CAD: Ineffective in Finding Breast Cancer
A recent study was conducted at UC Davis which concluded that CAD technology is ineffective in finding breast tumors and actually increases a woman's risk of being called back needlessly for additional testing following a mammogram.
Joshua Fenton, assistant professor in the UC Davis Department of Family and Community Medicine was quoted saying, "In real-world practice, CAD increases the chances of being unnecessarily called back for further testing because of the false-positive results without clear benefits to women. Breast cancers were detected at a similar stage and size regardless of whether or not radiologists used CAD."
A study used to determine the effectiveness of CAD examined screening mammograms that were performed on more than 680,000 women at 90 facilities within seven states from 1998 to 2006. The rate of false positive test results typically increased from 8.1 percent before CAD to 8.6 percent after CAD was installed at the facilities covered in the study. CAD was approved by the Food and Drug Administration in 1998 in order to analyze a mammogram image and mark suspicious areas for radiologists to review. The use of this detection software has greatly increased in recent years and is applied to a majority of screenings in the United States. Medicare data from 2009 demonstrated that Medicare typically paid about 12 dollars per screening mammogram for CAD in addition to the actual costs of the mammogram (about 81 dollars).
The most recent study of CAD examined screening results in 43 facilities, including seven that used CAD and determined that using CAD software reduced the accuracy of interpretation of screening mammograms but made no difference in the detection rate of invasive breast cancer. Critics of this current study claim that the findings were based on the use of an older kind of CAD technology and therefore did not accurately reflect the usefulness of the device. The authors of this study suggest that differences between real-world studies of CAD and pre-clinical ones may be due to the radiologists in the practice who do not always adhere to the strict use of the technology as it was designed.