A Singapore-developed AI tool that measures heart damage from MRI scans is moving toward clinical use, with researchers planning wider hospital testing before seeking regulatory approval. The technology, called CARDIA-GM, achieved more than 90% accuracy for measuring heart-attack-induced muscle scarring and microvascular obstruction volumes, according to its developers at the National Heart Centre Singapore (NHCS).
The tool analyses cardiac MRI scans in under a minute per patient. Manual analysis by experienced researchers typically takes 20 to 30 minutes, said Adjunct Clinical Associate Professor Tan Ru San, a senior consultant at NHCS's Department of Cardiology. Professor Zhong Liang, principal investigator and senior clinician-innovator at the National Heart Research Institute Singapore, said the shorter processing time translates into an 80% to 90% reduction in analysis time.
Validation across hospitals next
NHCS plans to validate the technology at other Singapore hospitals before pursuing clinical licensing. National University Hospital, Changi General Hospital, and Tan Tock Seng Hospital are among the potential sites. Hospitals in China, Malaysia, and Thailand have also expressed interest, Liang said.
"The next 12 to 18 months will focus on testing the technology across a larger and more diverse patient population," Liang said in a call with Tan.
Liang framed the technology as a support tool rather than a replacement for specialists. "Our goal is not to say that AI is better than our specialists," he said. He described CARDIA-GM as a "second pair of eyes" and a "copilot" for cardiologists, with doctors retaining responsibility for final clinical decisions.
Why the measurements matter
Detailed measurement of microvascular obstruction is often impractical in routine clinical settings because it requires significant analysis time and experienced specialists, Tan said. The measurements can help identify patients at higher risk of complications.
Patients with microvascular obstruction exceeding 1.4% of total heart muscle volume face a greater risk of death during follow-up, Liang said. Patients with scarring exceeding 20% have mortality rates three times higher than those below that threshold.
Market context
Pratibha Thammanabhatla, practice head for medical devices at GlobalData Plc, said investment interest in AI imaging continues to grow as healthcare systems face rising rates of cardiac disease and shortages of radiologists and cardiologists. Government grants and research institutions remain the main funding sources for many projects in the region.
"Singapore's CARDIA-GM remains grant-funded and has no disclosed full commercialisation path so far," Thammanabhatla said in an emailed reply to questions.
She said the broader Asian market for AI cardiac diagnostics is expected to expand, though success depends on more than technical performance. Companies that secure regulatory approvals, integrate their products into hospital workflows, and demonstrate measurable clinical benefits are likely to hold the strongest market position. "Singapore therefore has an opportunity to compete through quality and credibility rather than scale," she said.
Why this matters for healthcare professionals
For cardiologists and radiologists, CARDIA-GM signals a shift in how cardiac MRI analysis could fit into routine workflows. If validation across multiple hospitals succeeds, the tool could reduce the time burden of manual measurement while flagging patients whose scarring or microvascular obstruction levels indicate elevated risk. The 12-to-18-month validation timeline also gives hospital departments a window to assess how such tools might integrate with existing imaging protocols before regulatory approval arrives.
Your membership also unlocks:
