A recent study conducted by researchers at the University of East Anglia’s Norwich Medical School has revealed a groundbreaking artificial intelligence (AI) model that significantly speeds up heart scan diagnoses. The AI model, developed by lead investigator Pankaj Garg, MD, PhD, and his team, has the potential to revolutionize cardiac care by saving doctors’ time, improving patient outcomes, and ultimately saving lives.
The study, a multicenter, multivendor, and retrospective observational analysis, aimed to train and develop a deep learning AI model specifically designed to examine heart scans, focusing on the 4-chamber cine. This cardiac magnetic resonance (CMR) technique provides detailed insights into the heart’s volumetrics.
Using data from 814 participants, the AI model was trained and validated using scans from two studies: the ASPIRE register from Sheffield Teaching Hospital and Leeds Teaching Hospitals NHS Trust. An independent cohort of 101 patients from the PREFER-CMR register in Norfolk and Norwich University Hospitals was also included for validation and mortality prediction.
The results of the study demonstrated that the AI model accurately determined the size and function of the heart’s chambers, comparable to manual analyses performed by doctors but in a fraction of the time. The left and right heart measurements taken by the automated AI methods closely matched those taken manually, showing strong correlations. However, the automated method initially underestimated the volumes of the ventricles, which was later corrected with adjustment factors.
During an average follow-up period of 6.75 years, the study found that a specific measure of heart function, the left atrial ejection fraction, was independently linked to the risk of mortality in both manual and AI analyses. This highlights the potential of AI to predict mortality based on heart measurements, offering an efficient and accurate prognostic tool for identifying heart issues.
Lead investigator Pankaj Garg emphasized the time-saving benefits of the AI model, stating that it takes only a few seconds to analyze heart scans compared to the standard manual MRI analysis, which can take up to 45 minutes. This automation not only saves time and resources but also ensures consistent results for doctors.
PhD student Hosamadin Assadi, who was involved in the study, expressed optimism about the potential impact of AI in cardiac care. He believes that automating the process of assessing heart function and structure could lead to more efficient diagnoses, better treatment decisions, and ultimately improved outcomes for patients with heart conditions.
The development of this AI model represents a significant advancement in medical technology, with the potential to transform the field of cardiology. By harnessing the power of AI, doctors can expedite heart scan diagnoses, leading to more timely interventions and improved patient prognosis.
Overall, this study showcases the promising role of AI in healthcare, particularly in the field of cardiology, and highlights the potential for AI to revolutionize cardiac care and improve patient outcomes.
References:
Assadi, H., Alabed, S., Li, R. et al. Development and validation of AI-derived segmentation of four-chamber cine cardiac magnetic resonance. Eur Radiol Exp 8, 77 (2024). https://doi.org/10.1186/s41747-024-00477-7