AI Tool Predicts Heart-Related Death Risks, Enhancing Early Detection
University of Leeds researchers develop AI system to identify patients at high risk of heart-related deaths. The tool, trained on 2 million health records, aims to improve early diagnosis and treatment of cardiovascular conditions.
Researchers at the University of Leeds have developed an innovative artificial intelligence (AI) tool designed to identify individuals at high risk of heart-related deaths. This groundbreaking study marks a significant advancement in the application of AI to healthcare, particularly in the realm of cardiovascular disease prevention.
The AI system, named OPTIMISE, was trained using health records from over 2 million patients. Through this extensive dataset, the tool successfully identified more than 400,000 individuals at the highest risk of dying from heart-related conditions, including kidney failure and diabetes. Remarkably, this high-risk group accounted for nearly three-quarters of heart-related deaths over the subsequent decade.
To validate the AI's effectiveness, scientists conducted a test on 82 high-risk patients identified by the system. The results were striking: one in five of these individuals were diagnosed with previously undetected kidney disease, while half of those found to have high blood pressure received adjusted medication to better manage their risk of premature death.
The significance of this research becomes apparent when considering that approximately 80% of people with heart and circulatory diseases have at least one other health condition, significantly increasing their mortality risk. Early detection of these cases is crucial for prescribing appropriate medication and treatment.
Prof Chris P Gale, a consultant cardiologist at Leeds Teaching Hospitals NHS Trust and University of Leeds, and Dr Ramesh Nadarajah, a health data research UK fellow at the University of Leeds, led this groundbreaking study. Their findings revealed that many patients had undiagnosed conditions or were not receiving optimal medication to reduce their risk.
The OPTIMISE tool demonstrated superior capabilities in identifying high-risk patients at an earlier stage and with greater accuracy than existing methods. This advancement could lead to improved management of risk factors, potentially preventing conditions from worsening and reducing the likelihood of heart-related deaths.
Dr Nadarajah emphasized the multifaceted nature of heart-related deaths, stating:
"Heart-related deaths are often caused by a constellation of factors. This AI uses readily available data to gather new insights that could help healthcare professionals ensure that they are providing timely care for their patients."
The research team is optimistic about the potential impact of their work, hoping it will benefit patients living with heart and circulatory diseases while also alleviating pressure on NHS systems. They plan to conduct a clinical trial involving doctor-led care for patients identified by the AI tool.
Looking ahead, the researchers anticipate that the OPTIMISE tool could be implemented in GP practices within two years, enabling healthcare providers to identify high-risk patients efficiently.
Prof Bryan Williams, chief scientific and medical officer at the British Heart Foundation, praised the study, highlighting its potential to harness AI technology for detecting the multiple conditions contributing to heart-related deaths. He emphasized the importance of early diagnosis in reducing hospital admissions and heart-related fatalities, ultimately allowing people to live longer, healthier lives.
As AI continues to revolutionize healthcare, this research represents a significant step forward in the fight against cardiovascular diseases, offering hope for improved patient outcomes and more efficient healthcare delivery.
