Scientists at the University of Cambridge are developing a machine learning tool to better predict individuals’ long-term risk of developing cardiovascular disease (CVD)—specifically, heart attack or stroke.
The researchers, funded by the British Heart Foundation (BHF) and the Alan Turing Institute, seek to develop, train and test an AI-based tool that “provides accurate estimates for individual patients.”
The tool will help predict peoples’ risk of cardiovascular disease based on their health records and could transform the way primary care providers in the U.K., identify, treat and advise at-risk patients, according to a prepared statement issued by BHF.
At present, primary care providers in the U.K. utilize risk calculators as part of a National Health Service (NHS) Health Check to determine a patient’s 10-year risk for developing heart disease. However, the risk calculators do not assess a patient’s comprehensive medical history. Risk factors—including cholesterol levels and blood pressure readings—may have changed overtime, and the AI tool accounts for those changes.
“Such a tool could support doctors when prescribing drugs to ‘thin’ the blood following a heart attack; to identify patients where a short course of treatment is required to avoid unwanted severe side-effects, or those for whom prolonged treatment is truly in their best interests,” read the project page on the Alan Turing Institute website.
To develop the algorithms, the researchers will use the long-term health records of more than 2 million people in the U.K. The algorithm will produce the “most accurate” personalized risk score and will classify the risk for each type of heart and circulatory disease.
“More people than ever are living with the devastating aftermath of a heart attack or stroke,” said Metin Avkiran, PhD, professor at King’s College London and associate medical director at BHF. “Investing in data science and machine learning innovation is critical if we want to reduce the burden of early deaths and unnecessarily suffering from heart and circulatory disease.”
“Data science is set to accelerate breakthroughs in medical research and the outcome of projects such as this could ultimately transform care for millions of people living under the shadow of heart and circulatory disease in the UK,” Avkiran said.