A system presented at the SIIM meeting is able to develop work lists based on a patient’s insurance and a radiologist’s credentialing status, important considerations as more and more studies are interpreted away from central offices and facilities try to maximize reimbursement.
A system presented at the SIIM meeting is able to develop work lists based on a patient's insurance and a radiologist's credentialing status, important considerations as more and more studies are interpreted away from central offices and facilities try to maximize reimbursement.
The original inspiration for the system was to keep studies for Medicare and Medicaid patients off the work list used by a radiologist who was based outside of the U.S. CMS does not permit payment for interpretations performed on non-U.S. soil, although most private payers do. Few, if any, RIS or PACS today have the ability to filter work lists based on insurance status, according to the authors of the study, Drs. David S. Hirschorn and Leonard Lempert, both of Staten Island University Hospital.
Their solution, described in a poster presentation, was to develop an algorithm that removes CMS studies from a work list developed for an overseas teleradiologist reading night studies for the hospital.
The algorithm includes a table that specifies whether the patient's insurance coverage is from CMS and whether the teleradiologist is credentialed for the plan. A web-based tool allows users to modify and view the payer information and to adjust it as necessary when new payers are added.
The table is then used to filter out cases from the overseas teleradiologist's work list based on whether CMS will pay for them, the radiologist's credentialing status for the payers, and whether it is an emergency case.
Later, the same system was adapted to steer nonemergency cases toward radiologists who are credentialed by the payers that are associated with the cases. The system increases the likelihood of payment for all claims from the department, the authors said.
Could AI-Powered Abbreviated MRI Reinvent Detection for Structural Abnormalities of the Knee?
April 24th 2025Employing deep learning image reconstruction, parallel imaging and multi-slice acceleration in a sub-five-minute 3T knee MRI, researchers noted 100 percent sensitivity and 99 percent specificity for anterior cruciate ligament (ACL) tears.
The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring
December 5th 2020Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, discusses, during RSNA 2020, what new developments the annual meeting provided about these technologies, sessions to access, and what to expect in the coming year.