Using Artificial Intelligence To Improve Ventilator Settings For Intensive Care Patients

Research on Intelligent Optimization of Ventilator Parameters for Intensive Care Patients Based on Multimodal Large Models

This observational study aims to determine whether an AI-assisted 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 provided by medical staff. 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 than those managed by medical staff? By utilizing clinical data collected following tracheal intubation to generate AI-driven recommendations-and comparing these against the actual adjustments made by physicians-this study seeks to assess whether the AI-assisted decision support system can effectively improve clinical outcomes for mechanically ventilated patients in the PICU.

Inclusion Criteria:

1. PICU patients aged 1 month to 18 years.
2. Receiving invasive mechanical ventilation, expected to last ≥ 48 hours.
3. Informed consent signed prior to 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