ML-Based Compounding Device Consumable Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The pharmaceutical compounding process for intravenous medications is prone to errors due to the complexity of preparing medications in various forms, dosages, and delivery vehicles, which can lead to incorrect proportions, contamination, and human errors.
Innovation Solution
A pharmaceutical compounding device equipped with machine learning techniques that can identify consumables, determine their proper placement, and detect air bubbles in syringes, thereby reducing errors and improving the accuracy of medication preparation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual tracking of consumable products is used during compounding, then pharmacy workers can monitor inventory, but errors increase during high workload and the process becomes tedious
Solution Approach 1:
The system enables self-service by using machine learning models to automatically identify and track consumable products without requiring manual intervention from pharmacy workers. The device autonomously monitors inventory levels and verifies consumable usage, eliminating the need for tedious manual tracking while maintaining high accuracy even during high workload periods.
Solution Approach 2:
The patent replaces the mechanical manual tracking system with an automated optical recognition system using cameras and machine learning algorithms. This substitution eliminates human error in consumable tracking and significantly improves workflow efficiency by automating what was previously a manual, error-prone process.
2Measurement precision
If automated machine learning identification is implemented, then consumable tracking accuracy improves, but device complexity increases
Solution Approach 1:
The system achieves multi-functionality by using a single integrated device that performs multiple tasks: capturing images of consumables, identifying them through machine learning models, tracking their usage, and verifying proper placement. This universal approach improves identification accuracy while avoiding the complexity of multiple separate systems.
Solution Approach 2:
The patent uses optical copying through camera imaging to create digital representations of consumable products. These image copies are then analyzed by machine learning models for identification and tracking, achieving high measurement precision without requiring physical manipulation or complex hardware modifications to the consumables themselves.
3Manufacturing precision
If detailed protocols are followed for each medication preparation, then compounding accuracy improves, but the workload and time required increase significantly
Solution Approach 1:
The system implements continuous feedback by automatically monitoring each step of the compounding process through image capture and machine learning analysis. The device provides real-time verification of consumable usage and proper placement, enabling immediate correction of errors while maintaining high preparation accuracy. This automated feedback loop eliminates the need for time-consuming manual protocol verification.
Solution Approach 2:
The patent applies preliminary action by pre-training machine learning models with extensive datasets of consumable products and proper placement configurations. This preliminary training enables the system to automatically recognize and verify correct procedures during compounding without requiring time-consuming manual reference to detailed protocols, thus maintaining high accuracy while reducing compounding time.
4Object-affected harmful factors
If air bubbles are manually detected and removed from syringes, then patient safety improves, but the process requires additional training and time
Solution Approach 1:
The patent replaces manual visual inspection and physical manipulation for air bubble detection with an automated optical detection system using machine learning. The device captures images of syringes and automatically identifies air bubbles, eliminating the need for healthcare professionals to undergo extensive training in manual detection techniques while improving patient safety.
Solution Approach 2:
The system performs self-service by autonomously detecting and alerting healthcare professionals to the presence of air bubbles in syringes. This automated self-monitoring capability improves patient safety without requiring additional manual intervention or complex操作流程, thereby maintaining ease of operation while enhancing harm prevention.
Data Source
AI summary
Systems and methods of compounding of medication include a user interface that enables efficient design of compounding workflows and protocols. The device may include a memory storing instructions that, when executed by a processor, perform operations including capturing an image of an object placed on the scale plate using the physical light camera; accessing a plurality of trained machine learning models stored in a memory of the pharmaceutical compounding device; determining an identification of the object based at least in part on the image of the object using machine learning image analysis techniques using a trained model using at least a first one of the plurality of trained machine learning models; determining a workflow based on the identification of the object; and generate a notification on the electronic display based on the workflow.