Top in cardiology: AI models for heart failure; air pollution and hospitalization risk

Machine learning models were able to identify five distinct heart failure subtypes with predictive accuracy for 1-year mortality, according to a study published in Lancet Digital Health.

"Machine learning can be used in routinely collected data to develop and validate subtypes of diseases, which can be replicated and have clinical value," Amitava Banerjee MBBCh, DPhil, MA, MPH, a professor of clinical data science and honorary consultant cardiologist with the Institute of Health Informatics at University College London, told Healio.

It was the top story in cardiology last week.

Another top story was about data that showed weather patterns and air pollution were associated with acute heart hospitalizations, with interactions becoming increasingly important with age.

Read these and more top stories in cardiology below:

AI models identify five distinct heart failure types, better predicting prognosis

Researchers have identified five distinct heart failure subtypes using machine learning methods across nationally representative datasets that may predict prognosis and ultimately guide treatment plans for patients. Read more.

Weather patterns, air pollution influence risk for heart-related hospitalizations

Modeling data suggest that patterns of temperature, air pressure, precipitation and air pollution assessed over a decade are associated with hospitalizations related to heart failure, myocardial infarction and ischemic stroke, researchers reported. Read more.

AHA: Heart health of American Indian/Alaska Native women often suboptimal

Women who identify as American Indian or Alaska Native are more likely to have type 2 diabetes, to have obesity, to smoke and to report exposure to trauma and violence than white women, significantly increasing their risk for CVD. Read more.

Icosapent ethyl positively impacts coronary physiology on FFR-CT

In statin-treated patients with CAD and elevated triglycerides, icosapent ethyl benefited coronary physiology as assessed by CT-derived fractional flow reserve compared with placebo, according to new data from the EVAPORATE trial. Read more.

New dietary recommendations, dyslipidemia guidelines and more to be featured at NLA 2023

The National Lipid Association Scientific Sessions will spotlight statements on nutrition in adults with dyslipidemia, include sessions on the integration of lipid guidelines in clinical practice and more. Read more.