NuraLogix, a pioneer in contactless health insight technology, announced its latest research capability today, a multi-year cardiovascular disease (CVD) risk model, a breakthrough capability that estimates an individual’s long-term likelihood of developing cardiovascular disease over customizable timeframes ranging from 1 to 20 years. CVD risk refers to the likelihood of developing conditions such as heart attack, stroke, or peripheral artery disease, and serves as a key indicator for understanding and supporting long-term heart health.
Building on its existing 10-year cardiovascular model, the new multi-year version offers greater flexibility and long-range forecast, enabling health technology partners, wellness platforms, and research organizations to better understand population-level risk trajectories and explore the long-term impacts of wellness and lifestyle factors, all through a contactless, camera-based experience.
Cardiovascular disease remains the #1 cause of death globally, responsible for nearly 18 million lives each year. According to the World Health Organization, over 80% of these deaths are due to heart attacks and strokes, with one-third occurring prematurely in people under 70.1 While most discussions in healthcare focus on treatment, the true frontier lies in early detection and continuous risk awareness.
The new NuraLogix model was trained on data from over 100,000 individuals across diverse populations, creating a more globally representative dataset than previous U.S.-focused versions. Unlike traditional regression-based approaches, it uses advanced machine-learning techniques to adaptively capture complex physiological patterns applicable across regions and demographics.
“Cardiovascular disease doesn’t develop overnight,” said Dr. Keith Thompson, Chief Medical Officer at NuraLogix. “By extending our predictive horizon to 20 years, this capability provides valuable insight into how lifestyle and wellness factors could influence long-term cardiovascular health. It empowers users and organizations to make data-informed decisions that support prevention and early intervention. “