Digital Stethoscope Respiratory Abnormality Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current digital stethoscopes face limitations in real-time performance, inability to forecast respiratory events, and inadequate data management while ensuring patient privacy, particularly in detecting respiratory abnormalities and predicting their severity.

Innovation Solution

A digital stethoscope system that employs convolutional neural networks to analyze auditory signals, tracks coughs, predicts respiratory event likelihood, and forecasts future respiratory events by generating and transmitting data to a cloud-based service, while incorporating a base station for enhanced processing and wireless charging.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If traditional stethoscopes are used for respiratory diagnosis, then a doctor can detect abnormalities through auscultation, but the system requires a doctor to be present and cannot enable daily monitoring at patient's home

Engineering Contradiction:

Improveautomation of respiratory abnormality detectionVSAvoidcomplexity of detection system

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical acoustic detection system (traditional stethoscope requiring manual auscultation) with a digital electronic system that uses microphones, processors, and machine learning algorithms to automatically detect and classify respiratory sounds, enabling automated monitoring without requiring a doctor present

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-monitoring by providing automated detection capabilities that can operate independently without medical professional intervention. The device performs self-diagnosis through embedded processors and classification algorithms, allowing patients to monitor their own respiratory conditions at home

Inventive Principle:

Principle #25Self-service

2Reliability

If classification algorithms are used to distinguish normal from abnormal noises, then detection accuracy improves, but real-time performance is insufficient for local execution on patient's device

Engineering Contradiction:

Improveaccuracy of respiratory abnormality detectionVSAvoidreal-time processing speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent optimizes the machine learning model parameters and architecture to achieve real-time performance. This includes selecting appropriate classification algorithms, adjusting processing thresholds, and optimizing computational parameters to enable fast local execution while maintaining high detection accuracy

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system performs selective processing by focusing computational resources on the most critical detection tasks. The processor analyzes auditory signals through machine learning classification, but can prioritize certain analysis depth based on urgency, performing comprehensive analysis when needed while using lighter processing for routine monitoring

Inventive Principle:

Principle #16Partial or excessive action

3Adaptability or versatility

If coughs are tracked and data is transmitted to cloud-based service, then forecasting capabilities improve, but patient privacy protection becomes more challenging

Engineering Contradiction:

Improveforecasting of respiratory eventsVSAvoidpatient privacy risk

Core Design Contradiction:

Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The patent uses a cloud-based service as an intermediary that processes aggregated data remotely. The system transmits anonymized respiratory data to the cloud for analysis while maintaining patient privacy through secure transmission protocols and data encryption, allowing forecasting capabilities without direct exposure of sensitive patient information

Inventive Principle:

Principle #24Intermediary (Mediator)

4Measurement precision

If convolution procedure is used to generate features from auditory spectrogram, then detection performance improves, but computational requirements increase

Engineering Contradiction:

Improveprecision of respiratory abnormality detectionVSAvoidcomputational energy consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent divides the complex convolutional feature extraction process into discrete computational stages. The processor segments the auditory signal processing into sequential operations (spectrogram generation, convolution application, feature extraction), allowing optimized energy consumption at each stage and enabling real-time execution on mobile devices

Inventive Principle:

Principle #1Segmentation

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 real-time detection and prediction of respiratory abnormalities, improves forecasting capabilities, and ensures secure data management, allowing for timely patient intervention and enhanced monitoring.

Implementation Method 1

receiving, from a microphone, an auditory signal

Methodology Applied

Scientific EffectElectroacoustic transduction:

Data Source

PatentUS11696703B2Digital stethoscope for detecting a respiratory abnormality and architectures thereof

Publication Date: 2023.07.11 SONAVI LABS INC

AI summary

Embodiments disclosed herein improve digital stethoscopes and their application and operation. A first method detects of a respiratory abnormality using a convolution. A second method counts coughs for a patient. A third method predicts a respiratory event based on a detected trend. A fourth method forecasts characteristics of a future respiratory event. In a fifth embodiment, a base station is provided for a digital stethoscope.