Synthetic intelligence helps spot diabetes threat


Artificial intelligence isn’t telling you not to eat that second cookie. But it might help your doctor know if there’s a good chance you will get diabetes in the next year, which might make the dessert less appealing.

Robert Menzie, senior data scientist in Sanford Health’s Advanced Analytics Group, has developed an AI algorithm that shows the likelihood that someone has or could develop type 2 diabetes in the near future.

It examines the last five years of a patient’s medical history and compares it to similar patients diagnosed with type 2 diabetes. The AI ​​provides a risk assessment that the person’s groom can use to dig deeper.

“What it really does is calculate all of this information so the provider can do what we really want them to do: spend time with the patient. Because AI can’t do that. It can tell you a lot from your electronic medical record. But the provider is the only one who can tell you what life is like at home and how the patient has felt for the past 30 days, ”Menzie said. “These socio-economic components contribute significantly more to a person’s health than what is in the EMR.”

The goal is to identify high-risk patients so that the provider can diagnose and control diabetes as quickly as possible to avoid more serious problems such as heart disease, vision loss, and kidney disease later.

More than 34 million Americans, or roughly one in ten, have diabetes, and at least 90% are type 2, according to the Centers for Disease Control and Prevention.

“More done faster”

In addition to a risk assessment, the algorithm also informs the provider about the underlying factors. This gives the doctor some insight into the diagnosis and treatment of diabetes.

“The provider doesn’t have to look through a panel of 1,500 patients. The AI ​​can give them the top 10, the top 5 most at risk, and the reasons why, ”said Menzie.

The computer looks at about 800 different values, he said. “If you ask a vendor to look at all of these, they’ll laugh at you.

“The computer can figure that out for you. A doctor can if he has spent a lot of time in front of the computer. But we can have it in front of us in 30 seconds versus 30 days, ”said Menzie. “Anything we let the computer do, the doctor could have done. We only use the computer because we can do a lot more, faster. “

Diabetes education

Scott Boyens, MD, a sports medicine family doctor for Sanford Health, is serving as the vendor champion for the project. He gave Menzie information about what information is important, whether the data points make sense, and how the data should be presented.

“Diabetes is huge. Anything we can do to intervene sooner will benefit patients in the long term. The exciting thing about this tool is that in many cases it will pick up patients who weren’t necessarily on your radar, ”said Dr. Boyens.

He recently identified a patient using the AI ​​tool who did not immediately show signs of diabetes.

“It is now changing the conversation about what we can do to intervene in any of these risk factors to make a difference and prevent it from happening on passport,” said Dr. Boyens.

He said it also gives him visual aid to educate patients and aid previous conversations about risk factors.

“It gives me some credibility for what I said,” said Dr. Boyens. “You can’t do anything about age and gender. But what can you do about these particular data points to reduce your risk? I told you that you are at increased risk. And now I have a tool that shows you why and how we’re going to change that. “

Learn more

Posted in Health Information, Healthy Living, Innovations, Weight Loss

Leave a message