Handheld Diabetes Device Pattern Recognition for Glucose Management

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Handheld diabetes management devices have limited user interfaces, making it difficult to configure reminders for blood glucose measurements, classify measurements, and identify trends in glucose levels effectively.

Innovation Solution

A handheld diabetes management device equipped with a blood glucose measurement engine, a clock, a processor, and memory that classifies blood samples into types like fasting, pre-breakfast, post-breakfast, etc., calculates evaluation parameters, and generates indicators for high or low glucose levels, displaying recognized patterns and prioritizing them for user awareness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the user interface of handheld diabetes management devices is simplified to reduce operational complexity, then ease of operation is improved, but the ability to configure reminders, classify measurements, and identify trends is worsened

Engineering Contradiction:
Improveease of operationVSAvoidadaptability or versatility
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The device automatically classifies blood glucose measurements into contextual categories (fasting, pre-meal, post-meal, bedtime) without requiring manual user input. The system self-configures reminder schedules based on detected patterns in measurement data, and automatically identifies trends without complex user configuration, thereby maintaining simplicity while enhancing adaptability

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The device performs preliminary analysis of blood glucose measurements to pre-configure appropriate reminder schedules and classification parameters before the user needs them. By proactively analyzing measurement patterns and pre-setting appropriate monitoring parameters, the system eliminates the need for complex user configuration while maintaining high adaptability to individual needs

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If automated classification and pattern recognition features are added to handheld diabetes management devices, then adaptability is improved, but device complexity is worsened

Engineering Contradiction:
Improveadaptability or versatilityVSAvoiddevice complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The device segments blood glucose measurements into distinct contextual categories (fasting, pre-breakfast, post-breakfast, pre-lunch, post-lunch, pre-dinner, post-dinner, bedtime) based on timing patterns. This segmentation allows complex adaptability to be achieved through simple temporal classification rules rather than requiring complex algorithmic analysis, thereby maintaining device simplicity while enhancing functional adaptability

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The device uses parameter changes in measurement timing and frequency to automatically adjust classification and trigger pattern recognition. By monitoring changes in when measurements are taken and how often they occur, the system adapts its behavior based on detected patterns without requiring complex user configuration or sophisticated algorithms, thus achieving high adaptability with minimal added complexity

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If multiple blood glucose measurement classifications are implemented, then measurement precision is improved, but difficulty of detecting and measuring is worsened

Engineering Contradiction:
Improvemeasurement precisionVSAvoiddifficulty of detecting and measuring
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The device automatically determines the contextual classification of each blood glucose measurement based on its timing relative to typical daily routines (meals, bedtime). The system self-configures appropriate classification parameters and automatically assigns categories without requiring user judgment or complex input, thereby achieving precise contextual measurement while maintaining ease of operation

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The device performs preliminary classification of measurements into contextual categories based on timing patterns before the user needs to interpret the data. By pre-processing measurements and automatically assigning appropriate classifications, the system eliminates the need for users to manually determine measurement context, thus achieving high measurement precision without increasing user burden

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3019084B1Reminder, classification, and pattern identification systems and methods for handheld diabetes management devices
Publication Date: 2019.04.24 ROCHE DIABETES CARE GMBH
  • EP3019084B1 patent drawingFigure 1~2
  • EP3019084B1 patent drawingFigure 3
  • EP3019084B1 patent drawingFigure 4

AI summary

A method includes: measuring a blood glucose (bG) level in a blood sample; storing the bG level and a time of receipt of the blood sample; storing a classification of the blood sample; in response to the receipt of the blood sample, selecting a group of stored bG levels having the classification of the blood sample and that were received within a predetermined period before receipt of the blood sample; calculating a bG evaluation parameter from the selected bG levels; evaluating the bG evaluation parameter in relation to first predetermined criteria, the first predetermined criteria including a first threshold indicative of a high bG level or a low bG level; selectively displaying an indication of recognition of a pattern in the selected bG levels when the bG evaluation parameter is greater than or less than the first threshold; and selectively removing the indication from the display.