Medication Dispensing Conversion System for Adherence Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Patients with high medication burdens face challenges in adhering to complex medication regimens, and existing methods for converting traditional bottle dispensing to multiple-dose pouch packaging are inefficient and often miss opportunities due to manual processes and incompatibility issues.
Innovation Solution
A medication dispensing conversion system that analyzes prescription claims data to automatically identify at-risk patients and medications not compatible with alternate dispensing methods, using machine learning to generate conversion scores and trigger notifications for switching to multiple-dose pouch packaging or other adherence solutions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual processes are used to identify patients and medications for conversion to multiple-dose packaging, then resource consumption is reduced, but productivity and conversion efficiency deteriorate due to tedious and time-consuming manual identification
Solution Approach 1:
The system automatically identifies suitable patients and medications for conversion to multiple-dose packaging using machine learning models that analyze prescription claims data. The system self-evaluates conversion likelihood scores and triggers notifications without manual intervention, enabling the system to serve itself in the identification process while maintaining high productivity and efficiency.
2Measurement precision
If comprehensive analysis of prescription claims data is performed to identify suitable patients, then conversion accuracy is improved, but resource consumption and processing time increase
Solution Approach 1:
The machine learning model is pre-trained on historical prescription claims data to establish conversion likelihood scores. This preliminary training enables the system to quickly and accurately identify suitable patients for conversion without performing comprehensive real-time analysis, thereby maintaining high identification accuracy while minimizing processing time during actual deployment.
3Reliability
If alternate dispensing methods are converted to multiple-dose packaging, then medication adherence is improved, but compatibility issues arise for certain medications that cannot be converted
Solution Approach 1:
The system applies different conversion approaches based on medication-specific properties. For medications compatible with multiple-dose packaging, the system recommends conversion to improve adherence. For incompatible medications, the system identifies them as exceptions and maintains their original dispensing methods, ensuring that each medication receives the appropriate treatment based on its specific characteristics and compatibility requirements.
4Productivity
If automated machine learning models are deployed to identify conversion opportunities, then productivity and efficiency are improved, but device complexity and implementation difficulty increase
Solution Approach 1:
The system employs an intermediary notification mechanism that bridges the automated machine learning model and the manual conversion process. The model generates conversion likelihood scores and triggers notifications to relevant stakeholders, who then review and execute the conversion. This intermediary approach allows automated efficiency while maintaining manageable complexity through a clear separation of automated analysis and human decision-making.
Data Source
AI summary
Methods and systems for performing multidose packaging targeting are provided. The methods and systems perform operations comprising: receiving prescription related complexity data associated with a patient, the prescription related complexity data comprising medication regiment information for a plurality of medications and patient specific information, the prescription related complexity data representing complexity for the patient in adhering to the one or more medications; applying a model to the prescription related complexity data to generate a score for at least one medication of the plurality of medications, the score being indicative of a likelihood of converting the patient from a current dispensing process to an alternate dispensing process; and triggering, based on the generated score, a notification associated with converting the patient from the current dispensing process to the alternate dispensing process.