Cardiovascular disease is becoming an increasingly alarming health concern worldwide, with nearly a third of all deaths being attributed to it. It is particularly prevalent among lower socioeconomic communities, and is largely driven by social and environmental factors such as changes in diet and exercise. Researchers at New York University’s School of Global Public Health and Tandon School of Engineering recently conducted a study to determine how machine learning algorithms can be used to accurately predict and treat cardiovascular disease, and found that models that incorporate social determinants of health are most effective in capturing risk and outcomes for diverse groups.
Machine learning, a type of artificial intelligence used to detect patterns in data, is rapidly becoming a central component of assessing cardiovascular disease risk and prescribing treatment. The researchers identified 48 relevant studies that were published between 1995 and 2020, and found that including social determinants of health in machine learning models improved the ability to predict cardiovascular outcomes such as rehospitalization, heart failure, and stroke.
The study also highlighted the lack of geographic diversity in machine learning research, with the majority of studies having been conducted in the US, Europe, and China. This means that the risk structure of many parts of the world, which are experiencing increases in cardiovascular disease, is not being factored into predictive models.
The researchers point to the growing emphasis on capturing data on social determinants of health, such as employment, education, food, and social support, in electronic health records as an opportunity to use these variables in machine learning studies. This could provide health professionals with actionable information, enabling them to identify patients in need of referral to community resources such as housing services.
It is clear that machine learning for cardiovascular disease can be significantly improved by taking social and environmental factors into consideration. This could help to reduce disparities and provide better treatment for those at risk.
The ainewsarticles.com article you just read is a brief synopsis; the original article can be found here: Read the Full Article…
