Alzheimer’s Risk Adjustment Increases Detection, Medicare Spending

Incorporating Alzheimer’s disease and related dementias (ADRD) Hierarchical Condition Categories (HCCs) into risk adjustment for Medicare Advantage and Medicare accountable care organizations (ACOs) helps decrease false negative rates but may increase Medicare spending, according to a Health Affairs study.

CMS reintroduced risk adjustment for ADRD in 2020 after removing it in 2014. CMS also started managing coding and auditing incentives again. In Medicare Advantage, per beneficiary per month payments will be prospectively risk-adjusted by ADRD HCCs, while fee-for-service payments in Medicare ACOs will be reconciled against risk-adjusted expenditure benchmarks that include ADRD HCCs.

Researchers used Medicare Parts A and B claims and EHR data from the Mass General Brigham ACO from 2016 to 2018 to assess the accuracy of ADRD coding before ADRD risk adjustment was reintroduced. They compared claims with diagnosis codes included in the ADRD HCCs to a clinician-adjudicated reference standard.

Just over 2,800 beneficiaries had clinician-adjudicated ADRD and 3,282 beneficiaries had a qualifying ADRD diagnostic code under the HCC. Among the beneficiaries with ADRD HCCs, 34 percent did not have clinician-adjudicated ADRD and were classified as false positives.

For the HCC claims-based indicator of ADRD, there was a 3.2 percent false-positive rate and a 22.7 percent false-negative rate. This indicator was 66.1 percent likely to correctly identify a positive case of ADRD and 98.1 percent likely to identify a negative case of ADRD.

Researchers analyzed predicted and observed expenditures for beneficiaries with true- and false-positive and true- and false-negative ADRD HCCs.

Predicted spending for false negatives was $18,347 lower than observed expenditures, while predicted spending for false positives was $7,998 higher than observed expenditures. This suggests that ADRD risk adjustment could provide a financial incentive for Medicare Advantage plans and ACOs

The observed expenditures for false negatives exceeded those of true positives by $14,619 per beneficiary, researchers found.

Risk-adjustment scores differed for these subgroups. The average score for the entire beneficiary population was 1.08, while true negatives had the lowest score of 0.99.

Once the ADRD weight was removed, scores in the false-positive subgroup were 15 percent lower than the observed scores. Corrected scores for false negatives were 22 percent higher than observed scores.

Among beneficiaries with clinician-adjudicated ADRD, true positives (2.15) had a higher average prospective risk-adjustment score compared to false negatives (1.63).

After reclassifying false-negative beneficiaries as true positives, the average risk-adjustment score among beneficiaries with clinician-adjudicated ADRD increased by 9 percent to 2.07. If risk adjustment for ADRD helped reduce false negatives, this indicates that expenditure benchmarks for beneficiaries with ADRD would grow by 9 percent.

“Incorporating ADRD HCCs into risk adjustment creates incentives for providers to increase the use of ADRD International Classification of Diseases codes in claims, resulting in a concomitant increase in the false-positive rate and decrease in the false-negative rate of cases ascertained using the HCC definition,” researchers wrote.

However, changes in coding behavior in traditional Medicare could alter the weight assigned to patients with ADRD, which would increase Medicare spending in Medicare Advantage. In return, reimbursement for other diagnoses would decrease due to budget neutrality.

“Although risk adjustment for ADRD should reduce underdiagnosis, which may improve clinical management, its influence on false-negative and false-positive diagnoses has the potential to considerably increase total Medicare expenditures and the distribution of risk-adjustment weights across HCCs,” the study concluded.