EEG Signal Analysis for Hypoglycemia Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Individuals, particularly diabetics, often cannot sense when their blood sugar levels reach critically low levels, leading to hypoglycemic attacks, which can be severe and limit their activities, and existing methods for predicting these attacks are inadequate due to inter-patient variability in EEG signals.

Innovation Solution

A computer-based method for detecting hypoglycemia by analyzing EEG signals, involving frequency band components, intensity measures, long-term estimates of mean and variability, normalization, and machine analysis to classify the probability of hypoglycemia, integrating probabilities over time, and excluding signal artifacts to provide accurate warnings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If EEG signals are analyzed using simple methods, then the device complexity is reduced, but the measurement precision and reliability of hypoglycemia detection deteriorates due to inter-patient variability and false alarms

Engineering Contradiction:

Improvecomplexity of EEG analysis methodVSAvoidprecision of hypoglycemia detection

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The EEG signal analysis is segmented into multiple frequency bands (delta, theta, alpha, beta, gamma) with specific frequency ranges. Each band is processed separately to extract relevant features, allowing the system to capture different aspects of brain activity related to hypoglycemia while maintaining manageable complexity through structured decomposition

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system transforms raw EEG signals into multiple derived parameters including power spectral density, coherence, and phase-locking values across different frequency bands. These parameter transformations enable precise detection of hypoglycemic states by capturing subtle changes in brain activity that would be imperceptible in raw signals

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If EEG analysis considers only the occurrence and rate of EEG changes, then the device complexity is reduced, but the reliability of detection deteriorates due to false alarms from sporadic EEG events

Engineering Contradiction:

Improvecomplexity of analysis algorithmVSAvoidreliability of hypoglycemia prediction

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system performs preliminary analysis by computing long-term mean and variability estimates for each frequency band before detecting hypoglycemic events. This preparatory processing establishes baseline characteristics that enable more reliable detection by distinguishing true hypoglycemic patterns from sporadic artifacts

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system integrates probability values over a selected time period to produce a cumulative indication of hypoglycemia likelihood. This feedback mechanism allows the system to distinguish between transient sporadic EEG events and sustained hypoglycemic patterns, significantly reducing false alarms while maintaining reliability

Inventive Principle:

Principle #23Feedback

3Device complexity

If a common learning set is used for all patients, then the device complexity and training time are reduced, but the measurement precision deteriorates due to inter-patient variability in EEG signals

Engineering Contradiction:

Improvecomplexity of training procedureVSAvoidprecision of individual patient detection

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system adapts to individual patient characteristics by computing patient-specific long-term mean and variability estimates for each frequency band. This local customization allows the analysis to account for inter-patient variability in EEG signals while maintaining a relatively simple overall system architecture that doesn't require extensive personalized training

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS10327656B2Analysis of EEG signals to detect hypoglycaemia

Publication Date: 2019.06.25 UNEEG MEDICAL AS

AI summary

Apparatus for detecting hypoglycemia or impending hypoglycemia by analysis of an EEG comprises at least one EEG measuring electrode (10) for gathering an EEG signal and a computer (12) for receiving said EEG signals programmed to obtain a plurality of signal components each comprising a different band of frequencies, obtain a measure of the varying intensity of each said component, obtain a long time estimate of the mean of each intensity measure, obtain a long time estimate of the variability of each intensity measure, normalise each intensity measure e.g. by a subtracting from the intensity measure the long time estimate of the mean and dividing the result by the long time estimate of the variability so as to generate from each band a normalised feature, use machine analysis of the normalised features to obtain a varying cost function, classify values of the cost function according to the probability of the cost function being indicative of hypoglycemia, integrate the probabilities obtained during a selected time period, and determine that the EEG signals are indicative of hypoglycemia being present or being impending based on said integration.