Artificial intelligence (AI) has the potential to save thousands of lives by detecting individuals at risk of a heart attack up to ten years in advance, according to a major study led by Oxford University. Conventional scans often miss warning signs that AI technology can identify, leading to more accurate predictions and earlier interventions. The study, which analyzed data from over 40,000 patients who underwent routine cardiac CT scans in eight UK hospitals, revealed that individuals with significant narrowing of the arteries were more likely to have a serious heart attack. Surprisingly, twice as many patients with no significant narrowing also experienced heart attacks. By using a new AI tool trained to detect changes in the fat around inflamed arteries, researchers were able to accurately predict the risk of cardiac events in additional testing on 3,393 patients over several years.
In a world-first pilot presented at the American Heart Association’s Scientific Sessions, clinicians received AI-generated risk scores for 744 patients. The results showed that in up to 45% of cases, physicians altered the patients’ treatment plans based on the AI predictions. Professor Charalambos Antoniades from the University of Oxford emphasized the potential of AI in improving treatment for heart patients, especially those who display no signs of heart artery disease but are still at high risk of a heart attack in the next decade. Professor Sir Nilesh Samani, medical director at the British Heart Foundation, hailed the study as a demonstration of the valuable role AI can play in identifying individuals at risk and potentially saving thousands of lives each year.
The findings come as the National Health Service (NHS) in the UK launches various pilot schemes aimed at preventing hospital admissions this winter, utilizing AI technology. In Buckinghamshire, one initiative tracks the eating and drinking habits of frail individuals in their homes to identify potential health issues and prevent hospitalizations. Electronic sensors placed on kettles and fridges monitor consumption patterns and notify a care team of any concerning changes. In Birmingham, NHS teams are testing an algorithm that predicts the top 5% of patients at risk of hospital attendance or admission, allowing staff to offer necessary social care measures. The goal of these initiatives is to reduce unnecessary emergency room visits and overnight stays, as well as lower the number of GP appointments.
Amanda Pritchard, the head of NHS England, expressed the hope that AI technology can help identify the most vulnerable patients and reduce avoidable A&E attendances. These advancements in AI-based risk detection and prevention hold great promise for the healthcare industry. The ability to accurately predict heart attack risk up to ten years in advance means that more lives can be saved through early interventions and tailored treatment plans. By harnessing the power of AI, healthcare professionals can make more informed decisions, leading to improved patient outcomes and a significant reduction in heart attack cases.
