Fundamental Intelligent Building Blocks of the Intensive Care Unit (ICU) of the Future: Intelligent ICU of the Future

NCT03905668 | Active Not Recruiting

• 5 other identifiers: IRB201900354 -N1R21EB027344-011750192OCR20330R01NS120924-01
• Study Type: observational
• Target: 71
• Locations: 1 country
• Sites: 1

Brief Summary

The objective of this project is to create deep learning and machine learning models capable of recognizing patient visual cues, including facial expressions such as pain and functional activity. Many important details related to the visual assessment of patients, such as facial expressions like pain, head and extremity movements, posture, and mobility are captured sporadically by overburdened nurses or are not captured at all. Consequently, these important visual cues, although associated with critical indices, such as physical functioning, pain, and impending clinical deterioration, often cannot be incorporated into clinical status. The study team will develop a sensing system to recognize facial and body movements as patient visual cues. As part of a secondary evaluation method the study team will assess the models ability to detect delirium.

Conditions

Pain; Delirium

Outcome Measures

Primary Outcomes (1)

• Defense Veterans Pain Reporting Scale (DVPRS)

  Before discharge, patients will be shown three short video clips from their ICU admission and asked to rate their pain levels using the Defense Veterans Pain Reporting Scale. DVPRS is a 10 point visual scale used to self report pain (0-4 being mild pain; 5-7 being moderate pain; 8-10 being severe pain).

  Before hospital discharge, up to Day 8

Study Arms (2)

ICU Patients

Adults in admitted to an ICU at University of Florida Health Gainesville with an expected length of stay greater than 24 hours which are not on any form of contact precaution or isolation. Patients will have continuous video, accelerometer, and electromyographic monitoring for up to seven days while in the ICU.

Other: Video Monitoring; Other: Accelerometer Monitoring; Other: Electromyographic Monitoring; Other: Noise Level Monitoring; Other: Light Level Monitoring

ICU Patient Friends/Family Members

Adult visitors of participating ICU patients that are willing to provide feedback to the learning algorithms.

Interventions

Video Monitoring OTHER

Patients may have video monitoring for up to seven days while in the ICU. The video system will be placed in an unobtrusive area in the patient's ICU room.

ICU Patients

Accelerometer Monitoring OTHER

Patients may have accelerometer monitoring for up to seven days while in the ICU. Commercially available accelerometer units, which have been validated in previous clinical studies, will be used.

ICU Patients

Electromyographic Monitoring OTHER

Patients may have electromyographic monitoring for up to seven days while in the ICU.

Also known as: EMG monitoring

ICU Patients

Noise Level Monitoring OTHER

Patients may have noise level monitoring (in decibels) for up to seven days while in the ICU.

ICU Patients

Light Level Monitoring OTHER

Patients may have light level monitoring for up to seven days while in the ICU.

ICU Patients

Eligibility Criteria

• Age: 18 Years - 100 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adults in the ICU or Adults visiting recruited patients in the ICU

You may qualify if:

• patient admitted to University of Florida (UF) Health Gainesville ICU

You may not qualify if:

• Anticipated ICU stay is less than one day
• Patient is on any form of contact precaution or isolation
• Patient is unable to wear a Shimmer3 unit
• ICU Patient Friends/Family:
• Individual has their name designated on a patient's informed consent form giving them permission to view and modify facial and activity data collected about that patient
• Age \< 18
• They are unable to answer short questions on a touch screen display
• They are unable to wear a proximity sensor
• They were not on the listed of designated individuals specified in their friend/family members informed consent form

Sponsors & Collaborators

• University of Florida: lead
• National Institute for Biomedical Imaging and Bioengineering (NIBIB): collaborator
• U.S. National Science Foundation: collaborator
• National Institutes of Health (NIH): collaborator
• National Institute of Neurological Disorders and Stroke (NINDS): collaborator

Study Sites (1)

UF Health Shands Hospital

Gainesville, Florida, 32608, United States

Location

MeSH Terms

Conditions

Pain; Delirium

Condition Hierarchy (Ancestors)

Neurologic Manifestations; Signs and Symptoms; Pathological Conditions, Signs and Symptoms; Confusion; Neurobehavioral Manifestations; Nervous System Diseases; Neurocognitive Disorders; Mental Disorders

Study Officials

• Azra Bihorac, MD

  University of Florida

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: April 3, 2019
• First Posted: April 5, 2019
• Study Start: February 3, 2016
• Primary Completion: January 18, 2022
• Study Completion (Estimated): July 1, 2028
• Last Updated: June 3, 2025

Record last verified: 2025-06

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)