A new federal report suggests that Medicare Advantage plans may have earned millions in overpayments tied to unsupported stroke diagnoses.
The Department of Health and Human Services Office of Inspector General examined (PDF) 240,401 Medicare Advantage enrollees who were at high risk for an inaccurate diagnoses code for acute stroke, pulling out a sample of 97 members. The analysts found that across all 97 of those individuals, high-risk acute stroke diagnoses were not supported by the patients' medical records.
Based on this sample, OIG estimates that the Centers for Medicare & Medicaid Services overpaid MA plans by $462 million in 2021 alone from inaccurate stroke diagnoses.
"Previous OIG audits of specific MA organizations have identified acute stroke diagnosis codes submitted on physician data records without an acute stroke diagnosis on an inpatient or outpatient hospital data record during the same service year as a high-risk area for overpayment," the agency wrote in the report.
"This audit focused on this high-risk area across multiple MA organizations to examine whether MA organizations’ submissions of these diagnosis codes to CMS complied with federal requirements," OIG said.
Overpayments to Medicare Advantage plans have been a key focus for regulators and lawmakers. The Medicare Payment Advisory Commission estimated earlier this year that the federal government will overpay MA plans by $76 billion in 2026.
One of the key sources of these overpayments is "upcoding," a practice in which insurers inflate risk scores to secure additional payouts. The MedPAC analysis said that coding intensity is one of the key factors driving overpayments, with fraudulent or inaccurate diagnoses as one element of that.
Medicare Advantage plans are often more comprehensive in documenting diagnoses compared to traditional Medicare, MedPAC said.
OIG submitted a recommendation to CMS that the agency implement a policy to prevent MA plans from submitting acute stroke diagnoses that are not supported by inpatient or outpatient hospital data from that same timeframe. CMS did not specify if it concurs or not with the recommendation.