Can complicated math equations help detect heart disease, even before you realize you’re sick? The answer appears to be yes, and they can do it by sifting through potential clues left behind during your trips to the doctor’s office.

“We now have the automated intelligence tools to help us collect and analyze mountains of medical data in ways that we couldn’t just a short time ago,” said Nina Goodheart, a leader in women's heart health and a former Medtronic executive. “Artificial intelligence (AI) allows us to examine that data to identify certain types of heart disease sooner and get personalized treatment to the patient faster.”

So what does that actually mean for you?

Let’s use the example of Aortic Stenosis (AS) — a serious heart problem that affects 250,000 Americans every year and often goes undertreated.

AS is a condition where the heart’s aortic valve gradually narrows and restricts blood flow from the heart to the rest of the body. When this happens the body sends out a variety of warning signals through symptoms that can be subtle, vary from person to person, and develop slowly over time. All of which makes diagnosing the problem difficult.

But whenever you visit the doctor, clues to your developing AS may be left behind. At every medical visit, lots of health information gets entered into your Electronic Health Record (EHR). It could include everything from your history of alcohol or tobacco use to vital signs to lab results to notes and observations from the doctor, and much more. The clues pointing to AS might be buried in that EHR data—but it can be a modern-day version of the needle in a haystack.

That’s where the math comes in.

“AI helps us bring order to what can sometimes be data chaos,” said Chris Rogers, Sr. Director of Strategic Provider Solutions at Tempus AI, a healthcare technology company based in Chicago that uses data and artificial intelligence to create medical diagnostic solutions. “Our algorithms can look for unique characteristics in the health data that a clinician might not identify for every one of their patients.”

The company’s software, known as Tempus Next, includes 60 highly complex algorithms, developed to identify potential care gaps across 15 cardiovascular diseases, including AS.

“Our software is designed to handle the complexity of medical data, which requires sophisticated and adaptable solutions,” Rogers explained. “There is no one-size-fits-all algorithm in healthcare. Each institution has unique needs and circumstances, and our technology is built to consider as much information as possible to provide tailored insights.”

Tempus Next combs through the data points in your EHR, even the handwritten notes from your doctor, and compares your information to the diagnostic criteria in clinical guidelines for AS. If your health information meets enough of the criteria, the system notifies your doctor for possible next steps.

It’s much more than a theoretical exercise.

Tempus recently finished a case study with the John Brancaccio St. Francis Hospital and Heart Center in New York. The Tempus Next algorithm identified 388 patients who met the criteria for AS and/or one other serious heart condition, but who did not yet have an existing plan to treat their disease. The Tempus Next system flagged their cases and alerted their doctors to the findings.

Math has made a potentially life-changing difference in each of their lives.

Medtronic and Tempus launched the ALERT study to use Tempus's AI technology to scan patient electronic health records for severe aortic stenosis or mitral regurgitation. The system analyzed records like echocardiograms and physician notes, alerting clinicians to refer detected cases for specialized care.

The study examined data from 35 hospitals, involving 765 providers and at least 1,500 patients, and found that integrating AI into electronic health records helps doctors avoid missing cases of serious heart valve disease. With AI-driven alerts, patients received referrals and treatment more quickly and frequently, showing consistent improvements across different ages, genders, races, and regions. The referral is a critical step: even when diagnosed, many patients with severe heart valve disease are not referred to treatment, which can be a potentially fatal oversight. 

“The under diagnosis of severe symptomatic aortic stenosis is a pervasive problem that can be fatal within two years without intervention. The goal of this study is to move towards better solutions for more equitable and timely care and to eliminate barriers to treatment,” said Wayne Batchelor, M.D., M.H.S., M.B.A., Interventional Cardiologist, President of the Medicine Service Line, Inova Health System, Fairfax, Va. and Steering Committee Chair of the ALERT study.  The most exciting part, experts say, is the potential impact that such technology can have on human health.

“It’s breathtaking to think about the future,” Goodheart added. “Imagine the day when we can apply this technology to hundreds of thousands or millions of patients. Imagine the number of people we can reach before their AS becomes too severe. The number of lives we can lengthen or improve. It adds up in a hurry.”

That’s the kind of math everyone can appreciate.

This is one in a series of stories about how Medtronic is using math and AI to fight disease. Click here to learn how math can help prevent cancer.

L001-04022025

---

Related content