AHA Issues Statement on the Use of AI in Cardiovascular Care

The American Heart Association (AHA) released a scientific statement in Circulation this week detailing the current state of artificial intelligence (AI) use in the diagnosis and treatment of cardiovascular disease.

The statement is the first of its kind from the AHA, underscoring continued interest from healthcare organizations in how AI could potentially transform the industry. The report outlined limitations of these technologies, potential applications, challenges, and how AI may be deployed safely and effectively.

“Here, we present the state-of-the-art including the latest science regarding specific AI uses—from imaging and wearables to electrocardiography and genetics,” said the chair of the statement’s writing committee Antonis Armoundas, PhD, a principal investigator at the Cardiovascular Research Center at Massachusetts General Hospital and an associate professor of medicine at Harvard Medical School, in a press release. “Among the objectives of this manuscript is to identify best practices as well as gaps and challenges that may improve the applicability of AI tools in each area.”

Multiple factors limiting the use of AI in cardiovascular care were described: lack of protocols for appropriate information sourcing and sharing; legal and ethical hurdles; the need to grow the scientific knowledge base around these technologies; and the absence of robust regulatory pathways, among others.

“Robust prospective clinical validation in large diverse populations that minimizes various forms of bias is essential to address uncertainties and bestow trust, which, in turn, will help to increase clinical acceptance and adoption,” Armoundas noted.

The statement also reviewed potential cardiovascular applications for AI tools, some of which are already in use.

AI and machine learning have significant potential to improve medical imaging, but challenges abound. The AHA’s statement emphasized that using these tools for image interpretation is difficult due to a lack of representative, high-quality datasets, and further indicated that these technologies need to be validated in each potential use case prior to deployment.

AI could also be useful in interpreting information from implants, wearables, electrocardiograms, and genetic data.

“Numerous applications already exist where AI/machine learning-based digital tools can improve screening, extract insights into what factors improve an individual patient’s health and develop precision treatments for complex health conditions,” said Armoundas.

The statement also asserted that education and research are crucial to making good on the promise of healthcare AI.

“There is an urgent need to develop programs that will accelerate the education of the science behind AI/machine learning tools, thus accelerating the adoption and creation of manageable, cost-effective, automated processes. We need more AI/machine learning-based precision medicine tools to help address core unmet needs in medicine that can subsequently be tested in robust clinical trials,” Armoundas continued. “This process must organically incorporate the need to avoid bias and maximize generalizability of findings in order to avoid perpetuating existing health care inequities.” 

The AHA is the latest national healthcare stakeholder to weigh in on how AI should be implemented across the industry.

This week, the American Medical Association (AMA) and Manatt Health published “The Emerging Landscape of Augmented Intelligence in Health Care” report, which outlines key terms, potential use cases, and risks associated with these tools.

The report explored both clinical and administrative applications for AI in an effort to assist clinicians as they navigate the implementation of the technology.

Alongside opportunities and risks, the AMA also laid out critical questions that healthcare organizations should be asking themselves as they consider adopting AI and other advanced analytics tools.