Computer-aided mammography detection not associated with improved accuracy

CAD for mammography is intended to help radiologists identify subtle cancers that might otherwise be missed. The U.S. Food and Drug Administration approved CAD for mammography in 1998 and the Centers for Medicare and Medicaid Services (CMS) increased reimbursement for CAD in 2002. Measuring the true impact of CAD on the accuracy of mammographic interpretation has been challenging.

Constance D. Lehman, M.D., Ph.D., of the Massachusetts General Hospital, Boston, and coauthors measured the performance of digital screening mammography with and without CAD in U.S. community practice. The authors included more than 625,000 mammograms interpreted by 271 radiologists with CAD (n=495,818) or without (n=129,807) from 2003 through 2009 among 323,973 women. Linkages with tumor registries identified 3,159 breast cancers in the 323,973 women within one year of the screening.

The authors analyzed mammography performance based on sensitivity (the ability of a test to correctly identify those who do have the disease), specificity (the ability of a test to correctly identify those who do not have the disease) and cancer detection rates per 1,000 women.

The authors report screening performance with CAD was not associated with improvement based on the metrics they assessed. Sensitivity was 85.3 percent with CAD and 87.3 percent without CAD, while specificity was 91.6 percent with CAD and 91.4 percent without CAD. The authors also found no difference in the overall cancer detection rate (4.1 cancers per 1,000 women screened with and without CAD) or in the invasive cancer detection rate (2.9 vs. 3.0 cancers per 1,000 women screened with CAD or without), according to the results. Although the detection rate for ductal carcinoma in situ (DCIS) was slightly higher in patients whose mammograms were assessed with CAD compared to those without (1.2 vs. 0.9 cancers per 1,000 women), finding more low-grade DCIS may offer no improved outcomes for women in screening programs.

In subset analyses among 107 radiologists who interpreted mammograms both with and without CAD, performance was not improved with CAD and CAD was associated with decreased sensitivity (missing breast cancers).

"In the era of Choosing Wisely and clear commitments to support technology that brings added value to the patient experience, while aggressively reducing waste and containing costs, CAD is a technology that does not seem to warrant added compensation beyond coverage of the mammographic examination. The results of our comprehensive study lend no support for continued reimbursement for CAD as a method to increase mammography performance or improve patient outcomes," the authors conclude.

Commentary: Is it Time to Stop Paying for Computer-Aided Mammography

In a related commentary, Joshua J. Fenton, M.D., M.P.H., of the University of California, Davis Health System, Sacramento, writes: "If the CMS [Centers for Medicare and Medicaid Services] were to consider a proposal for new CAD coverage at this time, the current evidence base would not support approval. Thus, we should question whether society should continue to pay for CAD use. ... Congress should therefore rescind the Medicare benefit for CAD use. ... The lesson of CAD is that broad societal investment in new medical technologies should occur only after large-sample evaluations prove their real-world effectiveness and justify their costs."