Prescription Data Parsing for Dispensing Inaccuracy Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Inaccuracies in medical prescriptions, including prescriber and dispensing errors, are introduced during the conversion process from electronic medical record systems to dispensing systems, leading to potential harm to patients due to incorrect medication instructions or dosages.

Innovation Solution

A method and system for inaccuracy detection and prevention in prescription information, utilizing hierarchical prescription entries and machine learning algorithms to analyze and flag inaccuracies, including prescriber, dispensing, and financial errors, and providing alerts to the prescription provider system.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional rule-based systems are used to detect inaccuracies, then the system complexity is low, but the detection precision and ability to identify complex dispensing errors is insufficient

Engineering Contradiction:

Improveinaccuracy detection precisionVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces traditional rule-based mechanical detection systems with machine learning-based intelligent detection systems. The machine learning model automatically learns patterns and rules from training data, enabling more precise detection of dispensing inaccuracies without requiring manual configuration of complex detection rules, thus improving detection precision while managing system complexity through automated learning.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary machine learning model that acts as a mediator between the prescription data and the detection process. This intermediary layer processes and analyzes prescription data through learned patterns, providing more accurate detection results compared to direct rule-based approaches, while the model can be trained and updated independently of the core detection logic.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If data conversion from EMR system to dispensing system is performed, then the systems can communicate, but dispensing inaccuracies are introduced during conversion

Engineering Contradiction:

Improvesystem compatibilityVSAvoidprescription accuracy

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent applies preliminary action by performing inaccuracy detection before the dispensing process begins. The machine learning model analyzes the converted prescription data and identifies potential errors in advance, allowing corrections to be made before the patient receives the medication, thus preventing harmful inaccuracies from reaching the dispensing stage.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback by using the machine learning model to continuously analyze conversion processes and provide information about detected inaccuracies. This feedback loop allows the system to identify and correct errors introduced during data conversion between EMR and dispensing systems, improving the reliability of the converted data while maintaining system compatibility.

Inventive Principle:

Principle #23Feedback

3Reliability

If real-time inaccuracy detection is implemented, then patient safety is improved, but the processing time and system complexity increase

Engineering Contradiction:

Improvepatient safetyVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent applies partial action by focusing the machine learning model's detection capabilities on specific high-risk areas of prescription data, such as dosage instructions and medication names. Rather than analyzing every aspect of the prescription equally, the system concentrates computational resources on the most critical elements that pose the greatest risk to patient safety, thereby reducing overall processing time while maintaining high safety standards.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12592302B2Systems and methods for inaccuracy detection and prevention within prescription information

Publication Date: 2026.03.31 CVS PHARMACY INC

AI summary

In some instances, a method for inaccuracy detection and prevention within prescription information is provided. The method comprises: receiving, from a prescription generation system, prescriber prescription information indicating an electronically transmitted medical prescription associated with a patient; converting the electronically transmitted prescription information to a plurality of hierarchical prescription entries based on parsing the electronically transmitted medical prescription associated with the patient; determining whether the plurality of hierarchical prescription entries includes one or more dispensing inaccuracies based on using the plurality of hierarchical prescription entries, the prescriber prescription information, and one or more dispensing parameters indicating a ranking associated with the plurality of hierarchical prescription entries; and based on determining the one or more dispensing inaccuracies within the plurality of hierarchical prescription entries, providing, to a prescription provider system, provider prescription information indicating the converted electronically transmitted prescription information and the one or more dispensing inaccuracies.