Skip to content

AI-Guided Mechanical Ventilation in Children: A Randomized Controlled Trial

Randomized Controlled Study on Intelligent Optimization of Ventilator Parameters for Pediatric Patients Undergoing Mechanical Ventilation Based on Large Language Models

Status
Not yet recruiting
Phases
Unknown
Study type
Interventional
Source
ClinicalTrials.gov
Registry ID
NCT07728136
Enrollment
200
Registered
2026-07-27
Start date
2026-09-01
Completion date
2027-12-31
Last updated
2026-07-27

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Acute Respiratory Distress Syndrome, Congenital Heart Disease in Children, Pneumonia in Children, Respiratory Failure (Pediatric Patients)

Brief summary

This prospective, randomized controlled trial aims to evaluate whether an AI-driven decision support system can improve clinical outcomes for mechanically ventilated pediatric patients (aged 1 month to 18 years) in the PICU, compared to standard care. The primary question addressed is: Do patients whose ventilator parameter optimization decisions are guided by AI assistance achieve a greater number of ventilator-free days within 28 days compared to those managed with standard care by medical staff? Eligible pediatric patients requiring mechanical ventilation following tracheal intubation will be randomly assigned (1:1) to either the AI-guided intervention group or the standard care control group. In the intervention group, physicians will receive real-time, AI-generated recommendations for ventilator parameters to inform clinical adjustments. In contrast, the control group will be managed according to standard clinical protocols. This study seeks to assess whether AI-driven ventilator optimization can effectively improve clinical outcomes and shorten ventilation duration for pediatric patients in the PICU.

Interventions

OTHERAI-generated recommendations for ventilator parameters.

In the AI-Guided Group, physicians will receive real-time, AI-generated recommendations for ventilator parameters to inform clinical adjustments.

Sponsors

Wu Rongzhou
Lead SponsorOTHER

Study design

Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
HEALTH_SERVICES_RESEARCH
Masking
NONE

Intervention model description

In the intervention group, physicians will receive real-time, AI-generated recommendations for ventilator parameters to inform clinical adjustments. In contrast, the control group will be managed according to standard clinical protocols.

Eligibility

Sex/Gender
ALL
Age
1 Months to 18 Years
Healthy volunteers
Yes

Inclusion criteria

1. PICU patients aged 1 month to 18 years. 2. Receiving invasive mechanical ventilation, expected to last ≥ 24 hours. 3. Informed consent signed before enrollment.

Exclusion criteria

1. Expected survival \< 24 hours 2. Irreversible brain injury (GCS = 3 + absence of brainstem reflexes) 3. Severe congenital cardiopulmonary malformations affecting ventilation assessment 4. Pregnancy (must be ruled out in adolescent girls) 5. Currently participating in other ventilation intervention trials 6. Guardian refusal to participate

Design outcomes

Primary

MeasureTime frameDescription
Number of ventilator-free days within 28 daysFrom the start of tracheal intubation until 28 days after tracheal intubation.Days survived and free from invasive ventilation

Secondary

MeasureTime frameDescription
Mechanical Ventilation-Related ComplicationsFrom the start of tracheal intubation to Day 28Cumulative duration of mechanical ventilation, reintubation rate (within 48 hours of extubation), ventilator-associated pneumonia (VAP), barotrauma.
Length of Hospital StayThe duration from the time of admission to discharge for pediatric patients-up to a maximum of three months.PICU Length of Stay, Total Hospital Length of Stay
Artificial Intelligence System EvaluationFrom the start of tracheal intubation to Day 28Rate of physician adoption of AI recommendations

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Jul 28, 2026