Researchers may be able to predict cardiovascular disease – such as atrial fibrillation and heart failure – in patients by using artificial intelligence (AI) to examine the genes in their DNA, according to a new Rutgers study.
Researchers from the University of Nottingham have developed an artificial intelligence (AI) system that can predict cardiovascular disease more accurately than current methods.
The team used data from the UK Biobank, a large-scale biomedical database, to train the AI algorithm to identify risk factors for cardiovascular disease. The algorithm analyzed a range of factors, including age, gender, blood pressure, and lifestyle habits such as smoking and exercise.
Dr. Stephen Weng, an assistant professor of epidemiology and data science at the University of Nottingham and the lead author of the study, said in a statement, “We’ve shown that AI can accurately predict cardiovascular disease risk from raw data, significantly better than a human expert. This is particularly valuable in areas where access to expert health professionals is limited, and advanced screening could make a real difference in improving health outcomes.”
The AI system was able to predict cardiovascular disease with a 7.6% improvement in accuracy compared to current methods. The team also found that the AI algorithm was able to identify risk factors that are not currently included in traditional cardiovascular disease risk assessments, such as household income and social deprivation.
Dr. Weng added, “This research demonstrates that AI could revolutionize how we predict people’s risk of heart disease, and shows the advantage of using advanced techniques such as machine learning over traditional methods. This is particularly important in developing countries where cardiovascular disease is on the rise, but access to medical expertise may be limited.”
The study highlights the potential for AI to improve healthcare outcomes and reduce the burden on healthcare systems. The researchers hope that their findings will lead to the development of more accurate and efficient cardiovascular disease risk assessments, particularly in countries where access to expert health professionals is limited.
As Dr. Weng noted, “AI has the potential to revolutionize healthcare, but it requires careful validation and testing before it can be used in clinical practice. Our research provides an important step towards this goal, and we hope to see more studies like ours in the future.”
Via The Impactlab