Artificial Intelligence Shows Promise in Predicting Sudden Cardiac Death


Artificial intelligence could help detect a trend in medical information for individuals that would help physicians predict an increased risk of sudden cardiac death.

Artificial intelligence (AI) may help in predicting sudden cardiac death and even the risk of future death, according to preliminary results of a study presented at the American Heart Association’s Resuscitation Science Symposium 2023. Investigators added that AI could offer new insight into prevention and inform new global health strategies in cardiovascular disease.1

Abstract image of a man with chest pain. Background with selective focus and copy space. | Image Credit: top images -

top images -

“Sudden cardiac death, a public health burden, represents 10% to 20% of overall deaths. Predicting it is difficult, and the usual approaches fail to identify high-risk people, particularly at an individual level,” Xavier Jouven, MD, PhD, professor of cardiology and epidemiology at the Paris Cardiovascular Research Center in Inserm U970-University of Paris, said in a press release. “We proposed a new approach not restricted to the usual cardiovascular risk factors but encompassing all medical information available in electronic health records [(EHR)].”1

According to the CDC, more than 356,000 individuals experience cardiac arrest outside of the hospital in the United States every year, with approximately 60% to 80% dying before reaching the hospital. It can be due to brain injury, injury to internal organs, or psychological distress, including anxiety, post-traumatic stress disorder, and depression. Individuals at the highest risk for cardiac arrest are older adults and men.2

The investigators analyzed medical data with AI, collected from registries and databases from Paris, France, and Seattle, Washington, for approximately 25,000 individuals who died from sudden cardiac arrest and 70,000 individuals who were matched by age, sex, and residential area. Further, they included data on more than 1 million hospital diagnoses and 10 million medical prescriptions for up to 10 years prior to each death, according to the press release.1

Using the data with AI, the investigators used approximately 25,000 equations that included personalized health factors that identified individuals who were at very high risk of sudden cardiac deaths. They used the data to develop custom risk profiles for each individual who was included in the study.1

“We did not expect to reach such a high level of accuracy. We also discovered that the personalized risk factors are very different between the participants and are often issued from different medical fields (a mix of neurological, psychiatric, metabolic, and cardiovascular data) – a picture difficult to catch for the medical eyes and brain of a specialist in one given field” Jouven said in the press release.1

Jouven added that the use of AI could help detect a trend of medical information for individuals that would help physicians predict an increased risk of sudden cardiac death.

However, limitations were found in the study, including the potential use of the prediction model beyond this research, according to the press release. Additionally, medical data collected in EHR can sometimes include proxies, instead of raw data. The data may also differ among other countries, according to the press release, meaning that the adaption and research of the prediction model is needed.1

“We hope that with a personalized list of risk factors, patients will be able to work with their [physicians] to reduce those risk factors and ultimately decrease the potential for sudden cardiac death,” Jouven said in the press release.1


  1. Artificial intelligence may help predict – possibly prevent – sudden cardiac death. News release. American Heart Association. November 6, 2023. Accessed November 13, 2023.
  2. Centers for Disease Control and Prevention. Heart Disease: Cardiac Arrest. CDC. Updated May 30, 2023. Accessed November 14, 2023.
Related Videos
palliative and hospice care/ Image Credits: © David Pereiras -
multiple myeloma clinical trial daratumumab/ Image Credits: © Dragana Gordic -
multiple myeloma clinical trial/Image Credits: © Studio Romantic -
Medicine tablets on counting tray with counting spatula at pharmacy | Image Credit: sutlafk -
pharmacy oncology, Image Credit: © Konstantin Yuganov -
Mayo Clinic oncology pharmacy
A panel of 5 experts on ASCVD
A panel of 5 experts on ASCVD
A panel of 5 experts on ASCVD
© 2024 MJH Life Sciences

All rights reserved.