Brain Injury Neuroinformatics

KidsBrainIT

Background

Brain trauma (TBI) is the main cause of death in children older than 1 year of age. Children surviving a life-threatening TBI have new disabilities that affect how they function throughout the rest of their lives which also has an impact on their carers and supporting community. Currently the best option to improve survival and recovery of children with life-threatening TBI is to improve their early intensive-care as none of the experiemental therapies tested in the laboratory are useful in clinical practice.

During treatment of children with life-threatening TBI, often much of the routine bedside monitoring data that is available for clinical interpretation is not fully used. Vital information from this data is discarded rather than being used to help clinicians improve treatments. Multicentre data collection and analysis of such ‘big-data’ in adult TBI have been shown to generate new research ideas and analysis methods.

Using such ‘big-data’ from children’s intensive-care-units (PICU) and working with the adult BrainIT group, we know that new research ideas, and treatment improvement measures are possible which can lead to huge advances in children’s brain trauma treatment.

Funding

2017 - 2021 - ERA-NET NEURON - Paediatric Brain Monitoring with Information Technology (KidsBrainIT): Using Information Technology (IT) Innovations to Improve Childhood Traumatic Brain Injury Intensive Care Management, Outcome, and Patient Safety

Tsz-Yan Milly Lo (Coordinator)

Aims:

  • Better understanding of CPPopt and ICP dose response in childhood brain trauma
  • Establish a paediatric specific anonymised physiological data-bank for research use

Selected Publications

Kempen B, Depreitere B, Piper I, Poca M, Iencean SM, Garcia M, Weitz J, Subramanian G, O'Kane R, Zipfel J, Barzdina A, Pezzato S, Jones PA, Lo TM; KidsBrainIT consortium. KidsBrainIT: Visualization of the Impact of Cerebral Perfusion Pressure Insult Intensity and Duration on Childhood Brain Trauma Outcome. Neurocrit Care. 2026 Feb;44(1):85-94. doi: 10.1007/s12028-025-02296-z. Epub 2025 Jun 3. PMID: 40461767; PMCID: PMC12819434.
 
Haule H, Piper I, Jones P, Lo TM, Escudero J. CLaI: Collaborative Learning and Inference for Low-Resolution Physiological Signals: Validation in Clinical Event Detection and Prediction. IEEE Trans Biomed Eng. 2025 Nov;72(11):3186-3195. doi: 10.1109/TBME.2025.3563732. PMID: 40266872.
 
Haule, H., Piper, I., Jones, P., Qin, C., Lo, T. Y. M., & Escudero, J. (2025). VAE-IF: Deep feature extraction with averaging for fully unsupervised artifact detection in routinely acquired ICU time-series. Computers in Biology and Medicine, 186, 109610.

Lo T, Piper I, Depreitere B, Meyfroidt G, Poca M, Sahuquillo J, Durduran T, Enblad P, Nilsson P, Ragauskas A, Kiening K, Morris K, Agbeko R, Levin R, Weitz J, Park C, Davis P. KidsBrainIT: A New Multi-centre, Multi-disciplinary, Multi-national Paediatric Brain Monitoring Collaboration. Acta Neurochir Suppl. 2018;126:39-45. doi: 10.1007/978-3-319-65798-1_9. PMID: 29492529.
Format: