Autonomous Navigating Robot for Detecting Falls and Risk of Falls in Nursing Home Residents With Alzheimer Disease/ADRD - Feasibility Study

Autonomous Navigating Robot for Detecting Falls and Risk of Falls in Nursing Home Residents With Alzheimer Disease/ADRD

This study is a feasibility study to prove that an autonomously navigating robot can patrol nursing home rooms day and night and detect if a resident has fallen, turn on ambient light at night and a video camera and allow nursing staff to view and assess the situation through the robot video camera and communicate with the resident through the robot screen.

Study Overview

• Status: Terminated
• Conditions: Fall in Nursing Home

Detailed Description

Intervention Protocol Prior to sending the robot on patrol to detect whether a resident is attempting to get up from the chair or bed or if a resident fell, we will get residents used to the robot. We will do this through the morning musical wake up tour playing "Oh What a Beautiful Morning" for a month. We will explain to the residents that the robot will come to "visit" them on a regular basis to see how they are doing and demonstrate how the robot comes and observes them. Using an infra-red camera and artificial intelligence, the robot can find where a human is located in the room and in what position. If it visits a private room and the robot "sees" that a resident is not on the floor or is on her/his wheel chair or couch or in bed and is not attempting to get up or out of bed or stand up, it will just turn around and leave the room without interrupting the resident. If it detects that a human is on the floor, it will say "This is temi the robot, I am getting help". It will turn on ambient light, alert staff and turn on the robot video camera to facilitate communication between the staff and the resident so staff can assess the situation and take proper action. If it detects that there is more than one human in the room and no human is on the floor, it will leave the room. If there is another human in the room and one human is on the floor, it will alert staff. If the second person in the room is a staff member, s/he will be able to click a button on the robot screen to send it to continue the patrol and it will leave the room and continue the patrol. If the room is a semiprivate room and there are two residents living there, the robot will check on one resident and if s/he is not at risk it will turn around and check the status of the second resident. If both are resting, the robot will leave the room without interrupting the residents. If the robot detects that a resident is attempting to get up or out of bed it will say: "this is temi the robot, please sit, I am getting help". It will turn on ambient light and its video camera and alert staff. If it detects that a resident is on the floor, it will perform the procedure described above. If a staff member is already in a semi-private room where there was a fall, s/he will be able to send the robot to continue the patrol or task as described in the private room. All falls reported by the robot will have an image captured so that the fall can be verified by research staff. Falls reported by the staff and robot will be tabulated according to their concordance: 1) Robot correctly detected and reported but staff did not record a fall; 2) staff reported fall but robot did not; 3) robot correctly and staff reported a fall; and, 4) robot reports fall: no image in robot recording to validate that a fall occurred and staff does not report a fall.

• Study Type: Observational
• Enrollment (Actual): 40

Contacts and Locations

Study Locations

• United States
  • Rhode Island
    • Providence, Rhode Island, United States, 02903
      • Steere House Nursing & Rehabilitation Center

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

Nursing home residents living with dementia

Description

Inclusion Criteria:

• Nursing home resident living with dementia

Exclusion Criteria:

• Residents on isolation precautions (e.g. Clostridoides difficile, COVID 19, MRSA)
• Actively dying resident
• Resident and/or family decline
• Functional or structural quadriplegia with inability to mobilize with little to no risk of falling
• Residents become agitated when the robot engages with them

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort
A robot will patrol the rooms of nursing home residents to detect falls; Nursing home residents in a long-term-care memory unit

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Feasibility of a robot to detect falls in a nursing home	The Primary Outcome Measure is that 95% of the time the robot correctly detected that a resident fell, was able to turn on ambient light, alert nursing staff, turn on the video camera and facilitate communication between the resident and nursing staff.	during three months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Nursing staff satisfaction with the robot detection of falls	75% of nursing staff said that the fall detection system improved their ability to provide safe care	during three months
The robot was able to detect falls in the nursing home before the nursing staff	That in more than 30% of falls the robot detected the falls before the nursing staff.	During three months

Collaborators and Investigators

• Sponsor: Vigorous Mind, Inc.
• Investigators: Principal Investigator: Lynn McNicoll, BS, MDCM, Brown University Health

Publications and helpful links

General Publications

• Malinsky Y,McNicoll L,Gravenstein S

Study record dates

Study Major Dates

• Study Start (Actual): July 31, 2025
• Primary Completion (Actual): July 31, 2025
• Study Completion (Actual): August 31, 2025

Study Registration Dates

• First Submitted: February 27, 2026
• First Submitted That Met QC Criteria: February 27, 2026
• First Posted (Actual): March 5, 2026

Study Record Updates

• Last Update Posted (Actual): March 5, 2026
• Last Update Submitted That Met QC Criteria: February 27, 2026
• Last Verified: February 1, 2026

More Information

Terms related to this study

• Keywords: Using a robot for fall detection in nursing homes
• Other Study ID Numbers: VMRFalls1; 1R43AG082599-01 (U.S. NIH Grant/Contract)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: No IPD is collected

Drug and device information, study documents

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