Hamilton hospital introduces AI tool to reduce unnecessary cardiac procedures

November 21, 2026 - 05:15
 0  0
Hamilton hospital introduces AI tool to reduce unnecessary cardiac procedures

Canadian-developed technology is now being used in routine care at Hamilton General Hospital to help cardiologists select the most appropriate diagnostic tests for patients.

Hamilton Health Sciences (HHS) has introduced a new artificial intelligence tool into routine clinical care that could help reduce unnecessary invasive cardiac procedures while improving how patients with suspected coronary artery disease are assessed.

Known as CarDIA-AI, the technology uses machine learning to analyze patient information and help cardiologists determine whether an invasive coronary angiogram or a non-invasive coronary CT scan is the more appropriate diagnostic test.

The tool began routine clinical use at Hamilton General Hospital’s Heart Investigation Unit in early October 2026, making HHS the first hospital in Canada to implement CarDIA-AI in everyday cardiac care.

Improving cardiac testing decisions

Coronary artery disease occurs when arteries supplying blood to the heart become narrowed or blocked, potentially causing chest pain, heart attacks and other cardiovascular complications.

Patients suspected of having the condition are frequently referred for coronary angiography, an invasive procedure involving a catheter inserted through an artery to examine blood flow to the heart.

However, many angiograms reveal no significant blockages. For some patients, a non-invasive CT scan could provide sufficient diagnostic information without requiring catheterization.

CarDIA-AI analyzes patient data to estimate the likelihood of significant coronary artery disease, helping clinicians identify which patients are most likely to benefit from angiography.

The technology supports clinical decisions rather than replacing physician judgment.

Clinical trial demonstrates promising results

In a randomized controlled trial evaluating the technology, researchers compared conventional cardiac testing with an AI-guided approach.

Among patients who underwent coronary angiography, approximately 61 per cent in the usual-care group had no significant coronary blockages.

In the CarDIA-AI group, that proportion fell to approximately 24 per cent.

The findings suggest the technology can help clinicians better identify patients who require invasive testing while directing others toward less invasive diagnostic options.

Importantly, the percentages refer specifically to patients who underwent angiography in each study group, rather than all patients assessed.

Reducing unnecessary angiograms could also lower healthcare costs and limit patients’ exposure to procedural risks.

Developed using Canadian patient data

CarDIA-AI was developed through collaboration between HHS cardiologists, researchers and the hospital’s Centre for Data Science and Digital Health, known as CREATE.

Researchers initially trained the machine-learning model using 12 years of referral data from nearly 30,000 cardiac patients treated at Hamilton General Hospital and Niagara Health’s St. Catharines Hospital.

The model was subsequently evaluated using information from 22 cardiac centres across Ontario to assess its broader applicability.

Early modelling indicated that the proportion of patients referred for angiography who might have been able to avoid the invasive procedure decreased from 44 per cent to 14 per cent when the technology was used to guide assessment.

The hospital also reported comparable model performance for women and men.

From research to routine patient care

Dr. JD Schwalm, an interventional cardiologist at Hamilton General Hospital and director of the HHS Knowledge Centre, played a leading role in developing the technology.

The project builds on earlier research examining how expert clinical review could improve decisions about cardiac diagnostic testing.

By using machine learning to support those decisions, CarDIA-AI aims to make the process more efficient and scalable.

Following several years of development, evaluation and implementation planning, the system is now integrated into routine clinical workflows at Hamilton General Hospital.

HHS believes the technology has potential for wider adoption across Ontario and Canada.

The initiative demonstrates how hospital-developed artificial intelligence can move beyond research into practical clinical applications, supporting more personalized care while helping healthcare systems make better use of diagnostic resources.

The post Hamilton hospital introduces AI tool to reduce unnecessary cardiac procedures appeared first on Hospital News.

Apa Reaksi Anda?

Suka Suka 0
Kurang Suka Kurang Suka 0
Setuju Setuju 0
Tidak Setuju Tidak Setuju 0
Bagus  Bagus 0
Berguna Berguna 0
Hebat Hebat 0
Edusehat Platform Edukasi Online Untuk Komunitas Kesehatan Agar Mendapatkan Informasi Dan Pengetahuan Terbaru Tentang Kesehatan Dari Nasional Maupun Internasional. || An online education platform for the health community to obtain the latest information and knowledge about health from both national and international sources.