Research highlights:
- Using artificial intelligence (AI) to analyze medical information in electronic medical records may be able to predict sudden cardiac death, according to a preliminary study conducted by French researchers.
- Researchers analyzed the electronic health records of 25,000 people who died suddenly in Paris, France, and Seattle, Washington, and 70,000 people who were hospitalized for cardiac arrest but did not die, and used AI to developed a personalized health equation that identifies patients’ risk of dying from sudden cardiac arrest. .
- Additionally, researchers could develop a customized risk profile for each individual, and in the future, this tool could be used to address individual risk before a person goes into cardiac arrest, preventing death. He said it could lead to.
Embargoed until Monday, November 6, 2023, 4:00 a.m. CT/5:00 a.m. ET
DALLAS, November 6, 2023 — Artificial intelligence (AI) may also be able to predict sudden cardiac death and address human risks to prevent future deaths, according to preliminary research. It could lead to a new movement towards prevention and global health strategies.Study to be presented at American Heart Association meeting Resuscitation Science Symposium 2023. The conference, to be held in Philadelphia on November 11 and 12, is the premier global exchange on the latest advances in the treatment of cardiopulmonary arrest and life-threatening trauma.
“Sudden cardiac death is a public health burden, accounting for 10% to 20% of all deaths. It is difficult to predict and the usual approach is to identify people at high risk, especially at the individual level. “We cannot do that,” said Xavier Joubin, MD, lead author of the study and professor of cardiology and epidemiology at the University of Paris. University of Paris Inserm U970 Cardiovascular Research Center. “We proposed a new approach that is not limited to the usual cardiovascular risk factors, but encompasses all medical information available in electronic medical records.”
The personalized risk equation included personal medical details such as treatment for high blood pressure and history of heart disease, as well as mental and behavioral disorders, including alcohol abuse. This analysis identified the factors most likely to reduce or increase the risk of sudden cardiac death at specific rates and time frames. For example, the risk of sudden cardiac death within 3 months is 89%.
AI analysis was able to identify people with a 90% or higher risk of sudden death, who accounted for more than a quarter of all cases of sudden cardiac death.
“We have been working in the field of sudden cardiac death prediction for nearly 30 years and never expected to reach such high accuracy. We also found that these data are often published from different medical disciplines (a mix of neurological, psychiatric, metabolic and cardiovascular data). “It’s difficult for the human eye and brain to understand, in certain areas,” said Jouvin, who is also the founder of the Paris Center of Sudden Death Expertise. “While doctors have effective treatments such as risk factor modification, specific medications, and implantable cardioverter-defibrillators, there is a long-standing set of medical treatments that shape trajectories associated with increased risk. The use of AI is required to detect information from specific subjects of sudden cardiac death. We hope that using our personalized list of risk factors, patients can work with their clinicians to reduce those risk factors and ultimately reduce the likelihood of sudden cardiac death. Masu. ”
Limitations of this study include the potential for predictive models to be used beyond this study. Furthermore, medical data collected in electronic health records may include proxies rather than raw data, and the data collected may differ from country to country, requiring adaptation of predictive models.
Co-authors, disclosures, and funding sources are listed in the abstract.
Research statements and conclusions presented at American Heart Association scientific meetings are solely those of the study authors and do not necessarily reflect the policy or position of the association. The Association makes no representations or warranties regarding its accuracy or reliability. Abstracts presented at the Society’s scientific conferences are not peer-reviewed, but are hand-picked by an independent review committee and considered based on their potential to increase the diversity of scientific issues and views discussed at the conference. The findings are considered preliminary until published as a full manuscript in a peer-reviewed scientific journal.
The association is primarily funded by individuals. Foundations and corporations (including pharmaceuticals, device manufacturers, and other companies) also make contributions, which help fund specific programs and events for the association. The Society has strict policies in place to ensure that these relationships do not influence scientific content. Revenues from pharmaceutical companies, biotech companies, device manufacturers, health insurance companies, and overall financial information for the association can be found here.
Additional resources:
About the American Heart Association
The American Heart Association works tirelessly to help the world live longer, healthier lives. We are dedicated to ensuring equitable health in all communities. Through collaboration with thousands of organizations and the power of millions of volunteers, we fund innovative research, advocate for public health and share lifesaving resources. The Dallas-based organization has served as a leading source of health information for nearly a century. heart.org, Facebook, X Or call 1-800-AHA-USA1.
###
Media inquiries and AHA expert opinion:
AHA Communications and Media Relations in Dallas: 214-706-1173; ahacommunications@heart.org
Sarah Williams: 214-706-1156; sarah.d.williams@heart.org
General inquiries: 1-800-AHA-USA1 (242-8721)
heart.org and stroke.org
