Patient-Specific Digital Twins for Optimising Airflow and Voice in Above-Cuff Vocalisation Using LES and Machine Learning

About the Project

This PhD project aims to develop patient‑specific digital twins to improve Above‑Cuff Vocalisation (ACV) for individuals with tracheostomies. ACV enables speech by delivering airflow above the cuff, but current clinical practice relies heavily on trial‑and‑error approaches, which can lead to inconsistent outcomes and potential safety risks. This research seeks to transform ACV into a predictive, data‑driven intervention by modelling the complex airflow and sound‑generation mechanisms within impaired airways.

The project will employ high‑fidelity computational fluid dynamics, using Large Eddy Simulation (LES), to resolve unsteady turbulent airflow and pressure fluctuations in anatomically realistic, patient‑specific airway geometries. Simulation data will be used to generate detailed datasets capturing the relationship between airway geometry, flow conditions, and aeroacoustic output. These datasets will then be used to train supervised machine‑learning models capable of rapidly predicting airflow behaviour and acoustic performance across a range of clinical scenarios. The resulting models will be embedded within a digital‑twin framework to support optimisation of airflow delivery while minimising clinical risk. This interdisciplinary project sits at the interface of engineering, AI, and healthcare, contributing to safer, more effective, and personalised clinical decision‑making.

Entry Requirements

• Qualifications: First‑class or upper second‑class honours degree (or equivalent) in Mechanical, Biomedical, Aerospace Engineering, or a closely related discipline. A relevant Master’s degree is desirable.
• Skills & Experience: Background in fluid mechanics and computational modelling. Familiarity with CFD tools, numerical methods, and programming (Python or MATLAB) is advantageous.
• Additional Knowledge: Interest in interdisciplinary research at the interface of engineering, AI, and healthcare. Prior clinical experience is not required.

Application Details

• A motivational email as to why you wish to apply for the scholarship, stating which project you are applying for.
• Full CV
• Provide copies of transcripts and certificates of all relevant academic and/or any professional qualifications.
• Provide references from two individuals – please contact your referees and ask them to send your reference directly to gs.pgradmissions@hud.ac.uk from their email address. (references can be submitted late but must be received by 17th May 2026)
• Proof of eligibility – e.g. scan of passport photo page
• International applicants must be able to provide an IELTS 6.5 (with no element below 6) *or equivalent English Language certificate or proof of study in the UK within the past 2 years, for their application to be considered for shortlisting.

Please email gs.pgradmissions@hud.ac.uk with queries regarding eligibility and submitting documents. Informal enquiries about individual projects should be directed to the lead supervisor listed for each project.

Funding Notes

3 years full-time research covering tuition fees and a tax-free bursary (stipend) starting at £21,805 for 2026/27.