1
|
Ansari A, Pillay K, Arasteh E, Dereymaeker A, Mellado GS, Jansen K, Winkler AM, Naulaers G, Bhatt A, Huffel SV, Hartley C, Vos MD, Slater R, Baxter L. Resting state electroencephalographic brain activity in neonates can predict age and is indicative of neurodevelopmental outcome. Clin Neurophysiol 2024; 163:226-235. [PMID: 38797002 DOI: 10.1016/j.clinph.2024.05.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2023] [Revised: 05/01/2024] [Accepted: 05/04/2024] [Indexed: 05/29/2024]
Abstract
OBJECTIVE Electroencephalography (EEG) can be used to estimate neonates' biological brain age. Discrepancies between postmenstrual age and brain age, termed the brain age gap, can potentially quantify maturational deviation. Existing brain age EEG models are not well suited to clinical cot-side use for estimating neonates' brain age gap due to their dependency on relatively large data and pre-processing requirements. METHODS We trained a deep learning model on resting state EEG data from preterm neonates with normal neurodevelopmental Bayley Scale of Infant and Toddler Development (BSID) outcomes, using substantially reduced data requirements. We subsequently tested this model in two independent datasets from two clinical sites. RESULTS In both test datasets, using only 20 min of resting-state EEG activity from a single channel, the model generated accurate age predictions: mean absolute error = 1.03 weeks (p-value = 0.0001) and 0.98 weeks (p-value = 0.0001). In one test dataset, where 9-month follow-up BSID outcomes were available, the average neonatal brain age gap in the severe abnormal outcome group was significantly larger than that of the normal outcome group: difference in mean brain age gap = 0.50 weeks (p-value = 0.04). CONCLUSIONS These findings demonstrate that the deep learning model generalises to independent datasets from two clinical sites, and that the model's brain age gap magnitudes differ between neonates with normal and severe abnormal follow-up neurodevelopmental outcomes. SIGNIFICANCE The magnitude of neonates' brain age gap, estimated using only 20 min of resting state EEG data from a single channel, can encode information of clinical neurodevelopmental value.
Collapse
Affiliation(s)
- Amir Ansari
- Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium
| | - Kirubin Pillay
- Department of Paediatrics, University of Oxford, Oxford, UK
| | - Emad Arasteh
- Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium; Department of Neonatology, Wilhelmina Children's Hospital, University Medical Center Utrecht, Utrecht, Netherlands
| | - Anneleen Dereymaeker
- Department of Development and Regeneration, University Hospitals Leuven, Neonatal Intensive Care Unit, KU Leuven, Leuven, Belgium
| | | | - Katrien Jansen
- Department of Development and Regeneration, University Hospitals Leuven, Neonatal Intensive Care Unit, KU Leuven, Leuven, Belgium; Department of Development and Regeneration, University Hospitals Leuven, Child Neurology, KU Leuven, Leuven, Belgium
| | - Anderson M Winkler
- Department of Human Genetics, University of Texas Rio Grande Valley, Brownsville, TX, USA
| | - Gunnar Naulaers
- Department of Development and Regeneration, University Hospitals Leuven, Neonatal Intensive Care Unit, KU Leuven, Leuven, Belgium
| | - Aomesh Bhatt
- Department of Paediatrics, University of Oxford, Oxford, UK
| | - Sabine Van Huffel
- Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium
| | | | - Maarten De Vos
- Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium; Department of Development and Regeneration, University Hospitals Leuven, Child Neurology, KU Leuven, Leuven, Belgium
| | | | - Luke Baxter
- Department of Paediatrics, University of Oxford, Oxford, UK.
| |
Collapse
|
2
|
Nordvik T, Server A, Espeland CN, Schumacher EM, Larsson PG, Pripp AH, Stiris T. Combining MRI and Spectral EEG for Assessment of Neurocognitive Outcomes in Preterm Infants. Neonatology 2023; 120:482-490. [PMID: 37290419 DOI: 10.1159/000530648] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/02/2023] [Accepted: 03/31/2023] [Indexed: 06/10/2023]
Abstract
INTRODUCTION Predicting impairment in preterm children is challenging. Our aim is to explore the association between MRI at term-equivalent age (TEA) and neurocognitive outcomes in late childhood and to assess whether the addition of EEG improves prognostication. METHODS This prospective observational study included forty infants with gestational age 24 + 0-30 + 6. Children were monitored with multichannel EEG for 72 h after birth. Total absolute band power for the delta band on day 2 was calculated. Brain MRI was performed at TEA and scored according to the Kidokoro scoring system. At 10-12 years of age, we evaluated neurocognitive outcomes with Wechsler Intelligence Scale for Children 4th edition, Vineland adaptive behavior scales 2nd edition and Behavior Rating Inventory of Executive Function. We performed linear regression analysis to examine the association between outcomes and MRI and EEG, respectively, and multiple regression analysis to explore the combination of MRI and EEG. RESULTS Forty infants were included. There was a significant association between global brain abnormality score and composite outcomes of WISC and Vineland test, but not the BRIEF test. The adjusted R2 was 0.16 and 0.08, respectively. For EEG, adjusted R2 was 0.34 and 0.15, respectively. When combining MRI and EEG data, adjusted R2 changed to 0.36 for WISC and 0.16 for the Vineland test. CONCLUSION There was a small association between TEA MRI and neurocognitive outcomes in late childhood. Adding EEG to the model improved the explained variance. Combining EEG and MRI data did not have any additional benefit over EEG alone.
