Validating Wireless Gait Sensor for Elderly Fall Risk Classification

A Study on Validation of Gait Analysis Wireless Small Inertial Sensor and Diagnostic Machine Learning Model for Classification of Elderly Fall Risk Group

The walking status of elderly patients over 65 years of age in the hospital will be verified through political analysis and objective fall risk assessment through wireless inertial sensors and diagnostic machine learning models, and based on the results, As investigators, providing a foundation for the objective evaluation of the risk of falling patients by nurses in general wards in the future.

Study Overview

• Status: Completed
• Conditions: Elderly Person
• Intervention / Treatment: Device: Walking analysis sensor

Detailed Description

Currently, in the case of general clinical wards in Korea, the evaluator who assesses the risk of falling during the patient's hospitalization changes every time, and the evaluation of fall risk differs for the same patient depending on the subjectivity of the evaluator. Hence, evaluating falls requires assessing the patient's walking based on consistent criteria. Through walking analysis with a wireless small inertial sensor, there is an expectation that the incidence of fall risk will decrease. When analyzing walking to classify fall risk groups, quantitative evaluation should be applied for stride length, gait speed, step width, cadence, and gait cycle, but currently, fall assessments taking this into account are not properly conducted. Therefore, it is necessary to prepare and apply quantitative standards for fall evaluation through walking analysis through wireless small inertial sensors and data machine learning to classify the risk of falling in elderly hospitalized patients.

• Study Type: Interventional
• Enrollment (Actual): 51
• Phase: Not Applicable

Contacts and Locations

Study Locations

• Korea, Republic of
  • Yangsan, Korea, Republic of
    • Sungchul Huh, MD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

1. a person over the age of 55
2. Persons who can walk independently for at least one minute
3. Those who do not take drugs that affect their ability to maintain balance
4. A person who does not have an orthopedic problem such as a fracture of the lower extremities within six months

Exclusion Criteria:

1. Those who have difficulty understanding the gait analysis program or difficulty expressing symptoms
2. A person deemed unfit for this study by a rehabilitation specialist due to other conditions
3. A person who is unable to apply this walking analysis program due to serious cardiovascular diseases

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Gait group; Those aged 55 years or older; Those who can walk independently for at least 1 minute; Those who are not taking medications that affect the ability to maintain balance; Those who have not had any orthopedic problems such as lower limb fractures within the past 6 months	Device: Walking analysis sensor; Participant gait analysis with the inertial sensor

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Falls Risk Assessment Scale	A falls risk assessment scale measured through the analysis of patients' gait using wireless inertial sensors and a diagnostic machine learning model.	Patient gait data is collected continuously throughout the study period, enabling the ongoing measurement of falls risk.

Collaborators and Investigators

• Sponsor: Pusan National University Yangsan Hospital
• Collaborators: Pusan National University
• Investigators: Principal Investigator: Sungchul Huh, PhD, Pusan National University Yangsan Hospital

Study record dates

Study Major Dates

• Study Start (Actual): December 1, 2023
• Primary Completion (Actual): January 5, 2024
• Study Completion (Actual): April 30, 2024

Study Registration Dates

• First Submitted: December 21, 2023
• First Submitted That Met QC Criteria: May 2, 2024
• First Posted (Actual): May 3, 2024

Study Record Updates

• Last Update Posted (Actual): June 22, 2025
• Last Update Submitted That Met QC Criteria: June 17, 2025
• Last Verified: June 1, 2025

More Information

Terms related to this study

• Keywords: Walking analysis; Fall Risk Assessment; Machine Running
• Other Study ID Numbers: 11-2023-001

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No