In a significant advancement in cardiovascular healthcare, a new artificial intelligence (AI) system known as the Singapore Heart Lesion Analyzer (Sense) is set to undergo a year-long clinical trial starting in the third quarter of 2025. This trial will be conducted at three prominent medical facilities in Singapore: National Heart Centre Singapore (NHCS), National University Hospital (NUH), and Tan Tock Seng Hospital (TTSH).

Transforming Diagnosis with Speed and Precision

Sense is specifically designed to revolutionize the detection of coronary artery disease (CAD), which is the leading cause of heart-related fatalities in Singapore. Unlike conventional methods that can take several hours for scan analysis, Sense aims to provide results in less than ten minutes. This significant enhancement in speed has the potential to reduce waiting times, expedite treatment decisions, and ultimately save lives.

In controlled settings, Sense has demonstrated accuracy rates ranging from 85 to 99 per cent. The upcoming trial will evaluate whether the system can maintain such performance in real-world clinical scenarios.

How Sense Works: Behind the Technology

The Sense AI system utilizes deep learning algorithms to analyze CT scans and measure various key indicators of heart disease, including coronary calcium levels, fat deposits around the heart (epicardial adipose tissue), degree of artery narrowing (stenosis), and types and sizes of plaque formations. These metrics are then processed into a comprehensive risk report for doctors to review, significantly reducing the time required for interpretation without compromising diagnostic accuracy.

Trial Design and Patient Participation

The clinical trial will involve around 300 patients across the three hospitals. Over a 12-month period, the trial will assess how well Sense performs under typical hospital conditions. It is important to note that while the system accelerates analysis, clinical decision-making remains the responsibility of physicians. The AI serves as a supportive tool, not a substitute for medical expertise.

Built on a National Imaging Database

Sense was developed by the CardioVascular Systems Imaging and AI (CVS.AI) lab at NHCS in collaboration with researchers from A*STAR. The system is powered by a national CT coronary angiography database named APOLLO, which contains over three million images from approximately five thousand patients. The CVS.AI lab now operates from a 164-square-metre facility equipped with advanced computing hardware, facilitating rapid image processing and further advancement of AI healthcare solutions.

Addressing a National Health Crisis

Coronary artery disease continues to be a major cause of mortality in Singapore, accounting for more than 8,300 cardiovascular-related deaths in 2023 alone. Early detection is crucial for improving outcomes, and AI tools like Sense could significantly enhance the speed and accuracy of diagnoses. Globally, over 250 million individuals suffer from CAD, with the disease causing nearly nine million deaths in 2021. Singapore's investment in AI technology demonstrates a proactive approach to combatting this global challenge.

National and Global Implications

• Healthcare efficiency: Sense has the potential to optimize clinical resources and alleviate bottlenecks in patient diagnosis.
• Standardized assessments: AI can ensure consistent evaluations across hospitals and minimize human variability.
• Early intervention: Rapid analysis enables prompt treatment, potentially reducing long-term healthcare expenses and enhancing survival rates.