AI Predicts Long-Term Patient Survival After Cardiac Surgery

December 06, 2021 - According to Mayo Clinic researchers, a novel artificial intelligence algorithm can predict long-term patient survival after cardiac surgery.

The research team found an algorithm that previously showed it could detect patients with reduced left ventricular ejection fraction could also predict long-term mortality after cardiac surgery, creating a valuable risk assessment tool for a patient considering surgery.

“Our study finds there is a clear correlation between long-term mortality and a positive AI ECG screen for reduced ejection fraction among patients without apparent severe cardiomyopathy,” Mayo Clinic cardiologist and the study’s senior author, Mohamad Alkhouli, MD, said in a press release.

“This correlation was consistent among patients undergoing valve, coronary bypass, or valve and coronary bypass surgery.”

The retrospective study used data from 20,627 patients at Mayo Clinic in Rochester from 1993 to 2019. The patients underwent coronary artery bypass grafting, valve surgery, or both. Additionally, they had a left ventricular ejection fraction of greater than 35 percent.

Of those patients, 17,125 had a normal AI EKG screen and 3,502 had an abnormal screen. The patients with abnormal screens were typically older with more comorbidities.

The algorithm was applied to the most recent EKG the patient underwent within 30 days of surgery. Baseline characteristics as well as in-hospital, 30-day, and long-term mortality data were extracted from the Mayo Clinic cardiac surgery database.

The data indicated the probability of survival after five years was 86.2 percent for those with a normal screen versus 71.4 percent for patients with an abnormal screen. At ten years, the probability of survival was 68.2 percent and 45.1 percent for the two groups.

“Our study documented the algorithm’s prognostic value in predicting long-term, all-cause mortality after cardiac surgery,” Alkhouli said. “The analysis showed that an abnormal AI screen was associated with a 30% increase in long-term mortality after valve or coronary bypass surgery. For clinicians, this may aid in risk stratification of patients referred for surgery and facilitate shared decision-making.”

According to the press release, the study is believed to be the first large-scale research examining the usefulness of AI algorithms with a single EKG to improve cardiac surgery prediction outcomes. Additionally, the algorithm used a routine and inexpensive test, allowing it to be applied widely after validation.

More studies are underway to determine if the information provided by the algorithms could improve diagnosis, decision-making, and clinical outcomes. According to researchers, using AI-based tests in cardiology is becoming more common in academic healthcare centers. The results from this study could encourage more providers to pursue the AI method.