Representational image of a human heart. Mohammed Haneefa Nizamudeen/istock
Researchers at Case Western Reserve University, University Hospitals, and Houston Methodist are embarking on a groundbreaking initiative to harness artificial intelligence (AI) for predicting heart failure and other cardiovascular events with unprecedented accuracy.
Their efforts aim to estimate not only the likelihood but also the timing of such adverse events by developing an AI model that “learns” from patient scans.
Cardiovascular disease claims over 17 million lives annually worldwide, making it the leading cause of death, according to the American Heart Association.
Despite the widespread impact, accurately identifying individuals at high risk remains a critical challenge.
AI to spot heart attacks
The new project seeks to bridge this gap by leveraging advanced AI tools to analyze calcium-scoring computed tomography (CT) scans, which are commonly used to detect arterial plaque.
Beyond measuring plaque, these scans also capture valuable information about the aorta, heart shape, lungs, muscles, and liver, providing a wealth of data for AI analysis.
The initiative has received $4 million in funding through two grants awarded by the National Institutes of Health, underscoring the project’s potential to transform cardiovascular care.
“This project represents a significant leap forward in personalized healthcare,” said Shuo Li, project leader and professor of biomedical engineering and computer sciences at Case Western Reserve.
“It has the potential to set new standards for cardiovascular disease prevention and management, as well as advance the forefront of using AI to analyze images for transformational healthcare.”
The project will create AI-driven predictive models that interpret combined data from CT scans, clinical risk factors, and demographic information.
By doing so, the team, led by Li and Sadeer Al-Kindi, an imaging cardiologist at Houston Methodist DeBakey Heart and Vascular Center, hopes to uncover critical insights into the interplay between heart health and body composition.
“Accurate risk prediction allows us to tailor preventative treatments, reducing the burden of cardiovascular diseases and improving patient outcomes,” said Al-Kindi.
“By identifying risks early, this project can potentially redefine care protocols, save lives, and lower healthcare costs.”
Integrating AI into clinical workflows
Using existing screening CT data from Houston Methodist and University Hospitals, the research highlights AI’s potential to address longstanding clinical challenges in a scalable and cost-effective manner.
The calcium-scoring CT, a low-cost, non-invasive scan, already identifies calcified plaque in coronary arteries.
The AI model, however, will go further by analyzing additional factors like heart shape, body composition, bone density, and visceral fat, alongside age and other demographics.
“Our goal is to develop a non-invasive, accurate, and personalized method for predicting cardiovascular disease risk,” Li explained.
“This innovation will seamlessly integrate into existing clinical workflows, enhancing decision-making while minimizing the need for invasive diagnostic procedures.”
The research team also includes David Wilson, the Robert Herbold Professor of biomedical engineering and radiology, Pingfu Fu, professor of biostatistics, and Sanjay Rajagopalan, director of the Cardiovascular Research Institute at Case Western Reserve.
RECOMMENDED ARTICLES
Rajagopalan highlighted the broader implications: “A clearer understanding of these novel imaging-based risk factors will advance the knowledge of cardiometabolic disease phenotypes and support doctors in making timely therapeutic recommendations.”
This initiative represents a critical advancement in the fight against cardiovascular disease.
By integrating AI into routine diagnostics, the project not only aims to improve patient outcomes but also lays the groundwork for more personalized, efficient, and effective healthcare systems.
If successful, this approach could redefine how clinicians predict and manage cardiovascular risks, saving countless lives worldwide.
