According to research from the University of Colorado School of Medicine at Aurora (USA), coffee intake has been associated with a lower risk of heart failure and stroke. The results of the study were presented at the 2017 American Heart Association (AHA) Scientific Sessions held in Anaheim, California.
Experts used machine learning in conjunction with traditional data analysis techniques to discover an inverse relationship between how much coffee we drink per week and how we are exposed to the risk of heart failure and stroke with data from the Framingham Heart Study, In operation since 1948, providing crucial information on cardiovascular health.
Machine learning can make predictions based on associations of data, and it’s been increasingly used in health-related research in recent years. This is so, in part, because it allows researchers to perform data mining – the process of identifying patterns based on large amounts of data – much more efficiently.
Following analysis of machine learning data, the researchers found that an extra cup of coffee each week was associated with a 7% lower risk of heart failure and an 8% lower risk of stroke.
In addition, the scientists performed traditional data analyzes (Cox proportional hazards) on information obtained from two other large population studies: the Cardiovascular Health Study and the Community Atherosclerosis Risk Study. They found exactly the same association between coffee consumption and lower risk of heart failure and stroke, confirming the initial results of machine learning.
Although the findings were consistent, the authors comment that the association is not necessarily causal, so we should not come to any firm conclusions at this time.
More partnerships
The researchers also found a correlation between the amount of red meat we include in our diets and the risk of stroke and heart failure. In this case, the consumption of red meat was identified as a potential risk factor, although here, the association was less striking.
In the same way, they designed a predictive risk model targeting congestive heart failure and stroke, based on the known risk factors obtained with the Framingham risk score, to which they also added the correlation revealed between coffee consumption and cardiovascular health.
“Our findings suggest that machine learning could help us identify additional factors to improve existing risk assessment models. The risk assessment tools we currently use to predict whether someone might develop heart disease, particularly heart failure or stroke, they are very good but not 100% “, explains Laura Stevens, co-author of the study.
Referencia: Drinking coffee may be associated with reduced risk of heart failure and stroke. American Heart Association’s (AHA) Scientific Sessions 2017, en Anaheim, California (EE. UU.). Presentation M2040 – Session: LB.APS.07