Maintaining a good quality of care delivered in hospitals is a very important task in healthcare industry. Performance of a hospital plays an important role in various decision making. Hospital performance is assessed via health outcomes of their patients. The proposed model accounts for non linearity as well as interactions among patient risk variables, effect of co-occurring health conditions on health outcome. The main task here is to estimate the hospital specific contribution to health outcome given the data on patient risk profiles and their observed health outcome. Currently a Hierarchical Generalized Linear Model(HGLM) is used for the purpose. But its limitation is not non-linear variation is captured. To address above challange a non linear model is proposed for measuring risk adjusted hospital performance. Data used for the study is obtained from Nationwide Readmission Database.
Input variables : ICD Codes for primary diagnostics, Socio-demographic variables
Output Variables : Risk-Adjusted Hospital Performance Score
| Statistical | : | Somers D | Accuracy | Precision and Recall | Confusion Matrix | F1 Score | Roc and Auc | Prevalence | Detection Rate | Balanced Accuracy | Cohen's Kappa | Concordance | Gini Coefficent | KS Statistic | Youden's J Index |
| 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 : arxiv.org
| Model Category | : | Public |
| Date Published | : | November, 2020 |
| Healthcare Domain | : |
Payer
Provider |
| Code | : | github.com |
| Quality Management |
| Performance Score |