Collapse
Affiliation(s)
- Tone Nordvik
- Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Oslo, Norway
- Department of Neonatal Intensive Care, Oslo University Hospital, Ullevål, Oslo, Norway
| | - Andres Server
- Section of Neuroradiology, Department of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway
| | - Cathrine N Espeland
- Department of Neonatal Intensive Care, Oslo University Hospital, Ullevål, Oslo, Norway
| | - Eva M Schumacher
- Department of Neonatal Intensive Care, Oslo University Hospital, Ullevål, Oslo, Norway
| | - Pål G Larsson
- Department of Neurosurgery, Oslo University Hospital, Oslo, Norway
| | - Are H Pripp
- Oslo Center of Biostatistics and Epidemiology, Research Support Services, Oslo University Hospital, Oslo, Norway
| | - Tom Stiris
- Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Oslo, Norway
- Department of Neonatal Intensive Care, Oslo University Hospital, Ullevål, Oslo, Norway
| |
Collapse
|
3
|
Ko TS, Catennacio E, Shin SS, Stern J, Massey SL, Kilbaugh TJ, Hwang M. Advanced Neuromonitoring Modalities on the Horizon: Detection and Management of Acute Brain Injury in Children. Neurocrit Care 2023; 38:791-811. [PMID: 36949362 PMCID: PMC10241718 DOI: 10.1007/s12028-023-01690-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2022] [Accepted: 01/31/2023] [Indexed: 03/24/2023]
Abstract
Timely detection and monitoring of acute brain injury in children is essential to mitigate causes of injury and prevent secondary insults. Increasing survival in critically ill children has emphasized the importance of neuroprotective management strategies for long-term quality of life. In emergent and critical care settings, traditional neuroimaging modalities, such as computed tomography and magnetic resonance imaging (MRI), remain frontline diagnostic techniques to detect acute brain injury. Although detection of structural and anatomical abnormalities remains crucial, advanced MRI sequences assessing functional alterations in cerebral physiology provide unique diagnostic utility. Head ultrasound has emerged as a portable neuroimaging modality for point-of-care diagnosis via assessments of anatomical and perfusion abnormalities. Application of electroencephalography and near-infrared spectroscopy provides the opportunity for real-time detection and goal-directed management of neurological abnormalities at the bedside. In this review, we describe recent technological advancements in these neurodiagnostic modalities and elaborate on their current and potential utility in the detection and management of acute brain injury.
Collapse
Affiliation(s)
- Tiffany S Ko
- Department of Anesthesiology and Critical Care, Children's Hospital of Philadelphia, Philadelphia, USA.
| | - Eva Catennacio
- Division of Neurology, Department of Pediatrics, Children's Hospital of Philadelphia, Philadelphia, USA
| | - Samuel S Shin
- Department of Neurosurgery, Hospital of the University of Pennsylvania, Philadelphia, USA
| | - Joseph Stern
- Department of Radiology, Children's Hospital of Philadelphia, University of Pennsylvania, Philadelphia, USA
| | - Shavonne L Massey
- Division of Neurology, Department of Pediatrics, Children's Hospital of Philadelphia, Philadelphia, USA
| | - Todd J Kilbaugh
- Department of Anesthesiology and Critical Care, Children's Hospital of Philadelphia, Philadelphia, USA
| | - Misun Hwang
- Department of Radiology, Children's Hospital of Philadelphia, University of Pennsylvania, Philadelphia, USA
| |
Collapse
|
4
|
Whittemore BA, Swift DM, M Thomas J, F Chalak L. A neonatal neuroNICU collaborative approach to neuromonitoring of posthemorrhagic ventricular dilation in preterm infants. Pediatr Res 2022; 91:27-34. [PMID: 33627823 DOI: 10.1038/s41390-021-01406-9] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/28/2020] [Revised: 01/25/2021] [Accepted: 01/26/2021] [Indexed: 01/31/2023]
Abstract
Morbidity and mortality in prematurely born infants have significantly improved due to advancement in perinatal care, development of NeuroNICU collaborative multidisciplinary approaches, and evidence-based management protocols that have resulted from a better understanding of perinatal risk factors and neuroprotective treatments. In premature infants with intraventricular hemorrhage (IVH), the detrimental secondary effect of posthemorrhagic ventricular dilation (PHVD) on the neurodevelopmental outcome can be mitigated by surgical intervention, though management varies considerably across institutions. Any benefit derived from the use of neuromonitoring to optimize surgical timing and technique stands to improve neurodevelopmental outcome. In this review, we summarize (1) the approaches to surgical management of PHVD in preterm infants and outcome data; (2) neuromonitoring modalities and the effect of neurosurgical intervention on this data; (3) our resultant protocol for the monitoring and management of PHVD. In particular, our protocol incorporates cerebral near-infrared spectroscopy (NIRS) and transcranial doppler ultrasound (TCD) to better understand cerebral physiology and to enable the hypothesis-driven study of the management of PHVD. IMPACT: Review of the published literature concerning the use of near-infrared spectroscopy (NIRS) and a cerebral Doppler ultrasound to study the effect of cerebrospinal fluid drainage on infants with posthemorrhagic ventricular dilation. Presentation of our institution's evidence-based protocol for the use of NIRS and cerebral Doppler ultrasound to study the optimal neurosurgical treatment of posthemorrhagic ventricular dilation, an as yet inadequately studied area.
