Machine Learning Model for Predicting Recovery After Critical Illness

NCT07616388 | Completed DMC

• 1 other identifier: 20250554
• Study Type: observational
• Target: 2,016
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to develop and test an artificial intelligence (AI) model to predict long-term functional status and return to work after critical illness. The main question is: Can we develop and validate a machine learning model to predict long-term functional status and return to work after critical illness?

Conditions

Funcional Status; Return to Work; Predictive Learning Models

Keywords

Return to Work; Funcional Status; Intensive Care; Recovery; Critical Illness; Machine Learning; Post-intensive Care Syndrome; Critical Care

Outcome Measures

Primary Outcomes (1)

• Functional Status

  The primary outcome will be functional status at 6 months after ICU discharge, assessed using the Barthel Index (BI). The BI is a validated measure of functional status in activities of daily living, with total scores ranging from 0 to 100. For prediction modeling, the outcome will be treated as a binary variable, with functional impairment defined as a BI score \<91 points.

  3rd, 6th and 12th months after ICU discharge

Secondary Outcomes (1)

• Return to Work

  3rd, 6th and 12th months after ICU discharge

Study Arms (1)

Patients in follow-up

Patients under follow-up. No interventions were performed

Other: No interventions were performed.

Interventions

No interventions were performed. OTHER

No interventions were performed.

Patients in follow-up

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

Ten medical-surgical ICUs representing the five geopolitical regions of Brazil were selected as study sites. This study includes data from two databases with similar inclusion and exclusion criteria.

You may qualify if:

• Age ≥18 years
• ICU stay ≥ 72 hours
• ICU stay ≥ 120 hours if the participant was admitted for elective surgery

You may not qualify if:

• No telephone contact available
• Failure to establish contact
• Transfer to another ICU

Sponsors & Collaborators

• Federal University of Rio Grande do Sul: collaborator
• Hospital de Clinicas de Porto Alegre: lead
• Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul, Brazil: collaborator

Study Sites (1)

Hospital de Clínicas de Porto Alegre, Intensive Care Nursing Department

Porto Alegre, Rio Grande do Sul, 90035-903, Brazil

Location

MeSH Terms

Conditions

Critical Illness; postintensive care syndrome

Condition Hierarchy (Ancestors)

Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: OTHER
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: May 23, 2026
• First Posted: June 1, 2026
• Study Start: March 15, 2026
• Primary Completion: March 20, 2026
• Study Completion: April 15, 2026
• Last Updated: June 10, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will not share

Locations

BR (1)