A new study showed that artificial intelligence is faster, more accurate and more efficient than board-certified echo-cardiographers at reading and analyzing heart ultrasound scan.
According to CNET.com website, the study was conducted by researchers from the University of California, San Francisco, the University of California, Berkeley, and Beth Israel Deaconess Medical Center.
Researchers trained a computer to assess the most common echocardiogram (echo) views using more than 180,000 echo images. They then tested both the computer and trained doctor on new samples. The computers were 91.7 to 97.8 percent accurate at assessing echo videos, while humans were only accurate 70.2 to 83.5 percent of the time, reported AFP.
Senior author Dr. Rima Arnaout, a cardiologist at UCSF Medical Center and an assistant professor at the UCSF School of Medicine, said that these results are a foundational step for analyzing echocardiograms.
Interpreting echocardiograms can be complex. They consist of several video clips, still images and heart recordings measured from more than a dozen views. There may be only slight differences between some views, making it difficult for humans to offer accurate and standardized analyses.
The study suggested that artificial intelligence techniques could be more useful, and better computer setup ensures better results in the analysis of echocardiography, with the potential to benefit from this technology in the diagnosis of more diseases based on the analysis of echo videos in other medical fields.
Researchers at Stanford University published a study last year showing that AI-powered computers can also be used in diagnosing skin cancer.