Lung-RADS limits false readings and saves money in lung cancer screening, according to a study at ACR 2016.
Use of Lung-RADS will decrease Medicare costs over the next three years without affecting accuracy, according to a presentation at the 2016 annual meeting of the American College of Radiology.
Researchers from the Fred Hutchinson Cancer Research Center and the University of Washington in Seattle sought to evaluate the potential impacts of using a standardized low-dose CT (LDCT) lung cancer screening reporting and management system, the Lung Imaging Reporting and Data System, or Lung-RADS, compared with the use of a less structured system, from the National Lung Screening Trial (NLST). The study group involved patients aged 55 to 57, with a 30-pack-per-year or higher smoking history.
The researchers developed a simulation model to estimate the three-year incremental outcomes of screening using Lung-RADS compared with screening using the NLST protocol.
Projected outcomes were made for a Medicare population with 51.7 million members per year. The LDCT screening test characteristics were derived from the NLST. Costs that were included were:
• LDCT screening
• Follow-up imaging
• Confirmatory bronchoscopy/biopsy
• Stage-specific treatment
The outcomes were calculated assuming 100% adherence to Medicare screening criteria and nodule management protocols in the base case.
The results showed that an LDCT program in this patient group, over a three-year period, would be expected to see 1.3 million fewer false-positive screening results, 27,000 fewer invasive follow-up procedures, and decreased overall expenditure of $2.07 per-member per-year, for a total of $316 million.
The researchers concluded that their findings demonstrate that Lung-RADS can have important economic impacts in addition to reducing physical and psychological harms related to false-positive screening results.
Can CT-Based Deep Learning Bolster Prognostic Assessments of Ground-Glass Nodules?
June 19th 2025Emerging research shows that a multiple time-series deep learning model assessment of CT images provides 20 percent higher sensitivity than a delta radiomic model and 56 percent higher sensitivity than a clinical model for prognostic evaluation of ground-glass nodules.