Collapse
Affiliation(s)
- Brett A Whittemore
- Department of Neurosurgery, University of Texas Southwestern Medical Center, Dallas, TX, USA.
| | - Dale M Swift
- Department of Neurosurgery, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Jennifer M Thomas
- Department of Neurology, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Lina F Chalak
- Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, TX, USA
| |
Collapse
|
5
|
Stevenson NJ, Oberdorfer L, Tataranno ML, Breakspear M, Colditz PB, de Vries LS, Benders MJNL, Klebermass-Schrehof K, Vanhatalo S, Roberts JA. Automated cot-side tracking of functional brain age in preterm infants. Ann Clin Transl Neurol 2020; 7:891-902. [PMID: 32368863 PMCID: PMC7318094 DOI: 10.1002/acn3.51043] [Citation(s) in RCA: 26] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2020] [Accepted: 03/20/2020] [Indexed: 12/14/2022] Open
Abstract
Objective A major challenge in the care of preterm infants is the early identification of compromised neurological development. While several measures are routinely used to track anatomical growth, there is a striking lack of reliable and objective tools for tracking maturation of early brain function; a cornerstone of lifelong neurological health. We present a cot‐side method for measuring the functional maturity of the newborn brain based on routinely available neurological monitoring with electroencephalography (EEG). Methods We used a dataset of 177 EEG recordings from 65 preterm infants to train a multivariable prediction of functional brain age (FBA) from EEG. The FBA was validated on an independent set of 99 EEG recordings from 42 preterm infants. The difference between FBA and postmenstrual age (PMA) was evaluated as a predictor for neurodevelopmental outcome. Results The FBA correlated strongly with the PMA of an infant, with a median prediction error of less than 1 week. Moreover, individual babies follow well‐defined individual trajectories. The accuracy of the FBA applied to the validation set was statistically equivalent to the training set accuracy. In a subgroup of infants with repeated EEG recordings, a persistently negative predicted age difference was associated with poor neurodevelopmental outcome. Interpretation The FBA enables the tracking of functional neurodevelopment in preterm infants. This establishes proof of principle for growth charts for brain function, a new tool to assist clinical management and identify infants who will benefit most from early intervention.
Collapse
Affiliation(s)
- Nathan J Stevenson
- QIMR Berghofer Medical Research Institute, Brisbane, QLD, 4006, Australia
| | - Lisa Oberdorfer
- Department of Pediatrics, Division of Neonatology, Pediatric Intensive Care and Neuropediatrics, Medical University of Vienna, Vienna, Austria
| | - Maria-Luisa Tataranno
- Department of Neonatology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Michael Breakspear
- QIMR Berghofer Medical Research Institute, Brisbane, QLD, 4006, Australia.,Priority Research Center for Mind and Brain, University of Newcastle, Newcastle, NSW, 2305, Australia
| | - Paul B Colditz
- Centre for Clinical Research, Faculty of Medicine, University of Queensland, Brisbane, QLD, 4029, Australia
| | - Linda S de Vries
- Department of Neonatology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Manon J N L Benders
- Department of Neonatology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Katrin Klebermass-Schrehof
- Department of Pediatrics, Division of Neonatology, Pediatric Intensive Care and Neuropediatrics, Medical University of Vienna, Vienna, Austria
| | - Sampsa Vanhatalo
- Department of Children's Clinical Neurophysiology, BABA Center, Pediatric Research Center, Children's Hospital, HUS Medical Imaging Center, Helsinki University Central Hospital, University of Helsinki, Finland
| | - James A Roberts
- QIMR Berghofer Medical Research Institute, Brisbane, QLD, 4006, Australia
| |
Collapse
|