A new AI program has been found to identify chronic liver disease from pictures taken during a heart test known as an echocardiogram.
In a press release on 27 February, investigators from a Los Angeles hospital, Cedars-Sinai said the discovery shows the potential of AI models in helping researchers to augment clinical diagnostics at a body-systems level instead of just individual organs.
Making diagnosis easier
The AI program is said to detect chronic liver disease from pictures taken during an echocardiogram, which is the process of using ultrasound to visualize the heart and its associated structures.
The Investigators trained the AI program to study patterns in more than 1.5 million echocardiogram videos.
The program, EchoNet-Liver, detected liver cirrhosis by studying images of the liver picked up during the echocardiograms and the result was found to be similar with diagnoses made using patients’ abdominal ultrasounds or MRI images.
According to Alan Kwan, MD, assistant professor in the Department of Cardiology in the Smidt Heart Institute at Cedars-Sinai, this helps to significantly reduce the cost of diagnosis.
David Ouyang, MD, a cardiologist in the Department of Cardiology in the Smidt Heart Institute, an investigator in the Division of Artificial Intelligence in Medicine, and a senior author of the study also said:
“Our deep-learning model can help doctors spot liver disease that might have gone unnoticed and thus direct appropriate follow-up testing.”
AI in medicine
AI has found several applications in medicine in recent years. One of the most recent is its application in predicting the cause of brain injury in forensics.
Another is its use in eye surgery to increase precision so the risk of injury is reduced during such delicate surgeries.
As time advances, there will likely be many more discoveries in AI that will help in development of medicine and human health.
ReadNext
