Forecasting model for scheduling and staffing workflow
The model optimizes the scheduling and the staffing workflow efficiency across facilities and sub-specialists based on forecasting. It forecast the demand of the available radiologists and accordingly have a plan in place for meeting the demands for these radiologists. The model is trained using one year of radiologist scheduling data of 250 different facilities in terms of relative value unit (RVU). The model is validated on following 3 months of data. The average prediction accuracy of different models is 85% on test data.
Input variables : 1 year of radiologist scheduling data of 250 facilities in terms of relative value unit (RVU), weather data, holiday data, demographic parameters
Output Variables : RVU for different facilities, required staffing count for radiologist to meet the demand
Metrics to Monitor
|
Statistical
|
:
|
Mallow's CP |
R Squared |
Mean Square Error |
Adjusted R Squared |
Mean Absolute Error |
Huber Loss
|
|
Business
|
:
|
Cancelled/ Missed Appointments |
Staffing requirement by department
|
|
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