Dear Ultrasound Insider,
Machine learning might one day be able to tell which breast cancer patients will benefit from additional genetic testing. In a recent study, researchers used natural language processing to identify key features from ultrasound reports associated with cancer recurrence risk. Read more in this edition's Insider Exclusive.
Relatedly, ultrasound may be able to help predict metastases in endometrial cancer patients. Researchers found that ultrasound in combination with endometrial biopsy results and clinical characteristics allowed clinicians to predict the risk of lymph node metastases in endometrial cancer patients before surgery. The model they used was better than risk stratification alone.
Also new in the Ultrasound Community, imaging tools, including ultrasound, may be able to predict which infants have long-term risks from the Zika virus. Infants exposed to the Zika virus in utero but who appear normal at birth may be at a greater risk of neurodevelopmental delays if they have mild, nonspecific findings on cranial ultrasounds.
Late last year, the U.S. Preventive Services Task Force reaffirmed with no major changes its 2014 recommendations on using ultrasound to screen for asymptomatic abdominal aortic aneurysm. The recommendations include a one-time screening for male ever-smokers ages 65 to 75 (B grade) and selective screening for male nonsmokers ages 65 to 75 (C grade).
Finally, an astronaut used ultrasound to detect a blood clot while in space. Two months into a six-month mission on the International Space Station, the astronaut identified a deep vein thrombosis while performing a self-directed ultrasound exam as part of a vascular research study.
