Pervasive Sensing and AI in Intelligent ICU

NCT05127265 | Recruiting

• 3 other identifiers: IRB-202101013R01NS120924R01EB029699
• Study Type: observational
• Target: 400
• Locations: 1 country
• Sites: 1

Brief Summary

Important information related to the visual assessment of patients, such as facial expressions, 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, delirious state, and impending clinical deterioration, often cannot be incorporated into clinical status. The overall objectives of this project are to sense, quantify, and communicate patients' clinical conditions in an autonomous and precise manner, and develop a pervasive intelligent sensing system that combines deep learning algorithms with continuous data from inertial, color, and depth image sensors for autonomous visual assessment of critically ill patients. The central hypothesis is that deep learning models will be superior to existing acuity clinical scores by predicting acuity in a dynamic, precise, and interpretable manner, using autonomous assessment of pain, emotional distress, and physical function, together with clinical and physiologic data.

Conditions

Critical Illness; Pain; Delirium; Confusion

Keywords

Critical Illness; Pain; Delirium; Confusion; Patient Acuity; ICU; Acute Illness

Outcome Measures

Primary Outcomes (8)

• Algorithmic Activity Labeling

  The algorithm's output will report on which activity the patient is performing in the corresponding image data.

  Image frames collected continuously for up to 7 days maximum.

• Algorithmic Pain Labeling

  The algorithm's output will report on whether the patient is experiencing pain in the corresponding image data.

  Image frames collected continuously for up to 7 days maximum.

• Decibel Levels

  Determine relative decibel (noise loudness) levels in study patient's ICU room to alert for abnormalities in decibel level (noisiness of environment).

  Noise sensor data collected continuously for up to 7 days maximum.

• Lux Levels

  Determine relative lux (light illumination) levels in study patient's ICU room to alert for abnormalities in illumination level.

  Light sensor data collected continuously for up to 7 days maximum.

• Air Quality

  Determines relative air quality pollution levels in study patient's ICU room to alert for abnormalities in room air quality.

  Air quality sensor data collected continuously for up to 7 days maximum.

• Circadian Dyssynchrony Index

  Blood and urine samples will be collected and processed to determine the presence of dyssynchrony in a subject's internal circadian clock.

  Change in internal circadian profile from Day 1 to Day 2.

• Algorithmic Delirium Recognition Profile

  The algorithm's output will report on whether patient is likely to be delirious or at-risk of delirium based on activity, facial expression, and circadian dyssynchrony index data collected from study devices and biosamples.

  Data collected for up to 7 days maximum.

• Delirium Motor Subtyping Scale 4 (DMSS-4)

  Determines which subtype of delirium a subject is experiencing. This subtyping scale has 13 symptom items (5 hyperactive and 8 hypoactive) derived from the 30-item Delirium Motor Checklist. To subtype a delirious subject, at least 2 symptoms are required to be present from either the hyperactive or hypoactive checklist to meet the subtyping criteria for 'hyperactive delirium' or 'hypoactive delirium'. Patients who meet both hyperactive and hypoactive criteria are determined as 'mixed subtype', while patients meeting neither hyperactive or hypoactive criteria are labeled as 'no subtype'.

  Changes from baseline up to a maximum of 7 days

Secondary Outcomes (1)

• Mortality

  From baseline (study enrollment) up to a maximum of 7 days

Study Arms (1)

adult ICU patients

adult patients aged 18 or older admitted to University of Florida Health Shands Gainesville ICU wards

Other: Video Monitoring; Other: Accelerometer Monitoring; Other: Noise Level Monitoring; Other: Light Level Monitoring; Other: Air Quality Monitoring; Other: EKG Monitoring; Other: Vitals Monitoring; Other: Biosample Collection; Other: Delirium Motor Subtyping Scale 4 (DMSS-4)

Interventions

Video Monitoring OTHER

continuous video monitoring

adult ICU patients

Accelerometer Monitoring OTHER

continuous accelerometer monitoring of patient movements

adult ICU patients

Noise Level Monitoring OTHER

continuous environmental noise monitoring

adult ICU patients

Light Level Monitoring OTHER

continuous environmental light monitoring

adult ICU patients

Air Quality Monitoring OTHER

continuous environmental air quality monitoring

adult ICU patients

EKG Monitoring OTHER

continuous EKG monitoring

adult ICU patients

Vitals Monitoring OTHER

continuous vitals monitoring (heart rate, oxygen saturation)

adult ICU patients

Biosample Collection OTHER

blood and urine samples collected once on Day 1 and once on Day 2

adult ICU patients

Delirium Motor Subtyping Scale 4 (DMSS-4) OTHER

done daily on delirious patients to subtype delirium

adult ICU patients

Eligibility Criteria

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

Study Population

Critically ill adults, aged 18 and over, admitted to UF Health Shands Gainesville ICU wards

You may qualify if:

• aged 18 or older
• admitted to UF Health Shands Gainesville ICU ward
• expected to remain in ICU ward for at least 24 hours at time of screening

You may not qualify if:

• under the age of 18
• on any contact/isolation precautions
• expected to transfer or discharge from the ICU in 24 hours or less
• unable to provide self-consent or has no available proxy/LAR

Sponsors & Collaborators

• University of Florida: lead
• National Institute of Neurological Disorders and Stroke (NINDS): collaborator
• National Institute for Biomedical Imaging and Bioengineering (NIBIB): collaborator

Study Sites (1)

University of Florida Health Shands Hospital

Gainesville, Florida, 32610, United States

RECRUITING

Related Publications (1)

• Davoudi A, Malhotra KR, Shickel B, Siegel S, Williams S, Ruppert M, Bihorac E, Ozrazgat-Baslanti T, Tighe PJ, Bihorac A, Rashidi P. Intelligent ICU for Autonomous Patient Monitoring Using Pervasive Sensing and Deep Learning. Sci Rep. 2019 May 29;9(1):8020. doi: 10.1038/s41598-019-44004-w.

  PMID: 31142754 BACKGROUND

Biospecimen

Retention: SAMPLES WITH DNA

Blood and urine collection on two consecutive days of the study.

MeSH Terms

Conditions

Critical Illness; Pain; Delirium; Confusion

Condition Hierarchy (Ancestors)

Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Neurologic Manifestations; Signs and Symptoms; Neurobehavioral Manifestations; Nervous System Diseases; Neurocognitive Disorders; Mental Disorders

Study Officials

• Azra Bihorac, MD, MS

  University of Florida

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Andrea E Davidson, BS

CONTACT

352-294-8723; adavidson@ufl.edu

Study Design

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

Study Record Dates

• First Submitted: November 4, 2021
• First Posted: November 19, 2021
• Study Start: May 24, 2021
• Primary Completion (Estimated): December 1, 2026
• Study Completion (Estimated): December 1, 2026
• Last Updated: June 3, 2025

Record last verified: 2025-06

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)