Predicting sudden cardiac death may be possible using artificial intelligence (AI) to analyse medical information in electronic health records, according to French preliminary research.
A team analysed electronic health records from 25,000 people who had died suddenly and 70,000 people hospitalised for cardiac arrest who did not die. They used AI to build personalised health equations that identified each person’s risk of dying from sudden cardiac arrest.
Additionally, the researchers were able to develop a customised risk profile of each of the individuals – a tool they said could be used in the future to address individual risks before a person experiences cardiac arrest and may lead to preventing deaths.
The AI analysis was able to identify people who had more than a 90% risk of sudden death, and they represented more than one fourth of all cases of sudden cardiac death.
The research was presented at the American Heart Association’s Resuscitation Science Symposium held in Philadelphia in November.
“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 Xavier Jouven, the lead author of the study. “We proposed a new approach not restricted to the usual cardiovascular risk factors but encompassing all medical information available in electronic health records.”
Using AI to analyse the data from the electronic health records, researchers built nearly 25,000 equations with personalised health factors used to identify those who were at very high risk of sudden cardiac death.
Image credit | Sciencepl