A Stanford University study has found that the shape of a person’s heart could reveal their risk for developing cardiomyopathy, an illness in which it becomes harder for the heart to deliver blood throughout one’s body.
The study, titled “Deep learning-enabled analysis of medical images identifies cardiac sphericity as an early marker of cardiomyopathy and related outcomes,” published in the journal Cell, found that those with more spherical (round) hearts have an almost 50% higher probability of suffering from the condition than others.
Shoa Clarke and David Ouyang, MD, from the Smidt Heart Institute of Cedars-Sinai, served as senior authors of the study, while Milos Vukadinovic, a bioengineering student at UCLA, was the lead author. Clarke and Ouyang decided to focus on heart shape after their clinical experience revealed noticeable differences in shape and structure, even when standard measurements appeared normal, according to Clarke.
“Most people who practice cardiology are well aware that after someone develops heart disease, the heart will look more spherical,” said Shoa Clarke, MD, PhD, preventive cardiologist and an instructor in the Stanford School of Medicine’s departments of medicine and pediatrics.
Clarke explained that if heart shape becomes a routinely collected detail in clinical settings, doctors might begin to notice changes in the roundness that could indicate a patient is in the early stages of developing a heart problem.
Researchers used artificial intelligence (AI) to study over 38,897 MRI scans of healthy hearts from the UK Biobank. The UK Biobank is a large biomedical database that contains information from half a million participants in the United Kingdom.
Scientists looked at the roundness of the left ventricle, a usually cone-shaped heart chamber responsible for pumping oxygen-rich blood to the body. They then analyzed the participants’ health records to pinpoint those with specific genetic markers for heart conditions.
The researchers concluded that the presence of increased sphericity could “identify individuals with underlying molecular/cellular abnormalities that place them at heightened risk for developing overt cardiomyopathy or related diseases such as atrial fibrillation.”
The insights gained on cardiac roundness were just one aspect of the study for Clarke, who believes that existing MRI images of the cardiovascular system, like those they used, could offer a wealth of unexplored scientific clues for various new investigations.
Clarke emphasized that there is valuable information in current medical imaging that remains untapped.
Clarke and Ouyang, who met and became friends during their cardiology fellowships at Stanford Medicine, are equally focused on data science and biomedical science. They noted that while artificial intelligence is a widely discussed innovation spawned by technology, it has yet to yield concrete results in the field.
“There is broad enthusiasm for using artificial intelligence, biobanks and genomics to accelerate biomedical research,” Clarke said. “Yet, the number of practicing clinicians who have the technical skills to lead such research is still relatively small.”