In Dallas on November 6, 2023, a study revealed that using artificial intelligence (AI) can help predict sudden cardiac death and reduce the risk of future deaths. This could be a significant step toward global health and prevention strategies. The research will be presented at the American Heart Association’s Resuscitation Science Symposium 2023, happening on November 11-12 in Philadelphia. The event focuses on the latest developments in treating heart and lung-related emergencies.
Xavier Jouven, M.D., Ph.D., the lead author of the study and professor of cardiology and epidemiology at the Paris Cardiovascular Research Center, Inserm U970-University of Paris, said, “Sudden cardiac death, a public health burden, represents 10% of 20% of overall deaths. Predicting it is difficult, and the usual approaches fail to identify high-risk people, particularly at an individual level. We proposed a new approach not restricted to cardiovascular risk factors but encompassing all medical information in electronic health records.”
The research team used AI to study medical records from 25,000 individuals who had died from sudden cardiac arrest and 70,000 from the general population in Paris, France, and Seattle. They matched the data based on age, sex, and where they lived. They collected over a million hospital records and ten million medication prescriptions spanning up to a decade before each person’s death.
With AI, they created 25,000 equations that considered each person’s unique health factors to identify those at high risk of sudden cardiac death. They also made personalized risk profiles for each individual in the study.
The personalized risk equations considered a person’s medical history, like high blood pressure and heart problems, along with mental and behavioral issues, such as alcohol abuse. The analysis pinpointed factors that could either raise or lower the risk of sudden cardiac death, like an 89% risk within three months.
The AI analysis successfully identified individuals with over a 90% risk of sudden death, accounting for more than a quarter of all sudden cardiac death cases.
Jouven, founder of the Paris Sudden Death Expertise Center, said, “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.”
“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.” He added.
Some limitations of the study include the uncertainty about using the prediction models for purposes other than this research. Also, electronic health records sometimes use proxies instead of direct data, and the data can vary between countries, which may require adjustments to the prediction models.
For additional details about the study’s co-authors, disclosures, and funding sources, refer to the abstract.
It’s important to note that the statements and conclusions from studies presented at the American Heart Association’s scientific meetings are the author’s own and may not reflect the Association’s official stance. The Association doesn’t vouch for their accuracy or reliability. Abstracts at these meetings are not peer-reviewed but are selected based on their potential to contribute to the diversity of scientific topics discussed at the event. The findings are considered preliminary until published in a peer-reviewed scientific journal.
This study demonstrates the feasibility of AI to predict and potentially prevent sudden cardiac death. The personalized risk assessments and early intervention strategies AI can enable represent significant progress in cardiac health. Further research and implementation could lead to a substantial reduction in the incidence of sudden cardiac death, benefiting global health efforts.