Adverse drug events can lead to health hazards and have raised awareness of industries and governments internationally about pharmacovigilance. Baseline regularization(BR) is a regularized generalized linear model that uses the diverse health profiles available in longitudinal observational databases(LODs) like EHR and insurance claims databases across different individuals at different times to identify adverse drug events(ADEs). BR transforms the unsupervised learning of ADEs into a supervised learning problem. Quadratic approximation and blockwise minimization are used in the optimization algorithm for solving the compact BR model. Experimental results suggest that BR outperforms Self-Controlled Case Series(SCCS), the state-of-the-art model under various settings in identifying benchmark ADEs from the Observational Medical Outcomes Partnership ground truth.
Input variables : electronic health records (EHRs) and medical insurance claim databases
Output Variables : ADE identification
| 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 : github.com
Additional links : ncbi.nlm.nih.gov
| Model Category | : | Public |
| Date Published | : | May, 2018 |
| Healthcare Domain | : | Life Sciences |
| Code | : | github.com |
| Clinical Trials |
| Adverse Drug Events |