Sunday, May 8, 2016

Artificial intelligence beating humans in detecting illness

    According to a recent report in Kurzweil Accelerating Intelligence, Samsung Medison has updated its RS80A ultrasound-imaging machine with a feature called S-Detect for Breast that analyzes breast lesions. The system uses big data collected from breast-exam cases and suggests whether the lesion is benign or malignant.

Source: QMED

     "We saw a high level of conformity from analyzing and detecting lesion in various cases by using the S-Detect," said professor Han Boo Kyung, a radiologist at Samsung Medical Center. "Users can reduce taking unnecessary biopsies and doctors-in-training will likely have more reliable support in accurately detecting malignant and suspicious lesions."

   Researchers at the Regenstrief Institute and Indiana University School of Informatics have also noticed that computers are better than humans in detecting cancer. According to their research, existing algorithms and open-source, machine-learning tools are as good or even better than human when detecting cancer cases using data from free-text pathology reports. The electronic approach was also faster and used fewer resources than people, according to Regenstreif.

    "We think that it’s no longer necessary for humans to spend time reviewing text reports to determine if cancer is present or not," said author Shaun Grannis, MD, interim center director. "We have come to the point in time that technology can handle this. A human's time is better spent helping other humans by providing them with better clinical care."

No comments:

Post a Comment