A machine learning model is developed to assist decision-makers in determining real-world performance of their novel drug against key hard end-points like Readmission and Length of stay (LOS) and overall utilization. Claims data was used containing variables available in first 72 hours of admission. Stepwise binomial regression model was used to identify risk stratified readmission and its corresponding significant factors. Also Cox regression analysis is used to obtain risk stratified and very high Length of Stay visits. Accuracy for LR is75% and for Cox it is 91%.
Input variables : Claims data based features like demographic, diagnosis, comorbidities
Output Variables : Risk stratified Readmission and Length of Stay
| 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 |
| Business | : | # of Adverse Events |
| 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
Additional links : f.hubspotusercontent30.net
| Model Category | : | Commercial |
| Date Published | : | January, 2017 |
| Healthcare Domain | : | Life Sciences |
| Code | : | Not available |
| Clinical Trials |
| Adverse Drug Events |