According to a study, artificial intelligence could help detect people at risk of heart failure. Researchers from the University of Dundee’s School of Medicine have used artificial intelligence to improve the diagnosis and control of heart failure at an early stage.
Also Read: European Court of Auditors Criticize EU for Failing to Coordinate AI Investments
The researchers applied artificial intelligence via machine learning techniques in the analysis of echocardiographic images of thousands of patients to detect small signs of heart problems that lead to heart failure. This could greatly enhance diagnostic efficacy and benefit patients in the healthcare industry.
Researchers Use AI To Visualize Patterns in the Heart Shape
To achieve this, the research team, led by Prof Chim Lang, used trial artificial intelligence deep learning approaches to read and analyze echocardiographic images gathered from population-based electronic health records and cardiac scans. This allowed them to visualize patterns in the heart shape and function that may put a patient at higher risk for developing heart failure.
AI could be used to detect heart failure risk, study finds.https://t.co/TkUuruMLMs
— STV News (@STVNews) May 30, 2024
The researchers used data voluntarily provided by patients from the Scottish Health Research Register and Biobank (SHARE). They initially selected a dataset of 15,000 patient records, from which the final sample of 578 patients was derived.
AI Heart Scans Are More Precise
The heart scans that were done with the help of artificial intelligence provided measurements relatively more precise than the conventional ones. According to Professor Chim Lang who spearheaded the study, the AI software offered more features of heart structure and function important in the diagnosis of heart failure.
“Our research represents an advancement in the utilization of deep learning to interpret echocardiographic images automatically. This can allow us to streamline the identification of patients with heart failure at scale within electronic health record datasets.”
Professor Lang
The AI-enhanced echocardiographic images offered better-defined size and functions of the heart than the average scans retrieved from EHR data settings. This level of detail, along with the ability to process images at a larger scale, might expedite patient selection in clinical trials or help in the supervisory monitoring of heart failure across healthcare systems.
Also Read: Opera Integrates Google’s Gemini Models to Enhance Aria Browser AI
Heart failure remains a common clinical and public health problem. It is a state in which the heart can no longer pump sufficient blood to the rest of the body. There is no cure for the condition, but changes in lifestyle, surgery, and medicine can help control the symptoms and progression of the disease, which usually progresses with time.
Using the patient records, the researchers utilized machine learning to identify structural and functional anomalies that would be hard to notice from the echocardiographic image analysis alone.
AI Detects Anomalies Not Traceable With Traditional Analysis
In an interview, Professor Lang stated that the study holds a lot of potential in enhancing patients’ lives. He mentioned that based on the assessment of hallmark patient records, the team was able to detect morphologic and mechanistic abnormalities that would not have been seen on standard two-dimensional echocardiographic images.
“By assessing vast amounts of patient records, we have been able to detect structural and functional anomalies that we would not have been able to do with traditional analysis of echocardiographic images.”
Professor Lang
The study published in the ESC Heart Failure Journal highlights AI’s ability to change healthcare by helping in the early diagnosis of these challenging disorders. As stated, with the help of software developer Us2 and funding from ROCH Diagnostics International, the research opens the way for further exploration of AI applications in predictive diagnostics and personalized treatment.
Cryptopolitan reporting by Chris Murithi
