Working with £93,000 funding from the Engineering and Physical Sciences Research Council (EPSRC) the team at King's College London has taken the first steps towards developing models designed to optimise catheter ablation, a procedure used to correct atrial fibrillation, a condition which causes abnormal heart rhythms.
Atrial fibrillation - which affects the left atrium (or upper chamber) of the heart - reduces blood supply, leading to dizziness, breathlessness and fatigue, and increases the risk of a stroke. Every year, around 10,000 people in the UK have a catheter inserted in order to treat the condition using radiofrequency energy. But the procedure is not always effective, there is a small risk of it causing a stroke or death, and the condition often recurs.
The personalised computer models aim to increase the effectiveness of this procedure by making it possible to explore, in advance, different strategies for its use geared to the specific needs of individual patients.
With 16,000 catheter ablation procedures performed in the UK every year the group estimates that the technology could save the NHS £20m per year.
Developed using skills in computational modelling, software development and image processing, and based on detailed data about the patient's heart obtained through medical imaging, the models depict tissue condition and blood flow, and enable simulation of around 10 cardiac cycles lasting a few seconds in total.
Dr Adelaide de Vecchi of King's College London, who has led the project, said: “These new personalised models show the heart working as a whole 'system'. They allow different catheter ablation strategies to be assessed for each specific patient…and therefore enable the very best option to be pinpointed.”
So far the models have been tested using clinical data from patients at London’s St Thomas' hospital. The next step is to increase the number of cardiac cycles they can depict and apply them to larger cohorts of patients. Once this is achieved, it is anticipated that full clinical trials will be undertaken.
“We believe our models have the potential to enter routine clinical use within a decade, improving treatment of a condition that is especially common among older people,” added Dr de Vecchi.
AI is a gamble we cannot afford without cybersecurity
I am reminded of a quote and example from palaeontology. Herbivorous dinosaurs like stegosaurs/triceratops originally weere bi-pedal with large...