Artificial intelligence identifies people at risk of heart disease

Although the study only focused on cardiovascular disease, the researchers believe it may have much broader implications. In fact, they suggest that the findings could eventually lead to a new era of personalized, preventive medicine. Doctors will proactively communicate with patients to alert them to potential illnesses and what can be done to alleviate the problem.

“We can turn to the use of pediatric cardiology at Children’s Hospital I and Intermountain and a scientist at Ura Eccles,” says Martin Tristani-Firouzi, MD, study’s corresponding author and pediatric cardiologist at Children’s Hospital I and Intermountain, and scientist at Ura Eccles. Use AI to help refine risk for almost any medical diagnosis. Harrison Institute of Cardiovascular Research and Training. “Cancer risk, thyroid surgery risk, diabetes risk?? any medical term you can imagine.”

Research appears in online journal PLOS Digital Wellbeing.

According to Mark Yandell, Ph.D., senior author of the study and professor of human studies, current methods for calculating the combined effects of various risk factors such as demographics and history Disease for cardiovascular disease is often imprecise and subjective. genetics, HA and Edna Benning Presidential Endowed Chairman at U of U Health, and co-founders of Backdrop Health. As a result, these methods fail to identify some of the interactions that could profoundly affect heart and blood vessel health.

To more accurately measure how these interactions, also known as comorbidities, affect health, Tristani-Firouzi, Yandell and colleagues from U of U Health and Intermountain Elementary Children’s Hospital , used machine learning software to sort through more than 1.6 million electronic health records (EHRs) after names and other identifying information were removed.

These electronic records, which record everything that happens to a patient, including tests, diagnoses, medications, and medical procedures, have helped researchers identify comorbidities that are more likely potentially aggravating a specific medical condition such as cardiovascular disease.

In their current study, the researchers used a form of artificial intelligence called a probabilistic graphics network (PGM) to calculate how any combination of these comorbidities would may affect the risks associated with a heart transplant, congenital heart disease, or sinoatrial node dysfunction (SND, a disruption or failure of a natural pacemaker).

In adults, the researchers found that:

People with viral myocarditis are about 60 times more likely to need a heart transplant. Using milrinone, a vasodilator used to treat heart failure, pushed the risk of a transplant by 175 times. This is the strongest individual predictor of heart transplantation.

In some cases, the aggregate risk is even greater. For example, among patients with cardiomyopathy and taking milrinone, the risk of needing a heart transplant was 405 times higher than in those with healthier hearts.

According to Tristani-Firouzi, comorbidities have significantly different effects on transplant risk in children. Overall, the risk of children receiving a heart transplant is 17 to 102 times higher than that of children without pre-existing heart disease, depending on the underlying diagnosis.

The researchers also examined the effects that a mother’s health during pregnancy had on their children. Women who had high blood pressure during pregnancy were twice as likely to have a baby with a congenital heart defect and circulatory problems. Children with Down syndrome are about three times more likely to have heart defects.

Infants who received Fontan surgery, a procedure to correct a congenital heart defect, were about 20 times more likely to develop an SND arrhythmia than those who did not need surgery.

The researchers also discovered important demographic differences. For example, a Hispanic patient with atrial fibrillation (tachycardia) is twice as likely to develop SND as a Black and White patient, who have similar medical histories.

Josh Bonkowsky, MD Ph.D., director of the Center for Individualized Medicine for Elementary Children, who was not the study’s author, believes the study could lead to the development of a clinical tool practical readiness for patient care.

“This new technology demonstrates that we can estimate risks for medical complications accurately and can even identify better drugs for individual patients.” Bonkowsky said.

In the future, Tristani-Firouzi and Yandell hope their research will also help doctors untangle the growing web of disorienting medical information that surrounds them every day.

“No matter how perceptive you may be, there is no way to keep all the necessary knowledge in your head as a medical professional in this day and age,” says Yandell. Treat the patient in the best possible way. “The computers we are developing will help doctors make the best patient care decisions possible, using all the relevant information available in our electronic age. This machine is very important to the future of medicine.”

Source: Eurekalert

Source link


News7h: Update the world's latest breaking news online of the day, breaking news, politics, society today, international mainstream news .Updated news 24/7: Entertainment, the World everyday world. Hot news, images, video clips that are updated quickly and reliably

Related Articles

Back to top button