This model predicts the ART HEDIS® quality measure used to assess the receipt of disease-modifying antirheumatic drugs (DMARDs) among patients with rheumatoid arthritis (RA) for a given population of the interest using claims data. The accuracy of 0.79 is achieved. Performance measures related to disease-modifying drugs (DMARDs) based on claims data are the longest and most widely used rheumatoid arthritis (RA) measures in the U.S. health care system. The ART HEDIS® measure is now part of PCPI and PQRS reporting. This measure is based on percentage of patients ages 18 and older who were diagnosed with rheumatoid arthritis (RA) and were dispensed at least one ambulatory prescription(s) for a disease-modifying anti-rheumatic drug (DMARD) during the measurement year. If any patient with RA is not prescribed DMARD in 45 days,then it is considered as care gap and costs provider to lose the quality value or star rating. For targeted ART measure value for the given population, this model predicts which adults diagnosed with rheumatoid arthritis (RA) will not be dispensed at least one ambulatory prescription for a disease-modifying anti-rheumatic drug (DMARD) by end of reporting period. In other words this model tried to predict the care gap associated with ART measure. Knowledge of this predicted measure can help to identify potential patient need to be followed up for DMARD prescription and thus close the care gaps, improve compliance and help to develop clinical understanding of the Medicare member. Model made use of claims data spanned over 1 year as a training set and the accuracy of 0.79 was obtained for following year.
Input variables : Claims data based variables like demographic features, health history, pharmacy data, Diagnosis and procedure codes
Output Variables : Adults diagnosed with rheumatoid arthritis (RA)
| Statistical | : | Mallow's CP | R Squared | Mean Square Error | Adjusted R Squared | Mean Absolute Error | Huber Loss |
| Business | : | HEDIS Measure Improvement |
| Infrastructure | : | Log Bytes | Logging/User/IAMPolicy | Logging/User/VPN | CPU Utilization | Memory Usage | Error Count | Prediction Count | Prediction Latencies | Private Endpoint Prediction Latencies | Private Endpoint Response Count |
Visit Model : medictiv.citiustech.com
Additional links : cmit.cms.gov
| Model Category | : | Commercial |
| Date Published | : | May, 2019 |
| Healthcare Domain | : |
Payer
Provider |
| Code | : | Not available |
| Quality Management |
| Quality Measures |