The benefits of physical activity have been scientifically confirmed in thousands of studies. However, for athletes who engage in extensive high-intensity physical activity for professional sports, exercise does not protect them from sudden cardiac death.

As the name suggests, this death is defined as an unexpected death within one hour of a severe and instant heart condition without an external factor. With no obvious cause, sudden cardiac deaths have remained an issue for athletes and a major question to tackle for physical health scientists. Recently, researchers from the University of Foggia in Italy used machine learning to analyze data from over seven hundred athletes to solidify and confirm potential risks that have been previously identified for sudden cardiac death.

Several factors have been associated with sudden cardiac death, including age. Victims who were under the age of thirty-five had hereditary heart conditions that caused their deaths. For athletes under the age of thirty-five, hypertrophic cardiomyopathy, a condition that enlarges heart muscles, which prevents proper blood flow, was associated with thirty-six percent of sudden cardiac deaths, with that risk increasing with age. For nonathletes over the age of thirty-five, atherosclerotic coronary artery disease, which is the buildup of cholesterol and fat in blood vessels, is commonly associated with seventy-three percent of sudden cardiac death cases.

The second common factor with sudden cardiac death is gender, as men have a higher risk than women. This difference may be due to differences in the heart's exercise-induced adaptation and remodeling of its chambers between men and women, as found in previous studies from the University of London and the University of Oulu. Studies from these universities have also shown differences in the prevalence of heart scar tissue, with men having more, and estrogen providing a protective role for women.

Finally, demographics have been associated with sudden cardiac death. According to the Minneapolis Heart Institute Foundation, African American athletes face a three times higher incidence of sudden cardiac death. With a common theme of young cardiac death victims being athletes, medical professionals and researchers believe that intense exercise may intensify pre-existing heart abnormalities through dehydration and electrolyte imbalance, or create them through those same methods.

With the randomness of the condition and the variance in risks, early detection for sudden cardiac deaths is challenging to the point of being nonexistent. Victims present no symptoms or experience warning signs, and autopsies often reveal structurally normal hearts in younger individuals. A possible reason for these “normal” hearts succumbing to sudden cardiac death is electrical abnormalities within the heart, which could explain forty-one percent of cases, but no studies have confirmed this association.

So far, the only structural abnormalities found in cardiac death victims have been enlarged muscles of heart chambers or scar tissue, but the clinical significance of confirming these conditions caused the sudden death has been debated. With so much ambiguity surrounding this condition, more research needs to be done to identify other risks and confirm their associations with sudden cardiac death. With the rise of AI and machine learning using large datasets, researchers can more effectively identify and confirm these associations.

At the University of Foggia, researchers used machine learning to analyze data from 711 athletes. Initially, the researchers examined the factors identified in previous studies. But after refining the data and the AI model, the researchers narrowed the total variables to eight core factors.

To be more thorough in their analysis, the researchers created two data subsets: one analyzed using the eight core factors and the other using the factors identified in other studies. In this analysis, the researchers used hierarchical clustering, which groups data points into a “family tree” to show their relationships. The relationship to each data point and sudden cardiac death risk factors narrows the family tree into a single cluster representing the common factor that connects them.

After applying this clustering method, the researchers identified 21 clusters between the two data subsets. While this method was efficient for analyzing large amounts of data simultaneously, the researchers' lack of clinical relevance and interpretation led to no new observations from the analysis.

Without a clinical formula or index used by medical professionals who treat athletes, the researchers' clustering confirmed that the risks identified in previous studies remain risks, but provided no further concrete confirmation. Despite this lack of confirmation, the researchers propose that the next steps in their analysis focus on each cluster individually, with emphasis on the cluster's medical significance.

From there, the researchers plan to employ advanced mathematics and statistics using machine learning to analyze larger amounts of clinical data from sudden cardiac death victims. Ultimately, the goal is to develop a better understanding of this data analysis to interpret its significance and begin applying it to athletes' health. With this understanding, it is possible to transition from a mathematical representation to a practical tool for identifying the warning signs of sudden cardiac death, thereby removing the “sudden” from its title.