Given the EHR data this model uses features like demographics, diagnosis codes, procedures to predict the utilization of healthcare services. The predicted data can be used in Healthcare planning, risk adjustment and cost projections. The data for this model was sourced from the Register of Primary Health Care Visits of Finnish Institute for Health and Welfare. Electronic Health Records (EHR) of 1.4 million Finnish citizens, aged 65 and above, to develop a sequential deep learning model to predict utilization of healthcare services in the following year on individual level.The model architecture is enhanced to handle multiple medical codes during each patient visit which boosts the predictive performance.
Input variables : Features based on diagnosis codes, procedures, patient demographics
Output Variables : Healthcare service utilization prediction
| 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 : github.com
Additional links : researchportal.helsinki.fi
| Model Category | : | Public |
| Date Published | : | December, 2020 |
| Healthcare Domain | : |
Payer
Provider |
| Code | : | github.com |
| Utilization Management |
| Hospital Resource Utilization |