Research conducted in France suggests that using Artificial Intelligence to analyse medical data in electronic health records may hold promise in predicting sudden cardiac death
In their study, the researchers examined the electronic health records of 25,000 individuals who had experienced sudden cardiac death and 70,000 individuals who had been hospitalised due to cardiac arrest but did not succumb to it.
AI-Powered risk prediction
This analysis took place in Paris, France, and Seattle, Washington. The researchers used AI to construct personalised health models that could gauge each person’s risk of sudden cardiac death.
The study enabled the development of personalised risk profiles for each individual. This tool could potentially be used in the future to address and mitigate individual risks associated with cardiac arrest.
Artificial intelligence (AI) holds the potential to predict sudden cardiac death and, possibly, to manage an individual’s risk to avert future fatalities proactively. This groundbreaking prospect, to be presented at the American Heart Association’s Resuscitation Science Symposium 2023, could represent a significant stride in prevention and global health strategies.
Customised health equations
The research team employed artificial intelligence (AI) to examine medical data retrieved from registries and databases in Paris, France, and Seattle.
They focused on two groups: 25,000 individuals who had suffered sudden cardiac arrest and 70,000 individuals from the general population, matching these groups based on age, gender, and residential location. The dataset surrounded more than 1 million hospital diagnoses and 10 million medication prescriptions, spanning up to a decade before each individual’s demise.
Utilising AI, the researchers created nearly 25,000 customised health equations that integrated various individual health factors to identify those individuals at a notably high risk of sudden cardiac death. Furthermore, they developed individualised risk profiles for each participant in the study.
AI analysis
These personalised risk equations encompassed an individual’s medical history, such as their treatment for conditions like high blood pressure and a history of heart disease, in addition to mental and behavioural disorders like alcohol abuse. The analysis pinpointed the factors most likely to either increase or decrease the risk of sudden cardiac death, providing specific probabilities and timeframes, such as an 89% risk of sudden cardiac death within three months.
The AI analysis effectively identified individuals with a risk exceeding 90% of experiencing sudden cardiac death, constituting more than a quarter of all cases of sudden cardiac death.
“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, 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.
“We proposed a new approach not restricted to the usual cardiovascular risk factors but encompassing all medical information available in electronic health records.”
“Sudden cardiac death, a public health burden, represents 10% to 20% of overall deaths.”
The study has limitations, including potential restrictions on using the prediction models beyond this research. Medical data in electronic health records sometimes rely on proxies instead of raw data, and data variations among countries may require adjustments to the prediction models.
