New York Times Magazine asks AI: Is coffee good for you? Through machine learning, researchers are finally arriving at valid answers.

From Studies on Coffee & Health to Nutrition, ML Sorts Out the Impact of Variables

I first experienced a food controversy when I was a kid. It found that margarine was not as good for you as it was promoted to be. Then right behind that revelation came the news that butter probably isn’t good for you either. I mean, come on. How are we supposed to eat toast?

And then it seems like the research community would reverse their findings every couple of years. It wasn’t evident, to say the least. Well, get ready for a new controversy that will have many of us flummoxed. And not in a good way. Particularly if you enjoy your morning coffee.

An article found at from the New York Times Magazine brings up the coffee and heart disease issue. Writer Kim Tingly explains that back in 1991, researchers discovered that coffee could be the source of cancer problems and heart disease issues. So coffee bad, right?  The W.H.O studies showed that people who smoke are most likely to drink coffee and smoking was causing health issues; they had to re-evaluate.

Fast forward to 2017. That year, a review of the available evidence published in The British Medical Journal found a link between coffee and a lower risk for some cancers, as well as for cardiovascular disease and death from any cause.

Now, in 2021, a new analysis of existing data, published in the American Heart Association journal Circulation: Heart Failure, suggests that two to three (or more) cups of coffee per day may lower the risk of heart failure. Of course, the usual caveats apply: This represents correlation, not causation. It could be that people with heart disease tend to avoid coffee, possibly thinking it will be bad for them. So…good for you or not good for you, which is it? Since they generate confusion, what’s the point of these studies?

Here’s part of the reason why they didn’t get it right.

“You can dredge up any finding you want in science using your own biases, and you get a publication out of it,” says Steven Heymsfield, a professor of metabolism and body composition at the Pennington Biomedical Research Center at Louisiana State University.

The early studies’ problem is the variants or variables that could not be measured accurately—until recently when AI and Machine Learning changed the game entirely.

This is how the lead author David Kao, a cardiologist at the University of Colorado School of Medicine, characterized it:

“The overall question was, What are the factors in daily life that impact heart health that we don’t know about that could potentially be changed to lower risk.” Because one in five Americans will develop heart failure, even small changes in their behaviors could have a big cumulative impact.

The ability of machine learning to process vast amounts of data could transform the ability of nutrition researchers to study their subjects’ behavior more precisely and in real-time, says Amanda Vest, medical director of the Cardiac Transplantation Program at Tufts Medical Center, who wrote an editorial that was published with the Circulation study.

Tingly’s article goes into some depth on how today’s health studies will be vastly more accurate with AI and will cover a lot more data that will actually have meaning for the people being studied and the people doing the study.