Personalised Disease Modelling using Topological Data Analysis and Pseudo Time
The National Health Service states that the ‘one size fits all’ approach to the care and treatment of patients is ineffective as everyone responds to diseases differently. The need for personalised medicine arises so that we can better manage patients’ health based on an individual patient’s medical background including their genomic data. This project aims to use state-of-the-art Artificial Intelligence techniques in order to learn the “shape” of disease as it progresses. This will enable models to be built that capture realistic progression for an individual patient, facilitating better management of disease and more appropriate interventions.
The figure below shows how a network can represent stages in diabetes and an overall shape with starting points and endpoints (inferred from real patient data)