News | ECG | June 18, 2021

Study of AI-enabled EKGs Finds that Difference Between Numerical Age and Biological Age Significantly Affects Health, Longevity

 A new study found that differences between a person's age in years and his or her biological age, as predicted by an artificial intelligence (AI)-enabled EKG, can provide measurable insights into health and longevity.

Getty Images


June 18, 2021 — You might be older ― or younger ― than you think. A new study found that differences between a person's age in years and his or her biological age, as predicted by an artificial intelligence (AI)-enabled EKG, can provide measurable insights into health and longevity.

The AI model accurately predicted the age of most subjects, with a mean age gap of 0.88 years between EKG age and actual age. However, a number of subjects had a gap that was much larger, either seemingly much older or much younger by EKG age.

The likelihood to die during follow-up was much higher among those seemingly older by EKG age, compared to those whose EKG age was the same as their chronologic or actual age. The association was even stronger when predicting death caused by heart disease. Conversely, those who had a lesser age gap ― considered younger by EKG ― had decreased risk.

"Our results validate and expand on our prior observations that EKG age using AI may detect accelerated aging by proving that those with older-than-expected age by EKG die sooner, particularly from heart disease. We know that mortality rate is one of the best ways to measure biological age, and our model proved that," said Francisco Lopez-Jimenez, M.D., chair of the Division of Preventive Cardiology at Mayo Clinic. Dr. Lopez-Jimenez is senior author of the study.

When researchers adjusted these data to consider multiple standard risk factors, the association between the age gap and cardiovascular mortality was even more pronounced. Subjects who were found to be oldest by EKG compared to their actual age had the greatest risk, even after accounting for medical conditions that would predict their survival, while those found the youngest compared to their actual age had lower cardiovascular risks.

Mayo Clinic researchers evaluated the12-lead EKG data of more than 25,000 subjects with an AI algorithm previously trained and validated to provide a biologic age prediction. Subjects with a positive age gap — an EKG age higher than their chronological or actual age — showed a clear connection to all-cause and cardiovascular mortality over time. The findings are published in European Heart Journal ― Digital Health.

Study subjects were selected through the Rochester Epidemiology Project, an index of health-related information from medical providers in Olmsted County, Minnesota. The subjects had a mean age around 54 and were followed for approximately 12.5 years. The study excluded those with a baseline history of heart attacks, bypass surgery or stents, stroke or atrial fibrillation.

"Our findings open up a number of opportunities to help identify those who may benefit from preventive strategies the most. Now that the concept has been proven that EKG age relates to survival, it is time to think how we can incorporate this in clinical practice.More research will be needed to find the best ways to do it," says Dr. Lopez-Jimenez.

Mayo Clinic is a leader in the movement to bring the tools and technology of AI into routine practice to benefit people with heart disease and those who are at increased risk of it. Mayo's Artificial Intelligence in Cardiology Work Group continues to apply these new techniques to early risk prediction and diagnosis of serious and complex heart problems. Dr. Lopez-Jimenez notes that this individualized approach to medicine in the field of digital health complements the knowledge of doctors and improves shared decision-making with patients and their families.

Dr. Lopez-Jimenez and co-authors Paul Friedman, M.D.; Zachi Attia, Ph.D.; and Suraj Kapa, M.D. ― all of Mayo Clinic ― have filed intellectual property related to the AI algorithm used in this research.

For more information: www.mayoclinic.org

Related Content

News | Artificial Intelligence

September 27, 2021 — Zebra Medical Vision, the deep-learning medical imaging analytics company, announces its eighth U.S ...

Home September 27, 2021
Home
Feature | Artificial Intelligence | By Dave Fornell, Editor

Artificial intelligence (AI) is growing in all areas of medicine and was the topic of several advanced technology ...

Home September 08, 2021
Home
Webinar | Artificial Intelligence

Artificial intelligence is becoming best practice to support clinical decisions and help standardize echocardiography ...

Home August 12, 2021
Home
News | Artificial Intelligence

July 21, 2021 — Artificial intelligence (AI) medical imaging vendors Viz.AI and Avicenna.AI have partnered to enable ...

Home July 21, 2021
Home
Videos | Artificial Intelligence

Federico Asch, M.D., FASE, director of cardiovascular core labs, cardiovascular imaging, MedStar Health Research ...

Home July 01, 2021
Home
News | Artificial Intelligence

June 28, 2021 — Circle Cardiovascular Imaging Inc. and DiA Imaging Analysis Ltd. entered into a multi-year partnership ...

Home June 28, 2021
Home
News | Artificial Intelligence

June 25, 2021 – COVID-19 changed everything in healthcare, and a benefit from this pandemic was a surge in innovations ...

Home June 25, 2021
Home
Feature | Artificial Intelligence

The digital transformation of healthcare is underway, but it will advance further and faster if key stakeholders work ...

Home June 10, 2021
Home
News | Artificial Intelligence

June 9, 2021 — AI Med will present its Virtual Clinical Series: Imaging Built by Clinicians, for Clinicians, June 29-30 ...

Home June 09, 2021
Home
News | Artificial Intelligence

June 3, 2021 — Medical imaging AI specialist Avicenna.AI announced that it has received certification in the United ...

Home June 07, 2021
Home
Subscribe Now