Rapid response time is a critical element in ensuring heart attack survival, but researchers presenting at the recent Society of Nuclear Medicine and Molecular Imaging 2021 Annual Meeting have gone a step further, developing a deep learning network that can predict adverse cardiac events including heart attacks and death.

For their study, the results of which were also published in the Journal of Nuclear Medicine, the team tapped a data registry of over 20,000 patients, dividing the data into training, validation and testing cohorts.

According to a press release accompanying the study, “the deep learning network highlighted regions of the heart that were associated with risk of major adverse cardiac events and provided a risk score in less than one second during testing.” The network was able to predict major adverse cardiac events (MACE) using single photon emission tomography (SPECT) myocardial perfusion imaging (MPI). The researchers used data from the largest SPECT dataset called the REgistry of Fast myocardial perfusion Imaging with NExt generation SPECT (REFINE SPECT).

Researchers also developed a mechanism that identifies polar map image regions so that physicians can easily visually interpret a patient’s risk level. The network gave each patient a score that quantified how likely they were to have a major adverse cardiac event, and patients were tracked for a follow-up period of over four years, on average. Those with the highest deep learning scores had an annual major adverse cardiac event rate of 9.7 percent, an approximately 10-fold increased risk compared to patients with the lowest scores.

"These findings show that artificial intelligence could be incorporated in standard clinical workstations to assist physicians in accurate and fast risk assessment of patients undergoing SPECT MPI scans," said Ananya Singh, MS, a research software engineer in the Slomka Lab at Cedars-Sinai Medical Center in Los Angeles, California. "This work signifies the potential advantage of incorporating artificial intelligence techniques in standard imaging protocols to assist readers with risk stratification." 

As the study concluded, “Use of a deep learning network allows for prediction of MACE directly from polar map images with improved accuracy compared to automatic quantitation of perfusion. MACE-DL also incorporates a mechanism to explain to the physician, which polar map image regions contribute most to MACE prediction.”

Photo by SKapl/Getty Images