Entropy Detection via Delta Encoding and Lossless Compression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting atrial fibrillation and heart rate variability entropy are not suitable for continuous monitoring due to sensitivity to human error, discomfort from multiple electrodes, high computational complexity, and expense, making them unsuitable for long-term surveillance, especially in mobile devices with limited processing power.
Innovation Solution
A method using delta encoding and lossless compression of heart rate variability data from wrist or finger sensors or ECG signals to determine entropy levels, allowing for continuous, non-invasive, and computationally efficient monitoring of medical data, reducing false positives and errors from noise or small data defects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional automated methodology based on ECG with multiple electrodes is used, then detection accuracy of arrhythmias is improved, but patient comfort deteriorates and device complexity increases making it unsuitable for long term surveillance
Solution Approach 1:
The invention extracts the essential measurement function from complex multi-electrode ECG systems and implements it using a single photoplethysmography sensor. By taking out only the necessary sensing capability and implementing it through a simplified optical measurement approach, the system achieves adequate arrhythmia detection without the discomfort and complexity of multiple electrodes.
Solution Approach 2:
The invention replaces the mechanical/electrical contact-based ECG electrode system with an optical photoplethysmography sensing system. This substitution eliminates the need for skin contact with multiple electrodes, significantly improving patient comfort while enabling continuous long-term monitoring.
2Measurement precision
If known mathematical entropy analyses are used, then detection capability is improved, but computational complexity increases making them unsuitable for mobile devices with limited processing power
Solution Approach 1:
The invention replaces complex, computationally intensive mathematical entropy analysis algorithms with a simpler, more efficient entropy estimation method. This simpler approach consumes fewer computational resources and can be executed on mobile devices with limited processing power, while still providing reliable arrhythmia detection capability.
Solution Approach 2:
The invention changes the approach to entropy calculation from complex mathematical analysis to a simplified method based on detecting irregularities in pulse wave patterns. By changing the parameter of how entropy is computed (from complex mathematical transformations to pattern recognition), the system achieves the required detection capability with much lower computational complexity.
3Measurement precision
If known mathematical entropy analyses are used, then detection sensitivity is improved, but reliability deteriorates due to sensitivity to small errors and noise in measured data
Solution Approach 1:
The invention applies preprocessing steps including delta encoding and smoothing filters before entropy calculation. These preprocessing operations cushion the data against the effects of noise and small measurement errors before the entropy analysis is performed, preventing these errors from being amplified and ensuring more reliable detection results.
Solution Approach 2:
The invention introduces intermediary processing steps (delta encoding and smoothing) between the raw sensor data and the entropy calculation. These intermediary operations act as a buffer that reduces the impact of noise and errors, allowing the sensitive entropy detection to proceed on cleaned, more reliable data.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables reliable, continuous monitoring of entropy levels, reducing false alarms and improving data processing efficiency, making it suitable for mobile devices and long-term surveillance, while maintaining accuracy in detecting arrhythmias and critical illnesses.
Implementation Method 1
The medical data is received advantageously as waveform signals from the sensors, such as a photoplethysmography (PPG) sensor
Implementation Method 2
such as a photoplethysmography (PPG) sensor, an infrared (IR) sensor
Data Source
Figure 1~2
Figure 3
AI summary
A method for determining a degree of entropy of medical data from a waveform signal comprises steps of receiving the said medical data as a waveform, detecting a standard point, i.e. an apex of the wave, determining the beat-to-beat time period of the wave, converting the time period to a transient heart rate frequency, forming time series by using the sequential data of the said converted transient heart rate frequencies, and coding the said time series in the form of differences between sequential data. In addition, the said coded differences are compressed using a lossless compression method to form a result representing a degree of the compression.