Automating Delirium Severity in the ICU

NCT06172491 | Recruiting DMC

• 1 other identifier: 22-003098
• Study Type: observational
• Target: 400
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this observational study is to develop a passive digital marker (PDM) for delirium severity and examine its performance in comparison to validated delirium severity tools in ICU patients \>50 years of age. The main questions it aims to answer are:

• Is the trained convolutional neural network able to reliably measure delirium severity.
• Is the Passive Digital Marker able to accurately measure delirium severity
• Is the Passive Digital Marker acceptable and usable by frontline ICU nurse clinicians, patients, and their identified proxies (i.e., caregivers). Participants will:
• Study participation involves a video camera recording you 24 hours per day while you are a patient in the Intensive Care Unit (ICU).
• Study staff will visit you 4 times each day you are in the ICU. You will be asked questions each time they visit to train the digital marker and see differences between assessments and camera data.

Conditions

Intensive Care Unit Delirium; Encephalopathy; Delirium

Keywords

Delirium; Severity; Digital marker; Computer Vision; Artificial Intelligence

Outcome Measures

Primary Outcomes (3)

• Delirium Severity

  The level of delirium severity will be measured by two types of prospective data collection. The first method is completed by study team members. A trained member of the study team will administer validated assessment tools 4xdaily from enrollment until ICU discharge or death. The Confusion Assessment Method for the Intensive Care Unit Severy Scale (CAM-ICU-7) is the gold standard for delirium severity measurement in the ICU. It is a 7-point scale, with 7 being severe delirium and 0 being no delirium. The second method is a passive digital marker (in development).

  12-48 months

• Acceptability of passive digital marker for delirium severity

  Participants and their identified care partners will be randomized 1:1 to either the Passive Digital Marker for Delirium Severity or usual care. The acceptability of the PDM by clinicians, patients, and care partners will be evaluated. The 4-question tool named Treatment Acceptability and Preference Questionnaire (TAPQ) is scored on a 5-point Likert scale. A higher score indicates higher acceptability.

  48 months - 60 months

• Usability of passive digital marker for delirium severity

  Participants and their identified care partners will be randomized 1:1 to either the Passive Digital Marker for Delirium Severity or usual care. The usability of the PDM by clinicians, patients, and care partners will be evaluated. The 10-question System Usability Scale is scored on a Likert scale from 1-5. A higher score (0-100 range) indicates higher usability.

  48 months - 60 months

Study Arms (2)

No Delirium Severity

Patients who did not experience a level of delirium severity (subsyndromal, mild, moderate, severe)

Delirium Severity

Patients who did experience a level of delirium severity (subsyndromal, mild, moderate, severe)

Eligibility Criteria

• Age: 50 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Aging adults admitted to an intensive care unit

You may qualify if:

• Estimated length of stay \>24 hours in ICU; and
• Are not admitted for acute alcohol intoxication, drug (prescribed or illicit) overdose or withdrawal.

You may not qualify if:

• Admitted for acute alcohol intoxication, drug (prescribed or illicit) overdose or withdrawal.
• Admitted for acute neuronal injury
• Unable to communicate with research team due to sensory deficits (aphasic, blind, deaf) or language (does not speak English)

Sponsors & Collaborators

• Mayo Clinic: lead

Study Sites (1)

Mayo Clinic

Rochester, Minnesota, 55905, United States

RECRUITING

Related Publications (1)

• Raghu R, Nalaie K, Ayala I, Morales Behaine JJ, Garcia-Mendez JP, Friesen H, Leistikow K, Bhattacharyya A, Jayaraman A, Franco PM, Rabinstein A, Chlan LL, Boustani M, Herasevich V, Lindroth H. Harnessing the Power of Technology to Transform Delirium Severity Measurement in the Intensive Care Unit: Protocol for a Prospective Cohort Study. JMIR Res Protoc. 2025 Sep 25;14:e62912. doi: 10.2196/62912.

  PMID: 40998312 DERIVED

MeSH Terms

Conditions

Brain Diseases; Delirium

Condition Hierarchy (Ancestors)

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

Central Study Contacts

Heidi Lindroth, PH.D. R.N.

CONTACT

507-284-3662; lindroth.heidi@mayo.edu

Hannah Friesen

CONTACT

1-507-284-2197; friesen.hannah@mayo.edu

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Heidi L. Lindroth, Ph.D., Nurse Scientist, Assistant Professor of Nursing

Study Record Dates

• First Submitted: December 7, 2023
• First Posted: December 15, 2023
• Study Start: January 15, 2023
• Primary Completion (Estimated): May 31, 2027
• Study Completion (Estimated): May 31, 2028
• Last Updated: April 8, 2026

Record last verified: 2026-04

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)