Heart Failure Detection Using Dynamic Reference Signals

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current medical devices for monitoring congestive heart failure (CHF) patients face challenges in accurately detecting worsening heart failure decompensation events due to noise interference and signal drift over time, which can lead to low sensitivity and inappropriate detection of worsening or improvement in heart failure status.

Innovation Solution

A system that includes a signal input circuit to sense physiological signals, transforming them into baseline statistical values, historical extreme values, and short-term values, and generates a cardiac condition indicator using relative differences between short-term and reference values, allowing for timely detection of worsening heart failure events.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If signal filtering or smoothing is used to reduce noise, then measurement precision is improved, but reliability deteriorates due to signal drift over time

Engineering Contradiction:
Improvedetection accuracyVSAvoiddetection reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent implements a dynamic reference signal generation system that continuously adapts to changing patient conditions. Instead of using a fixed reference value, the system dynamically updates the reference signal based on rolling time windows and statistical parameters (mean, standard deviation) calculated from recent historical data. This allows the detection algorithm to maintain reliability despite signal drift over time, as the reference automatically adjusts to new baseline conditions while still providing noise filtering benefits.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the parameters used for reference signal generation from static values to dynamic statistical parameters. By calculating the mean and standard deviation of physiological signals over rolling time windows and using these statistical parameters to define the reference signal, the system adapts to signal drift while maintaining detection precision. The detection thresholds are also dynamically adjusted based on these changing parameters.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If data-smoothing window is used to generate reference signal, then measurement precision is improved, but loss of information occurs from historical sensor data

Engineering Contradiction:
Improvereference signal accuracyVSAvoidhistorical data power
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The system performs preliminary analysis of historical data to establish statistical baselines before using them for detection. By pre-calculating the mean and standard deviation over rolling time windows and storing these statistical parameters, the system preserves the informational content of historical data in a compressed form that can be efficiently used for real-time detection without losing the ability to recognize target events.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system transforms the raw historical sensor data into statistical parameters (mean, standard deviation, percentiles) that capture the essential characteristics of the historical data distribution. This parameter transformation preserves the informational power of historical data while enabling efficient real-time comparison and detection, avoiding the need to store and process all raw historical data points.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If multiple sensors are used to improve detection accuracy, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
ImproveHF decompensation detection accuracyVSAvoidsensor integration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent merges multiple sensor inputs (impedance, heart rate, respiration rate, activity level) into a unified detection framework. Instead of analyzing each sensor independently, the system combines these diverse physiological parameters into a composite detection algorithm that evaluates them collectively. This merging approach improves detection precision by considering multiple aspects of cardiac function simultaneously while managing complexity through integrated processing.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The detection system is designed with multi-functionality to handle various sensor types and physiological parameters through a single unified algorithmic framework. The system can process impedance data, heart rate variations, respiration patterns, and activity levels using the same statistical comparison methodology, making the device versatile and reducing the need for separate analysis modules for each sensor type.

Inventive Principle:
Principle #6Universality (Multi-functionality)

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

This approach enhances the accuracy and reliability of detecting heart failure decompensation events by integrating historical data with real-time signal analysis, reducing false positives and negatives and improving patient management.

Implementation Method 1

Techniques such as signal filtering or smoothing can be used to produce a less noisy reference sensor signal

Methodology Applied
Scientific EffectSignal filtering: Filter (electronic)

Implementation Method 2

signal filtering or smoothing may not be effective in some circumstances

Methodology Applied
Scientific EffectSignal smoothing: Filter (electronic)

Implementation Method 3

using transthoracic impedance or other sensor signals to detect a disease or a disease condition. For example, fluid accumulation in the lungs decreases the transthoracic impedance due to the lower resistivity of the fluid than air in the lungs

Methodology Applied
Scientific EffectElectrical impedance: Electrical Resistance

Data Source

PatentEP3367884B1Prediction of worsening of heart failure
Publication Date: 2020.07.22 CARDIAC PACEMAKERS INC
  • EP3367884B1 patent drawingFigure 1
  • EP3367884B1 patent drawingFigure 2
  • EP3367884B1 patent drawingFigure 3

AI summary

Systems and methods for detecting cardiac conditions such as events indicative of worsening of heart failure (HF) are described. A system can receive a physiological signal from a patient, transform one or more first portions of the physiological signal into respective one or more baseline statistical values, transform one or more second portions of the physiological signal into one or more historical extreme values, and generate one or more reference values of a physiologic parameter using the baseline statistical values and the historical extreme values. The system can transform one or more third signal portions of the physiological signal into respective one or more short-term values, and produce a cardiac condition indicator using a combination of relative differences between the short-term values and the corresponding reference values. The system can output the cardiac condition indicator, or deliver therapy according to the cardiac condition indicator.