Adaptive Prescription Reminder System Using Cloud ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional pharmacy computing environments face limitations in data synchronization across devices, lack of geographic flexibility, and insufficient insight into patient adherence to prescription instructions, leading to inefficiencies and reduced ability to assist patients effectively.
Innovation Solution
A cloud-based system using machine learning to generate adaptive prescription schedules and reminders, synchronizing data across devices, and providing insights into patient medication adherence, while accommodating local regulations and supporting both chronic and acute medication regimens.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If prescription data is stored exclusively in the patient's device, then data security and accessibility are improved, but data synchronization across multiple devices deteriorates
Solution Approach 1:
The patent introduces a cloud-based server as an intermediary between the patient's devices and the pharmacy system. This server acts as a mediator that receives prescription data from the pharmacy, stores it securely in the cloud, and distributes it to multiple patient devices. This resolves the contradiction by maintaining data security through centralized control while enabling seamless synchronization across devices through the cloud intermediary.
2Device complexity
If centralized computing architecture is used, then system control and data management are improved, but geographic flexibility and adaptability to local regulations deteriorate
Solution Approach 1:
The patent segments the centralized system into modular components that can be independently configured for different geographic regions. The cloud-based architecture allows the core system to remain centralized for control and data management, while regional nodes or interfaces can be customized to comply with local laws and regulations. This segmentation enables both centralized control and geographic adaptability simultaneously.
3Ease of operation
If conventional reminder systems are used, then implementation simplicity is improved, but patient adherence monitoring and insight into medication consumption deteriorate
Solution Approach 1:
The patent implements a feedback mechanism where the system sends prescription reminders to patients and simultaneously tracks their responses and medication consumption status. This feedback loop provides the pharmacy with real-time insights into patient adherence while maintaining a simple user interface for patients. The system automatically monitors whether patients have taken their medications and provides this information back to the pharmacy without requiring complex patient input.
4Device complexity
If all medications are assumed to be chronic schedules, then system simplicity is improved, but adaptability to acute illness medications deteriorates
Solution Approach 1:
The patent implements a dynamic prescription scheduling system that can automatically adjust medication schedules based on patient feedback and consumption patterns. For acute illnesses, the system can modify dosing frequencies and timeframes as the patient recovers, transitioning from intensive initial dosing to maintenance dosing. This dynamic adaptability allows the system to handle both chronic and acute medications effectively without requiring completely different system architectures.
Data Source
AI summary
A computing system for adaptive prescription reminders includes a processor and a memory storing instructions that, when executed by the processor, cause the system to receive a fill event, generate an initial schedule, receive an medication consumption indication, generate an updated schedule using a trained machine learning model, cause the updated schedule to be displayed, and receive a patient confirmation. A computer-implemented method includes receiving a fill event, generating an initial schedule, receiving an medication consumption indication, generating an updated schedule using a trained machine learning model, causing the updated schedule to be displayed, and receiving a patient confirmation. A non-transitory computer readable medium includes program instructions that when executed, cause a computer to: receive a fill event, generate an initial schedule, receive an medication consumption indication, generate an updated schedule using a trained machine learning model, cause the updated schedule to be displayed, and receive a patient confirmation.