A groundbreaking artificial intelligence (AI) model, developed through a collaborative effort by researchers from the University of British Columbia (UBC) Okanagan and BC Cancer – Kelowna, is set to transform how cardiovascular disease risks are identified in breast cancer patients. Announced on June 2, 2026, this new tool utilizes existing chest CT scans, routinely performed for radiation therapy planning, to detect early indicators of heart health issues.
The initiative addresses a critical concern for breast cancer patients, who are at a higher risk of experiencing cardiovascular complications compared to the general population. This elevated risk can stem from certain cancer treatments. Dr. Mohammad Shehata, a professor in the Irving K. Barber Faculty of Science’s computer science department at UBC Okanagan, emphasized the model's potential. "Breast cancer patients already face immense challenges. Cardiovascular disease is a critical and often overlooked health threat they endure," Dr. Shehata stated. "The model we have created gives clinicians a new tool to proactively identify those patients who are at high-risk of developing cardiovascular disease, allowing them to intervene earlier and potentially save lives."
Traditionally, cardiovascular risk assessments rely on clinical data such as age, hypertension, and diabetes symptoms. The new AI model, however, integrates both CT imaging and clinical health records, including a patient's general health, age, hypertension, diabetes, and family history. This multimodal approach allows it to identify subtle structural changes in the heart from CT scans, alongside systemic risk factors, offering a more precise and personalized risk assessment.
Dr. Rasika Rajapakshe, study co-lead, clinical associate professor of surgery in UBC’s Faculty of Medicine, and senior medical physicist at BC Cancer – Kelowna, highlighted the efficiency of this method. "This research marks a significant step forward in how we assess cardiovascular risk in breast cancer patients," said Dr. Rajapakshe. "By combining routinely collected CT imaging with clinical health records, we can detect risk earlier and more accurately than ever before—without adding extra burden to patients or the health-care system."
Published in 'Radiotherapy and Oncology', the research showcases the model's outstanding predictive accuracy, significantly outperforming existing methods. The team notes that this level of precision could enable early identification of high-risk patients during their cancer treatment, facilitating tailored interventions and care. This non-invasive, clinically valuable tool holds promise for improving survival outcomes by allowing for timely intervention against cardiovascular-related mortality.
The BC Cancer Foundation has provided support for this crucial research, underscoring a broader commitment to enhancing long-term health management for cancer survivors in British Columbia.