Forecasting based approach for case volume prediction in a clinic
A time series forecasting based models are developed to enhance current case volume prediction for Anesthesia line of business. The model makes use of ensemble of multiple time series models such as ARIMA, Holt-Winter, Exponential Smoothing to improve the prediction accuracy. The prediction time horizon of 15 days is used. The model makes use of clinical data comprising of demands for anesthesia unit services. Prediction accuracy of 92% is obtained on unseen data. The resulting model is integrated with angular based application and deployed at client side for real time prediction
Input variables : Hospital data - Case Volume
Output Variables : Case volume prediction model for Anesthesia line of business
Metrics to Monitor
Statistical
|
:
|
Mallow's CP |
R Squared |
Mean Square Error |
Adjusted R Squared |
Mean Absolute Error |
Huber Loss
|
Business
|
:
|
Bed Occupancy Rate |
Medical Equipment Utilization |
Optimized Hospital Resource Utilization
|
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