Predictive Model for Computing HEDIS Measure Osteoporosis Management in Women
The predictive model is built to predict value of the HEDIS measure Osteoporosis Management in Women (OMW) for given cohort of female patients. The model predicts, how many female patients ages 67 to 85 who suffered a fracture will either undergo bone mineral density (BMD) test or will receive a prescription to treat osteoporosis in the six
months after the fracture. Claims dataset was used to extract demographic and clinical feateures in order to train a machine learning model. The resulting XGBoost model showed training data accuracy of 0.67 (67%) and for test data it was 0.57 (57%)
Input variables : 22 different demographic features, health history, Dignosis and procedure codes.
Output Variables : Identified members with osteoporosis
Metrics to Monitor
|
Statistical
|
:
|
Mallow's CP |
R Squared |
Mean Square Error |
Adjusted R Squared |
Mean Absolute Error |
Huber Loss
|
|
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