Artificial intelligence may help predict-possibly prevent-sudden cardiac death

USA: Artificial intelligence (AI) can predict cardiac death, and address a person's risk to prevent future death, preliminary research has revealed. 

The findings, presented at the American Heart Association’s Resuscitation Science  Symposium 2023, could offer a new move toward prevention and global health strategies. 

The AI analysis identified people who had more than 90% of the risk of dying suddenly, and they represented more than one-fourth of all cases of sudden cardiac death.

"Predicting sudden cardiac death, and perhaps even addressing a person’s risk to prevent future death, may be possible through artificial intelligence (AI) and could offer a new move toward prevention and global health strategies," the study stated. 

The research team analyzed medical information with AI from registries and databases in Paris, France and Seattle for 25,000 people who had died from sudden cardiac arrest and 70,000 people from the general population, with data from the two groups matched by age, sex and residential area. The data was gathered from medical records up to ten years prior to each death.

Using AI to analyze the data, researchers built nearly 25,000 equations with personalized health factors used to identify those people who were at very high risk of sudden cardiac death. Additionally, they developed a customized risk profile for each of the individuals in the study.

The personalized risk equations included a person’s medical details as well as mental and behavioural disorders including alcohol abuse. The analysis identified those factors most likely to decrease or increase the risk of sudden cardiac death at a particular percentage and time frame, for example, 89% risk of sudden cardiac death within three months.

The AI analysis was able to identify people who had more than 90% of the risk of dying suddenly, and they represented more than one-fourth of all cases of sudden cardiac death.

Ref: American Heart Association Resuscitation Science Symposium 2023, Abstract 347