Walking-and-Talking Fall Risk Detection Using Accelerometer and Voice

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing medical devices fail to effectively predict falls in individuals by integrating real-time monitoring of walking and talking activities, which are known indicators of fall risk, particularly in elderly populations.

Innovation Solution

A device or system that includes accelerometer circuitry to detect walking and a microphone to capture voice, processing circuitry to determine when a person is walking and talking, and calculates the risk of falling based on this combination.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If existing medical devices are used to monitor patient activities, then basic movement detection is provided, but fall risk prediction capability is insufficient

Engineering Contradiction:
Improvefall risk prediction accuracyVSAvoidmonitoring system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines accelerometer data (movement detection) and microphone data (voice detection) into a unified fall risk assessment system. The processing circuitry integrates multiple sensor inputs to generate a composite fall risk score, merging previously separate monitoring functions into a single predictive system that improves reliability without requiring entirely new device architecture

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The monitoring system is designed to perform multiple functions: detecting walking activity, detecting talking activity, and predicting fall risk. By making the system universal across these different monitoring needs, the patent avoids requiring separate specialized devices for each function, thereby improving prediction capability while managing overall system complexity

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

2Measurement precision

If accelerometer and microphone sensors are integrated to detect walking and talking, then fall risk detection capability is improved, but device complexity increases

Engineering Contradiction:
Improvewalking and talking detection accuracyVSAvoidsensor integration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the monitoring function into distinct sensor modules (accelerometer for movement, microphone for voice) that can be independently optimized and calibrated. The processing circuitry handles each sensor type separately before integrating the data, which simplifies the overall integration process while maintaining high measurement precision for each individual sensor

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The processing circuitry acts as an intermediary that receives raw data from both accelerometer and microphone sensors, processes each data stream independently through appropriate algorithms, and then combines the processed information. This intermediary processing layer simplifies the integration complexity by providing a structured interface between diverse sensor types and the final fall risk assessment output

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If real-time monitoring of walking and talking is performed, then fall risk prediction is enhanced, but energy consumption increases

Engineering Contradiction:
Improvereal-time fall risk assessmentVSAvoiddevice power consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs monitoring at periodic intervals rather than continuously, with the processing circuitry evaluating accelerometer and microphone data at scheduled time points. This periodic sampling approach maintains real-time fall risk prediction capability while significantly reducing average power consumption compared to continuous monitoring of all sensors

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The processing circuitry selectively activates full monitoring functions only when fall risk is suspected or during high-risk periods, rather than maintaining maximum monitoring intensity at all times. This partial action approach concentrates energy usage on critical assessment moments while reducing overall power consumption during low-risk periods

Inventive Principle:
Principle #16Partial or excessive action

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

Provides an objective measure of fall risk by determining whether a person is talking while walking, aiding in guiding therapies and predicting potential falls.

Implementation Method 1

accelerometer circuitry configured to generate at least one signal indicative of a person walking

Methodology Applied
Scientific EffectAccelerometer: Accelerometer

Implementation Method 2

a microphone configured to capture a voice of the person

Methodology Applied
Scientific EffectSound: Sound

Data Source

PatentEP4366604B1Predicting a likelihood of a fall based on walking but not talking
Publication Date: 2026.02.04 MEDTRONIC INC
  • EP4366604B1 patent drawingFigure 1
  • EP4366604B1 patent drawingFigure 2
  • EP4366604B1 patent drawingFigure 3

AI summary

An example device or system and method includes accelerometer circuitry configured to generate at least one signal, a microphone configured to capture a voice of a person, a memory, and processing circuitry communicatively coupled to the accelerometer circuitry, the microphone, and the memory. The processing circuitry is configured to determine when the person is walking based on the at least one signal and determine when the person is talking based on the captured voice. The processing circuitry is configured to determine a risk of falling based on the determination of when the person is walking and the determination of when the person is talking.