Researchers Harness Artificial Intelligence to Help Predict Sudden Cardiac Death

Researchers are actively exploring the use of artificial intelligence (AI) to predict and potentially help to address sudden cardiac death, according to research that will be shared at the American Heart Association’s Resuscitation Science Symposium 2023. According to the study authors, AI could present an innovative path forward in reshaping the landscape of global health strategies.

Image credit: Tierney | stock.adobe.com

“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,” said study lead author Xavier Jouven, MD, PhD, professor of cardiology and epidemiology at the Paris Cardiovascular Research Center, Inserm U970-University of Paris, 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.”

Investigators used to AI to analyze medical information from registries and databases for 25,000 individuals who died from sudden cardiac arrest, as well is 70,000 individuals from the general population. Data from these groups were matched by age, sex, and residential area.

These data were collected from medical records up to 10 years before each death occurred and included more than 1 million hospital diagnoses and 10 million medication prescriptions. The use of AI to enabled researchers to build approximately 25,000 equations with personalized health factors that identified individuals with a very high risk of sudden cardiac death and helped develop a customized risk profile for the study population.

Personalized risk equations include information, such as medical details that include high blood pressure treatments and heart disease history, as well as mental and behavioral health disorders and substance abuse history. The investigators identified the factors that are most likely to raise or lower the risk of sudden cardiac death at a specific percentage and time frame. AI analysis was also able to identify those with a more than 90% of risk of sudden death.

Study limitations included the potential use of prediction models beyond the AI research project, medical data were collected in electronic health records that sometimes included proxies instead of raw data, and the data collected may be different among the countries, which necessitates an adaptation of the prediction models, according to the investigators.

“We have been working for almost 30 years in the field of sudden cardiac death prediction, however, 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. “While doctors have efficient treatments such as correction of risk factors, specific medications and implantable defibrillators, the use of AI is necessary to detect in a given subject a succession of medical information registered over the years that will form a trajectory associated with an increased risk of sudden cardiac death. We hope that with a personalized list of risk factors, patients will be able to work with their clinicians to reduce those risk factors and ultimately decrease the potential for sudden cardiac death.”

Reference

Artificial intelligence may help predict – possibly prevent – sudden cardiac death. American Heart Association. News release. November 6, 2023. https://newsroom.heart.org/news/artificial-intelligence-may-help-predict-possibly-prevent-sudden-cardiac-death?preview=62f2