Machine Learning Model for Predicting Recovery After Crit... | NCT07616388

Studies
Machine Learning Model for Predicting Recovery After Critical Illness

NCT07616388

Sponsor

Hospital de Clinicas de Porto Alegre

Status

Completed

Last Update Posted

Jun 10, 2026Actual

Enrollment

2,016Actual

Phase

Not provided

Conditions

Funcional Status
Return to Work
Predictive Learning Models

Interventions

No interventions were performed.

Countries

Brazil

Protocol Section

Identification Module Status Module Sponsor/Collaborators Module Oversight Module Description Module Conditions Module Design Module Arms/Interventions Module Outcomes Module Eligibility Module Contacts/Locations Module References Module IPD Sharing Statement Module

Results Section

Participant Flow Module Baseline Characteristics Module Outcome Measures Module Adverse Events Module More Info Module

Annotation Section

Annotation Module

Document Section

Large Document Module

Derived Section

Miscellaneous Info Module Condition Browse Module Intervention Browse Module

Protocol Section

Identification Module

NCT ID

Results Section

No data available

No data is available for this block.

Annotation Section

No data available

No data is available for this block.

Document Section

No data available

No data is available for this block.

Derived Section

Miscellaneous Info Module

Version Holder

Status Module

Record Verification Date

Jun 2026

Overall Recruitment Status or Expanded Access Status

Completed

Last Known Status

Not provided

Delayed Posting

Not provided

Why Stopped

Not provided

Expanded Access Info

Start Date

Mar 15, 2026Actual

Primary Completion Date

Mar 20, 2026Actual

Completion Date

Apr 15, 2026Actual

First Submitted Date

May 23, 2026

First Submission Date that Met QC Criteria

May 23, 2026

First Posted Date

Jun 1, 2026Actual

Results Waived

Not provided

Results First Submitted Date

Not provided

Results First Submitted that Met QC Criteria

Not provided

Results First Posted Date

Not provided

Certification/Extension (aka Delayed Results) First Submitted Date

Not provided

Certification/Extension First Submitted that Passed QC Review

Not provided

Certification/Extension First Posted Date

Not provided

Last Update Submitted Date

Jun 6, 2026

Last Update Posted Date

Jun 10, 2026Actual

Sponsor/Collaborators Module

Responsible Party, by Official Title

Karina De Oliveira Azzolin, Professor, Hospital de Clinicas de Porto AlegrePrincipal Investigator

Lead Sponsor

Hospital de Clinicas de Porto AlegreOTHER

Collaborators

Name	Class
Federal University of Rio Grande do Sul	OTHER
Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul, Brazil	OTHER

Oversight Module

Has Data Monitoring Committee (DMC)

Yes

Is FDA Regulated Drug

Is FDA Regulated Device

Is Unapproved Device

Not provided

Pediatric Postmarket Surveillance of a Device Product

Not provided

Product Exported from US

Not provided

FDAAA801 Violation

Not provided

Description Module

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?

Detailed Description

This is a retrospective observational study using secondary data from two primary studies conducted between 2017-2019 and 2020-2022. No new participants will be recruited. Data were combined and harmonized for the present secondary analysis.

Design Module

Study Type

Observational

Number of References to an Expanded Access Study

Not provided

Expanded Access Types

Not provided

Patient Registry

Target Follow-Up Duration

Not provided

Phases

Not provided

Interventional Study Design

Allocation

Not provided

Intervention Model

Biospecimen

No data available

No data is available for this block.

Enrollment

2,016Actual

Arms/Interventions Module

Arm Groups

Label	Type	Description	Intervention Names
Patients in follow-up		Patients under follow-up. No interventions were performed	Other: No interventions were performed.

Interventions

Name	Type	Description	Arm Group Labels	Other Names
No interventions were performed.	Other	No interventions were performed.	Patients in follow-up

Outcomes Module

Primary Outcomes

Measure	Description	Time Frame
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

Measure	Description	Time Frame
Return to Work	Being employed	3rd, 6th and 12th months after ICU discharge

Other Outcomes

Not provided

Eligibility Module

Eligibility Criteria

Inclusion Criteria:

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

Exclusion Criteria:

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

Accepts Healthy Volunteers

Sex

All

Sex/Gender Based

Not provided

Sex/Gender Description

Not provided

Minimum Age

18 Years

Maximum Age

Not provided

Standard Ages

AdultOlder Adult

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.

Sampling Method

Non-Probability Sample

Contacts/Locations Module

Central Contacts

Not provided

Overall Officials

Not provided

Locations

Facility	Status	City	State	ZIP	Country	Contacts
Hospital de Clínicas de Porto Alegre, Intensive Care Nursing Department		Porto Alegre	Rio Grande do Sul	90035-903	Brazil

IPD Sharing Statement Module

Plan to Share IPD

Description

Not provided

Types

Not provided

Time Frame

Not provided

Access Criteria

Not provided

URL

Not provided

Condition Browse Module

MeSH Terms

ID	Term
D016638	Critical Illness
C000657744	postintensive care syndrome

Ancestor Terms

ID	Term
D020969	Disease Attributes
D010335	Pathologic Processes
D013568	Pathological Conditions, Signs and Symptoms

Browse Leaves

Not provided

Browse Branches

Not provided