A framework to automatically detect near-falls using a wearable inertial measurement cluster
2024

Detecting Near-Falls with Wearable Sensors

Sample size: 18 publication 10 minutes Evidence: high

Author Information

Author(s): Maximilian Gießler, Julian Werth, Bernd Waltersberger, Kiros Karamanidis

Primary Institution: Offenburg University of Applied Sciences

Hypothesis

The IMC will enhance accuracy in near-fall detection, reducing false detections of trips and slips among activities of daily living.

Conclusion

The proposed wearable IMC and framework can accurately identify near-falls and balance disturbances during daily life tasks.

Supporting Evidence

  • The IMC achieved 100% sensitivity in detecting balance disturbances.
  • The framework showed 98.4% specificity with only seven false positives.
  • Personalized thresholds improved detection accuracy for individual gait characteristics.
  • The study demonstrated the feasibility of remote fall risk assessment.
  • Results indicated that the IMC outperformed a single IMU in detecting near-falls.
  • The framework can classify types of perturbations accurately.
  • Findings suggest potential for long-term monitoring of fall risk.
  • The approach may help in clinical and research settings for assessing fall risk.

Takeaway

Researchers created a smart sensor that can tell when someone is about to fall, helping to keep people safe.

Methodology

The study used a wearable inertial measurement cluster to assess trunk kinematics during various locomotion tasks.

Potential Biases

The participant group was homogeneous, which may not represent the broader population.

Limitations

The study had a small sample size and was conducted in a controlled environment, limiting generalizability.

Participant Demographics

18 healthy young adults (8 females, 10 males) aged 26 to 31 years.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1038/s44172-024-00325-x

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication