Prediction of patient copayment ahead of time by machine learning.
How acurate can it be?

Using a set of (SIMULATED) pharmacy data-billing claims that were run from a pharmacy to a third-party payer (insurance plan) who covers some portion of the prescription drug price on behalf of a patient. As part of the claim process the amount that the payer reimburses the pharmacy and copayments required of the patient are set by complicated negotiations and contracts between the drug manufacturer, the payer, and the pharmacy. Those negotiations also often cover decisions on what drug claims will ultimately be approved (preferred / non-preferred / non-covered formulary status of each drug) based on the relative discounts that the payer can secure relative to other drugs in the same class that may treat the similar types of medical conditions. Therefore, using this claim billing data into machine learning algorithms to build a method of predicting the copayments required of patients ahead of time will be useful for doctors to presribe drugs based on patient affordability.

Feaures in the model

  • Model Result

Filter Search in the dataset

Date Month Pharmacy Diagnosis Drug Bin Pcn Group Rejected Patient_pay