AI-ENCODE Analyzes Machine Learning for Extracting Noncoronary Data From Routine Angiograms

May 2, 2024—Findings from the AI-ENCODE study showed that artificial intelligence (AI) successfully allowed automated extraction of key functional and physiologic data from routine angiograms.

The AI-ENCODE study leveraged advanced machine learning techniques to expand the range of data obtained from routine coronary angiograms. Investigators used a library of > 20,000 angiograms performed from 2016 to 2021 at the Mayo Clinic in Rochester, Minnesota. Mohamad Alkhouli, MD, Division Chair of Research and Innovation at Mayo Clinic School of Medicine, is lead investigator of the study.

The late-breaking results were presented at SCAI 2024, the Society for Cardiovascular Angiography & Interventions scientific sessions held May 2-4 in Long Beach, California.

According to the SCAI press release, data extracted from coronary angiograms are currently confined to detecting blockages in the coronary arteries. However, AI technology has the potential to broaden the diagnostic abilities of conventional coronary angiography by expanding its diagnostic scope, which can improve clinical decision-making and positively impact patient outcomes.

The study team developed and validated multiple AI algorithms to extract data on left and right ventricular function, intracardiac filling pressures, and cardiac index from one to two angiographic videos. Echocardiograms obtained close to the angiogram served as the gold standard for comparison, noted the SCAI press release.

As summarized in the SCAI press release, the AI models predicted left ventricular ejection fraction, left ventricular filling pressures, right ventricular dysfunction, and cardiac index with an area under a receiver operating curve of 0.87, 0.87, 0.80, and 0.82, respectively. The investigators concluded that these results show that novel AI models were able to extract key diagnostic data that would routinely have required additional tests such as echocardiograms and/or right heart catheterization.

“Traditional diagnostic tools in cardiovascular medicine harbor vast information, but much remains underutilized,” commented Dr. Alkhouli in the SCAI press release. “The AI-ENCODE project proved that AI can be leveraged to unlock and deliver a broader, more meaningful spectrum of clinical findings from existing angiograms.”

Dr. Alkhouli added, “This study truly shows us AI’s prowess in revealing insights beyond what the human eye can see. It is important that we leverage AI’s capabilities as a diagnostic tool to provide the best possible for our patients.”