Machine Learning Prescription Cost Estimates Before Filling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
A significant number of prescriptions for medications go unfilled, leading to financial overhead and unmet medical needs due to unaffordability, necessitating a solution to estimate costs before filling to ensure patient compliance and reduce waste.
Innovation Solution
Implementing a system that uses machine learning to estimate prescription costs based on patient coverage, medication details, and ancillary information, providing estimates to prescribers and patients to facilitate informed decision-making and alternative medication selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If prescriptions are filled without cost estimation, then pharmacy operations are simplified, but patient compliance decreases and unfilled prescriptions increase
Solution Approach 1:
The system performs cost estimation before the prescription filling process begins. By predicting the out-of-pocket cost using machine learning models and presenting it to patients prior to pickup, the system enables informed decision-making and improves compliance without complicating the actual filling operation.
Solution Approach 2:
The cost estimation system acts as an intermediary between the pharmacy and patient. It provides bridging information (predicted costs) that enables patients to make informed decisions about whether to fill their prescriptions, thereby improving compliance without requiring complex changes to the core pharmacy operation.
2Reliability
If cost estimation is performed for every prescription, then patient compliance improves, but processing time increases
Solution Approach 1:
The system uses machine learning models that automatically generate cost estimates independently, without requiring manual intervention or complex processing. The models process input data (prescription details, patient coverage) and output predictions rapidly, minimizing time added to the prescription workflow while maintaining high compliance improvement.
3Measurement precision
If actual cost data is submitted to payors before estimation, then cost accuracy improves, but financial overhead increases due to unfilled prescriptions
Solution Approach 1:
The system performs cost estimation before submitting claims to payors. By predicting costs in advance using machine learning models trained on historical data, the system can identify potentially unfillable prescriptions beforehand, preventing financial overhead from unfilled prescriptions while maintaining accurate cost information for claim submission.
Data Source
AI summary
Example methods, apparatus, and articles of manufacture to estimate costs of prescriptions are disclosed herein. An example system to estimate a cost of a prescription for a medication includes receiving a prescription for a medication for a patient, receiving a request for an estimated cost for the prescription for the patient from an entity, forming an input vector including prescription information for the received prescription and payor information for the patient, processing the input vector for the received prescription with a trained machine learning model to determine the estimated cost of the medication for the patient, updating the machine learning model based upon computed differences between predicted costs determined by the machine learning model and actual sold costs for the plurality of sold prescriptions, providing the estimated cost to a user device, and deploying the updated machine learning model.