Development of a ‘Digital-Twin’ model for cerebrospinal fluid dynamics to use in real-time monitoring of patients after severe traumatic brain injury

Summary

This project is related to the pure data driven approach in the first project, except that it takes a different approach.  It focuses on taking advantage of the known physiological relationships within the fluid mechanics of the brain circulations, blood and cerebrospinal fluid.

There are number of mathematical models that have been exercised in the literature that bring together various aspects of this dynamic system, with various degree of success when applied to different physiological and pathophysiological scenarios.  

Project aims

The purpose of this project is to develop a practical model that can be used to track the patho-physiological state of the patients treated in ICU for severe traumatic injury, based on real-time processing of measurements streamed from bed-side monitors, including systemic variables, arterial pressure, ECG, arterial saturation, blood gas CO2 concentration, and intracranial variables, like intracranial pressure, ultrasound based cerebral blood flow velocity, cerebral oxygenation.  

In order to achieve this the student will synthesise the various models already described in the literature into one, parsimonious model, that can have a robust, stable solution, when fed measurements data streams. They will then need to develop practical framework that can be used for solving the simulation and inverse problems with the help of physics informed (PINNs) approaches. 

This approach will take advantage both of the large retrospective database of TBI patients that the Brain Physics lab has acquired over the last two decades (the largest set available anywhere in the world in fact) and the physiological modelling to constrains the data driven tasks to ensure better generalisation of the resulting solutions.

The model will then be encapsulated into a python based plugin to our flagship brain monitoring software ICM+ (https://icmplus.neurosurg.cam.ac.uk) for real time processing evaluation.  The ultimate ambition of the project is to provide a ‘digital twin’ of the brain perfusion mechanism, that we can used to track the progression of the patient pathology and to experiment with different scenarios triggered by interaction between rapidly developing pathology and treatment protocols.

Contact details

Dr Peter Smielewski - ps10011@cam.ac.uk

Opportunities

This project is open to applicants who want to do a:

• PhD
• MPhil

This project would suit graduates in Biomedical Engineering, Physics, Mathematics, Signal Processing, Electrical Engineering, and Computer Science.