HealthCare Claims is an AI driven FRAUD DETECTOR Android Application created to protect the payer by identifying inconsistencies and potential rule-breaking and hence prevent med-care scamming and by providing real-time safety feature to flag out fraud transactions and block them. The model involves KNeighbors Classifier and is developed in Jupyter and Dart. On uploading necessary information, in real-time, the application flags the claims as fraudulent or genuine. The application providers have also given an option of customization according to the needs and data provided by the organization.
Input variables : Patient and claim information
Output Variables : Claim status (fraudulent or not)
| 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 | : | Claims Processed | $ Saved | FWA Rate | FWA by CPT | FWA by Provider |
| 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 : youtu.be
| Model Category | : | Public |
| Date Published | : | October, 2020 |
| Healthcare Domain | : | Payer |
| Code | : | github.com |
| Claims Management |
| Fraud Waste and Abuse |