Developing a Falls Prediction Tool Using Both Accelerometer and Video Gait Analysis Data in Older Adults

NCT04354623 | Completed

• 1 other identifier: H19-03094
• Study Type: observational
• Target: 100
• Locations: 1 country
• Sites: 1

Brief Summary

Our group, consisting of academic clinicians and research engineers, seeks to create a database of stability measures (accelerometers, gyroscopes and altitude sensor data) in older adults monitored longitudinally. This Stability Measures (SM) database will allow us to use new machine learning methods to develop and then validate algorithms that predict future falls, allowing for better targeting of vulnerable patients.

Conditions

Fall Injury Prevention

Outcome Measures

Primary Outcomes (1)

• Classification of accuracy of the algorithm on the validation dataset

  Consisting of True positive (TP), False positive (FP) rate, Precision, Recall (similar to sensitivity), F-measure (conveys the balance between precision and recall) and the Receiver Operation Curve area

  60 min

Study Arms (2)

High Risk Subjects (n=50)

All subjects will be recruited from falls and geriatrics clinics at Vancouver General Hospital. These clinics see about 2500 patients per year and are currently used for research recruitment. Each clinic patient has gait speed measured, which will allow to recruit both high and low risk fallers. This test will allow us to recruit 50 subjects at marked risk for falls, providing us with prospectively gathered dataset of greater than 100 events, five times higher than any other sensor study.

Other: A 6-minute walk test

Low Risk Subjects (n=50)

We will use newspaper advertisements to recruit and then screen low risk subjects. All subjects will have a gait speed \> 0.8 m/s and have had no falls in the last year.

Other: A 6-minute walk test

Interventions

A 6-minute walk test OTHER

Each subject will perform a 6-minute walk test during which gait assessment will be obtained from the APDM system (Portland, OR). In addition there will be four video cameras (on the front, back and sides) that will measure raw video data for our gait analysis. The camera does not record any facial data (in fact, 'deepfake' software in the system deletes all facial details) and the patient's movements are converted to a 'stick figure' prior to being saved in the system.

Also known as: Video recording

High Risk Subjects (n=50); Low Risk Subjects (n=50)

Eligibility Criteria

• Age: 65 Years+
• Sex: all
• Age Groups: Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

We're planning to recruit 100 subjects from the Geriatric Medicine clinic at Vancouver General Hospital

You may qualify if:

• All subjects must be aged 65 years and older • All subjects must have had at least one fall in the last year and have been referred to the falls clinic (High Risk Subjects) OR have had no falls on the last year and have responded to our newspaper advertisement (Low Risk Subjects)

You may not qualify if:

• Subjects age less than 65 years old

Sponsors & Collaborators

• University of British Columbia: lead

Study Sites (1)

Vancouver Coastal Health Research Institute, VGH Research Pavilion Room 186

Vancouver, British Columbia, V5Z 1M9, Canada

Location

MeSH Terms

Interventions

Videotape Recording

Intervention Hierarchy (Ancestors)

Tape Recording; Audiovisual Aids; Educational Technology; Technology; Technology, Industry, and Agriculture; Television

Study Officials

• Kenneth Madden, MD

  UBC

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Division Head, Vancouver General Hospital Division of Geriatric Medicine Department of Medicine University of British Columbia

Study Record Dates

• First Submitted: April 16, 2020
• First Posted: April 21, 2020
• Study Start: April 15, 2025
• Primary Completion: April 15, 2026
• Study Completion: April 22, 2026
• Last Updated: May 1, 2026

Record last verified: 2026-04

Data Sharing

• IPD Sharing: Will not share

Locations

CA (1)