Cardiac Condition Indicator Using Weighted Physiological Signal Trends

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for detecting congestive heart failure (CHF) decompensation events, particularly through ambulatory medical devices, face challenges in achieving high sensitivity and specificity due to signal noise and confounding factors, leading to unreliable detection of thoracic fluid accumulation and other indicative events.

Innovation Solution

A system that includes a sensor circuit to sense physiological signals, transform signal portions into baseline and short-term values, and generate a cardiac condition indicator using a weighted combination of relative differences, with weight factors determined by timing, to provide timely detection and potential therapy delivery.

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 and loss of localized sharp changes

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

Solution Approach 1:

The patent segments the physiological signal into multiple discrete sensor signals (e.g., impedance, heart rate, activity, respiration) and processes each separately through individual trend analyses and deviation calculations. This segmentation allows the system to capture localized sharp changes in specific signals without being blurred by smoothing operations on composite signals, while still achieving noise reduction through multi-signal correlation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from analyzing a single smoothed signal to analyzing multiple dimensions of physiological data simultaneously. By evaluating deviations across multiple sensor signals and combining them through a composite metric, the system achieves noise reduction through dimensional diversity rather than temporal smoothing, preserving the reliability of acute change detection.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Device complexity

If a single sensor signal is used for detection, then device complexity is reduced, but measurement precision deteriorates due to confounding factors and noise

Engineering Contradiction:
Improvesystem complexityVSAvoiddetection precision
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent merges multiple sensor signals (impedance, heart rate, activity, respiration) into a unified detection framework. Each signal is processed through similar trend analysis and deviation calculation methods, then combined into a composite metric that improves detection precision. This merging approach allows the system to achieve high measurement precision while maintaining manageable complexity through standardized processing pipelines.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent creates a universal detection algorithm that can process multiple types of physiological signals through the same analytical framework. The trend analysis, deviation calculation, and threshold evaluation methods are applied universally across different sensor modalities, enabling multi-functional detection without requiring separate complex processing paths for each signal type.

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

3Measurement precision

If signal filtering is applied to remove noise, then measurement precision is improved, but loss of information occurs due to removal of localized sharp changes

Engineering Contradiction:
Improvesignal clarityVSAvoidsignal detail loss
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent extracts trend information and deviation metrics from raw sensor signals without applying smoothing filters that would remove localized sharp changes. By calculating deviations from trending values and identifying acute changes through threshold-based detection, the system extracts meaningful information while preserving the integrity of rapid physiological changes that indicate worsening heart failure.

Inventive Principle:
Principle #2Taking out (Extraction)

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 detection of CHF decompensation events by improving sensitivity and specificity, allowing for timely intervention and reducing unnecessary medical interventions and healthcare costs.

Implementation Method 1

The ambulatory medical devices can include physiologic sensors which can be configured to sense electrical activity and mechanical function of the heart

Methodology Applied
Scientific EffectElectrical activity sensing: Electrical Impedance Tomography

Implementation Method 2

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

PatentEP3355985B1Predictions of worsening heart failure
Publication Date: 2020.11.25 CARDIAC PACEMAKERS INC
  • EP3355985B1 patent drawingFigure 1
  • EP3355985B1 patent drawingFigure 2
  • EP3355985B1 patent drawingFigure 3

AI summary

Systems and methods for detecting cardiac conditions such as events indicative of worsening heart failure are described. A system can include a sensor circuit to sense a physiological signal, transform one or more first signal portions of the physiological signal into one or more baseline values, and transform one or more second signal portions of the physiological signal into short-term values associated with respective timing information. The system can generate a cardiac condition indicator using a weighted combination of relative difference between the one or more short-term values and the one or more baseline values. The weighting can include one or more weight factors determined according to the timings of the one or more second signal portions. The system can output an indication of a progression over time of the cardiac condition indicator, or deliver therapy according to the cardiac condition indicator.