion pressure (CPP), and pressure reactivity index (PRx), as well as autonomic nervous system parameters: baroreflex sensitivity (BRS) and the ratio between the low (LF, 0.04–0.15 Hz) and high (HF, 0.15–0.40 Hz) frequency ranges of heart rate variability (LF/HF) during the first three days (72 h) of recordings in traumatic brain injury patient hospitalized at Wroclaw University Hospital (WUH)
Fig. 3
Fig. 3
The pipeline of the analysis uses windowed time-lagged cross-correlation (WTLCC) (Upper panel) WTLCC is applied to two series I1(n) and I2(n) of length N, creating a matrix with K rows and J columns. (Lower panel) A custom convolutional neural network (CNN) was used as a general approximator for the task of finding a mapping from the WTLCC matrices to a binary variable of unfavourable/favourable outcome. The details of WTLCC and CNN are presented in the Supplementary materials
Fig. 4
Fig. 4
A receiver operating characteristic (ROC) curve and confusion matrix for the convolutional neural network (CNN) model utilizing windowed time-lagged cross-correlation (WTLCC) in two experiments. The first experiment (‘WTLCC utility’) aimed to predict short-term outcome and was trained and validated on the Wroclaw University Hospital (WUH) database (Ptraining = 31 with 1,079 matrices, Pval = 16 with 573 matrices). The second experiment (‘WTLCC generalizability’) aimed to predict long-term outcome and was trained on the CENTER-TBI database and validated on WUH (Ptraining = 100 with 17,062 matrices, Pval = 47 with 6,220 matrices). Abbreviations: Fav. – Favourable outcome; Unfav.– Unfavourable outcome
See this image and copyright information in PMC

References

    1. Ackland GL, Iqbal S, Paredes LG, Toner A, Lyness C, Jenkins N et al (2015) Individualised oxygen delivery targeted haemodynamic therapy in high-risk surgical patients: a multicentre, randomised, double-blind, controlled, mechanistic trial. Lancet Respir Med 3:33–41 - PubMed
    1. Åkerlund CAI, Holst A, Bhattacharyay S, Stocchetti N, Steyerberg E, Smielewski P et al (2024) Clinical descriptors of disease trajectories in patients with traumatic brain injury in the intensive care unit (CENTER-TBI): a multicentre observational cohort study. Lancet Neurol 23:71–80 - PubMed
    1. Alali AS, Vavrek D, Barber J, Dikmen S, Nathens AB, Temkin NR (2015) Comparative study of outcome measures and analysis methods for traumatic brain injury trials. J Neurotrauma 32:581 - PMC - PubMed
    1. Barnaby D, Ferrick K, Kaplan DT, Shah S, Bijur P, Gallagher EJ (2002) Heart rate variability in emergency department patients with sepsis. Acad Emerg Med 9:661–670 - PubMed
    1. Behrens F, Moulder RG, Boker SM, Kret ME (2020) Quantifying physiological synchrony through windowed cross-correlation analysis: Statistical and theoretical considerations. bioRxiv, pp 1–53. 10.1101/2020.08.27.269746