Machine learning for personalised prescribing after a heart attack
The BHF-Turing Cardiovascular Data Science Awards (First Call): Machine learning in myocardial infarction to improve risk prediction and inform treatment decisions (joint funding with The Alan Turing Institute)
Nicholas Mills (lead researcher)
Edinburgh, University of
Start date: (Duration 1 year)
Heart attacks occur when a blood clot blocks a coronary artery. After a heart attack, people are prescribed drugs to reduce the risk of another. This includes medicines to prevent blood clots, often described as 'thinning' the blood. Unfortunately, this does increase a person’s risk of uncontrolled bleeding, with potentially life-threatening consequences. The balance of harms and benefits of blood thinning drugs differs between different people, but we don’t currently have a good way of measuring this to enable doctors to make personalised decisions about a person’s care after a heart attack.
This Turing Award goes to researchers at the University of Edinburgh, in collaboration with a team at the Alan Turing Institute. They will use clinical information from over 50,000 heart attack patients in Scotland, combined with advanced computational techniques, to develop and test a personalised risk predictor.
The aim is to create a tool to support doctors when prescribing blood thinning drugs to people following a heart attack. It may be able to identify those for whom a short course of treatment is advisable, and those for whom the benefits of prolonged treatment truly outweigh the risks of bleeding. This decision-making tool could become a key aid to help doctors prescribe drugs safely for individuals who have had a heart attack.
< back to search results