Predictive Model for Pharmacy Prescription Return to Stock
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current prescription processing methods result in significant returns of medications and medical devices to stock, which are costly, time-consuming, and prone to errors, as they do not effectively predict whether a patient will pick up their prescribed items.
Innovation Solution
A predictive model is developed that uses patient health record data and electronic prescription data to estimate the probability of a prescription being returned to stock, incorporating various data attributes and machine learning techniques to generate a predictive model that notifies patients and adjusts filling decisions accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If prescriptions are filled without prediction, then all prescriptions are processed, but many are returned to stock unnecessarily
Solution Approach 1:
The system performs preliminary actions by predicting patient pickup behavior before the prescription is filled. The predictive model analyzes patient data, prescription characteristics, and historical patterns to generate a pickup probability score, allowing the pharmacy to proactively identify prescriptions likely to be returned and take preventive measures such as patient notification or alternative arrangements.
2Loss of substance
If predictive model is implemented, then return to stock is reduced, but system complexity increases
Solution Approach 1:
The predictive model serves multiple functions: it predicts pickup probability, identifies high-risk prescriptions, generates patient notifications, and provides decision support for pharmacy staff. This multi-functionality consolidates what could be multiple separate systems into a single integrated platform, reducing overall complexity while achieving comprehensive return reduction.
3Reliability
If patient notification is sent, then patient awareness is improved, but time and resources are consumed
Solution Approach 1:
The system implements self-service by automatically notifying patients about their prescriptions and the potential for return to stock. Patients receive automated communications with actionable information, allowing them to take initiative in ensuring their prescription is filled without requiring manual intervention from pharmacy staff for each notification.
4Productivity
If all prescriptions are filled, then pharmacy output is maximized, but error risk increases due to returns
Solution Approach 1:
The system implements feedback loops where prediction results are continuously monitored, patient responses are tracked, and model accuracy is evaluated. This feedback mechanism allows the system to learn from actual outcomes and improve its predictions over time, increasing reliability while maintaining high productivity through data-driven decision making.
Data Source
AI summary
Apparatuses, systems, and methods are provided for reducing return of prescriptions to stock. The apparatuses, systems and methods provide for one or more processors to: (1) store pharmacy prescription information in a standardized pharmacy format; (2) receive updated information in a non-standardized electronic prescription format for a prescription of a patient; (3) receive patient health record data; (4) generate prescription return to stock prediction data that indicates a probability the prescription of the patient would be returned to stock based upon the electronic prescription data, the patient health record data, and a predictive model; (5) convert the electronic prescription data and the prescription return to stock prediction data to pharmacy prescription information; and (6) generate a pharmacy prescription in a standardized format based on the updated pharmacy prescription information.