Given patient demographic and diagnoses information for a collection of patients, this model predicts prospective insurance cost using a trained LightGBM Regression Model. Inclusion of Demographics at the ZIP code-level Social Determinant of Health (SDOH) factors reduces underestimation of cost among people living in vulnerable areas. A 2-by-2 factorial design comparing: (I) linear regression versus ML (gradient boosting) (ii) demographics and diagnostic codes alone, versus additional ZIP code-level SDH indicators shows the value add from the model against other prevailing approaches. The model's utility and usage is demonstrated using Healthcare claims data from privately-insured US adults for 2016-17, and Census data.
Input variables : Patient Demographics, ZIP code ,list of ICD-10 Diagnoses
Output Variables : Prospective Insurance cost
| 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 | : | Drug Cost per Visit | Avg Treatment Cost |
| 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 : bmcpublichealth.biomedcentral.com
| Model Category | : | Public |
| Date Published | : | January, 2020 |
| Healthcare Domain | : | Payer |
| Code | : | github.com |
| Utilization Management |
| Cost of Care |