Newswise — ROCHESTER, Minnesota – A new artificial intelligence (AI) algorithm that identifies cardiac dysfunction from a single-lead electrocardiogram ( ECG ) may also predict long-term patient survival after cardiac surgery , according to new research of the Mayo Clinic .

The study, published in the medical journal Mayo Clinic Proceedings , finds that an algorithm that has already demonstrated the ability to effectively detect patients with reduced left ventricular ejection fraction can also be used to predict long-term mortality after cardiac surgery, which makes it a potentially valuable tool for assessing risk as patients and healthcare providers consider surgery.

"Our study finds that there is a clear correlation between long-term mortality and a positive AI ECG screening for reduced ejection fraction among patients without apparent severe cardiomyopathy," says Mohamad Alkhouli, MD, cardiologist at Mayo Clinic and senior author of the study. "This correlation was consistent between patients undergoing valve surgery, coronary bypass, or valve and coronary bypass."

The retrospective study involved the analysis of 20,627 patients at the Mayo Clinic in Rochester from 1993 to 2019. The patients underwent bypass surgery, valve surgery, or both, and had a left ventricular ejection fraction of greater than 35%. Among these patients, 17,125 had a normal AI ECG screen and 3502 had an abnormal screen. Patients with an abnormal screening tended to be older and with more comorbidities.

The algorithm was applied to the most recent ECG performed on patients 30 days before surgery. Baseline characteristics, as well as 30-day and long-term in-hospital mortality data were extracted from a Mayo Clinic cardiac surgery database.

The probability of survival at five years was 86.2% for patients with a normal screen versus 71.4% for patients with an abnormal screen. The probability of survival at 10 years was 68.2% and 45.1%, respectively, for the two groups.

"Our study documented the predictive value of the algorithm in predicting long-term, all-cause mortality after cardiac surgery," says Dr. Alkhouli. “The analysis showed that an abnormal AI screening was associated with a 30% increase in long-term mortality after coronary bypass or coronary bypass surgery. For physicians, this can help to stratify the risks of patients referred for surgery and facilitate shared decision-making.”

The study is believed to be the first large-scale research to illustrate the usefulness of single ECG AI algorithms to better predict cardiac surgery outcomes. As the algorithm uses a routine and the test is relatively inexpensive, it can be applied widely after validation.

Additional studies are underway to determine whether the information provided by the algorithms can improve diagnosis, decision making, and clinical outcomes. The use of AI-based tests in cardiology is becoming increasingly common in academic health care centers and the results of this study may encourage more providers to consider their clinical significance.


Journalists : Dr. Alkhouli is available for interviews in English and Arabic. Information about Mayo Clinic's international services is available here . Watch a video by Abdullah Mahayni, study co-author, who discusses the article.

About Mayo Clinic Proceedings

Mayo Clinic Proceedings is a monthly, peer-reviewed medical journal that publishes articles and reviews on clinical and laboratory medicine, clinical research, basic science research, and clinical epidemiology. The magazine, sponsored by the Mayo Foundation for Medical Education and Research as part of its commitment to medical education, has been published for 95 years and has a circulation of 127,000.

About Mayo Clinic

The Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, providing compassion, knowledge and answers for all who need healing. Visit the Mayo Clinic News Network for more information about the Mayo Clinic.

Journal Link: Mayo Clinic Proceedings