Cardiovascular disease is the single largest killer in the world, causing heart attacks and strokes. Experimental investigation of underlying principals are key in combating this epidemic, however individual considerations are still completely missing.
The aim of this work is to develop accurate machine learning neural networks to identify links between a large set of demographic, arterial shape and flow data with clinical risk. This will help to identify biomarkers which can be deployed in clinical practice for early risk detection.
Available data will be transformed into a readily available input, suitable set of ML tools will be identified and outcomes will be critically analysed. This will inform and drive personalised cardiovascular consideration in clinical practice.