AI Improves Accuracy of Cardiac CT Scans, Boosting Treatment for Patients
Cardiac CT scans play a crucial role in detecting blockages or narrowing in the arteries, allowing doctors to provide appropriate treatment for patients. However, these scans have limitations, sometimes failing to pick up small, undetectable narrowings that can lead to fatal heart attacks in the future. To improve the accuracy of these scans, researchers at the University of Oxford turned to artificial intelligence (AI) technology.
The study, funded by the British Heart Foundation (BHF), analyzed the data of over 40,000 patients who underwent routine cardiac CT scans at eight UK hospitals. The researchers discovered that not only were patients with significant narrowing of the arteries more likely to have heart attacks, but twice as many patients with no significant narrowings also experienced heart attacks. This discrepancy highlighted the need for more accurate risk assessments.
To address this issue, the research team developed an AI program that was trained using information on changes in the fat around inflamed arteries, which can indicate the risk of a heart attack. The AI tool was then tested on an additional 3,393 patients over almost eight years. The results were promising, as the software accurately predicted the risk of a heart attack.
AI-generated risk scores were presented to healthcare professionals for 744 patients, resulting in treatment plans being altered for 45% of them. This highlights the potential impact of AI in guiding patient treatment and preventing unnecessary deaths from heart attacks.
Professor Charalambos Antoniades, chairman of cardiovascular medicine at the BHF and director of the acute multidisciplinary imaging and interventional centre at the University of Oxford, stressed the importance of accurate risk assessment: Our study found that some patients presenting in hospital with chest pain – who are often reassured and sent back home – are at high risk of having a heart attack in the next decade, even in the absence of any sign of disease in their heart arteries. Here we demonstrated that providing an accurate picture of risk to clinicians can alter, and potentially improve, the course of treatment for many heart patients.
The potential of AI in healthcare extends beyond improving the accuracy of cardiac CT scans. Professor Sir Nilesh Samani, medical director at the BHF, emphasized the importance of harnessing AI for guiding patient treatment and ensuring that healthcare systems are equipped to support its use. By leveraging AI technology, healthcare professionals can make more informed decisions, ultimately reducing the number of unnecessary heart attack-related deaths.
The study conducted by the University of Oxford and funded by the BHF received support from the National Institute for Health and Care Research Oxford Biomedical Research Centre. With the promising results of this research, there is hope that AI will play a significant role in improving the accuracy of cardiac CT scans and enhancing treatment options for patients with heart conditions.
