Singapore Scientists Integrate AI Tools To Improve Diagnosis of Heart Disease

Singapore is a hotbed of AI innovation. 80 of the world’s top 100 technology companies have a strong presence in Singapore enabling innovation and accelerating adoption of AI. This month, a team of leading physicians, AI scientists, and tech experts at the Agency for Science, Technology and Research (A*STAR), National Heart Centre Singapore (NHCS), National University Health System (NUHS) and Tan Tock Seng Hospital (TTSH) announced the development of a new AI platform called APOLLO (AI-driven national Platform for CT cOronary angiography for clinicaL and industriaL applicatiOns) to help doctors improve diagnosis and treatment of cardiovascular disease.

The APOLLO platform integrates several AI toolkits that analyze Computed Tomography Coronary Angiography (CTCA) scans into clinical workflow. By integrating AI toolkits with diagnostic and prognostic capabilities, the platform enables them to work functionally together to provide automated anonymization, reporting, calcium scoring, epicardial fat, coronary stenosis and plaque quantification. This is a really practical step forward because the AI tools are integrated into one platform so it's much more efficient for doctors.

The AI tools that are integrated on the APOLLO platform were developed by A*STAR scientists at?Bioinformatics Institute (BII), Institute for Infocomm Research (I2R), and the Institute of High Performance Computing (IHPC) in Singapore.

APOLLO Team

Collaborations

The APOLLO team is interested in expanding industry collaborations. If you are interested in collaborating on the APOLLO project please contact the team at?[email protected]

Coronary Artery Disease

Coronary artery disease (CVD) is the world’s number one killer. Over 18 million people die every year from CVD. It affects 20% of people over 65 years of age and causes 33% of deaths globally. The number of coronary artery disease cases is growing due to population aging and increasing prevalence of diabetes.

Computed tomography (CT) is the first line of investigation for coronary artery disease. This is?an imaging test that helps determine if plaque buildup has narrowed the coronary arteries that supply blood to the heart. Plaque (composed of fat, cholesterol, and calcium) builds up over time on the inner lining of the arteries.?This can reduce, and in some cases, completely block blood flow to the heart.

The Traditional Method

• CT report generation currently requires 2-4 hours of CT specialists’ time depending on complexity.
• There is no efficient toolbox to analyze calcium score, epicardial fat, and severity of coronary stenosis and plaque characteristics.
• Current imaging biomarkers are fragmented and operating in silos.
• These problems have constrained the cost effectiveness of CT as a diagnostic tool.?

New AI-Based Approach

The new APOLLO platform allows accurate assessment of plaque burden in coronary artery disease and shortens the processing time for image analysis and diagnosis. The scientists are building a large sharable, de-identified, PDPA compliant curated digital warehouse of CT real-world data from 3 hospitals in Singapore. The integrated APOLLO AI platform will be used for anonymization and reporting of coronary calcium, epicardial fat, stenosis and plaque quantification in large scale clinical trials.

The APOLLO team will assess usability and workflow integration and the ability to provide a rapid assessment of patients’ conditions using AI solutions. The team plans to test the AI toolkits in several different hospitals and in clinical trials.?The platform can provide objective and consistent clinical trial end-point measurements at a cheaper cost. In return, this will increase the probability of success and reduce timelines in drug discovery and development.

Benefits of Using AI

• AI improves productivity and optimizes the healthcare workforce and resources.
• Using AI this analysis can be completed in 10 minutes - more than 10 times faster than the traditional approach.
• AI reduces variability in reporting.
• AI assists clinicians in objectively interpreting CT images, diagnosing and monitoring the severity of disease and treatment response.
• AI provides greater depth of detail.
• AI provides physicians with unprecedented insights into a patient’s condition to effectively provide personalized care and early intervention; this could delay disease onset and prevent adverse events.

4 AI modules

The APOLLO platform consists of four AI modules each of which performs a different AI analyses of CT images to detect high-risk plaque and risk-stratify patients.?

1. AI Calcium Score allows for the quantification of calcium score, volumetric score and detection of calcified vessels.
2. AI EAT allows for the quantification of total volume of epicardial fat and density.
3. AI Stenosis allows for the quantification of stenosis severity and detection of stenosis location.
4. AI Plaque allows the quantification of plaque volume and characterization of plaque type, and the number of plaques.

Alleviating Burden to the Healthcare System

This AI-enabled coronary CT angiography can significantly alleviate the burden to the healthcare system.?

• APOLLO is used by hospitals and physicians to identify, characterize, and quantify coronary calcium, epicardial fat, stenosis, and plaque. This helps clinicians determine a patient’s risk of a future heart attack. The platform implementation includes a one-time setup fee, followed by a yearly subscription fee.
• APOLLO is used as an objective quantitative tool in clinical trials to test the effectiveness of drugs and treatments. For example, pharmaceuticals can develop and choose from a range of medications and determine if they inhibit build-up of plaque, prevent atherosclerosis, and reduce the risk of heart attacks.
• APOLLO will be used to anchor the medical technology industry in Singapore through collaborations in technical development via service agreement on a per-contract basis.?

Current Industry Partners

Collaborations

The APOLLO team is interested in expanding industry collaborations. If you are interested in collaborating on the APOLLO project please contact the team at?[email protected]

Subscribe, Comment, Join Group

I'm interested in your feedback - please leave your comments.

To subscribe to the AI in Healthcare Milestones newsletter please click here.

To join the AI in Healthcare Milestones Group please click here.

Copyright ? 2022 Margaretta Colangelo. All Rights Reserved.

This article was written by Margaretta Colangelo. Margaretta is a leading AI analyst who tracks significant milestones in AI in healthcare. She consults with AI healthcare companies and writes about some of the companies she consults with. Margaretta serves on the advisory board of the AI Precision Health Institute at the University of Hawai?i?Cancer Center @realmargaretta