Using machine learning, AI and computational modelling to predict recovery from stroke from brain-scans across a range of language and cognitive deficits.

This funding model includes a 36 month fully funded PhD Studentship, in-line with the Research Council values, which comprises a tax-free stipend paid monthly (2024/5 - £19,237) per year and a Full Time Fee Scholarship for up to 3 years, subject to you making satisfactory progression within your PhD. 

All applicants will receive the same stipend irrespective of fee status.

Application Closing Date: 
23:59 on Tuesday 30th April 2024 for a start date of the 2nd September 2024.

How to Apply 

To apply, please complete the project proposal form,ensuring that you quote the project reference, and then complete the online application where you will be required to upload your proposal in place of a personal statement as a pdf document. 

You will also be required to upload two references, at least one being an academic reference, and your qualification/s of entry (Bachelor/Masters certificate/s and transcript/s). 

Project Title: Using machine learning, AI and computational modelling to predict recovery from stroke from brain-scans across a range of language and cognitive deficits. 

Project Lead: Professor Eirini Mavritsaki  Eirini.Mavritsaki@bcu.ac.uk

Reference: PreSReB

Project Description

Stroke can be caused when blood flow to the brain is interrupted, this can take place either by blockage or through a traumatic event. Several cognitive deficits can be caused by stroke ranging from paralysis or weakness on one side of the body to problems with memory, attention, vision, thinking, emotional changes and language problems. For the best possible recovery from stroke, the correct rehabilitation is vital. However, predicting the best treatment and outcomes is challenging since every patient is different, and each case of stroke is unique. Machine learning has been previously used, but it is difficult to interpret the outcomes due to complex interactions of the large data used. To overcome these challenges, we are planning to combine machine learning with AI and computational modelling. To achieve the best outcomes, we are collaborating with  University of Birmingham and UCL and we have access to the Predicting Language Outcome and Recovery After Stroke (PLORAS) database with over 2000 stroke patients.

Anticipated Findings and Contribution to Knowledge

This research work aims to contribute towards the development of new approaches for predicting stroke recovery. This will not only advance research in this area, but it will also lead to development of new tools that  clinicians can use to predict outcomes for rehabilitation approaches. 

In addition, this work will make significant contributions towards the advancement of research in computational neuroscience. By combining machine learning, AI and computational modelling, it will help improve our understanding of this complex field. 

Furthermore, the outcomes from this work will provide a basis for external funding applications to MRC or EPSRC, enabling the continuation of research in the area.