Using Artificial Intelligence to Improve Decision Support for Invasive Mechanical Ventilation in ICU Patients Retrospective Study Evaluating Patient Treatment Data

What this Trial Is About

This research aims to evaluate and improve an artificial intelligence AI algorithm designed to support clinical decisions in invasive mechanical ventilation for intensive care patients. Mechanical ventilation is a life-saving therapy in the ICU but can cause organ damage if settings are not properly adjusted. The study focuses on learning from how healthcare providers adjust ventilator and extracorporeal lung support device settings to reduce risks and enhance patient care. The study uses retrospective patient treatment data to assess an AI-based decision support system called IntelliLung. This system helps optimize mechanical ventilation settings by analyzing both the AI recommendations and the actual clinical decisions made by experts. The research compares the time when the AI settings match the healthcare providers settings from intubation until extubation or discharge, with assessment up to 12 months. Participants are ICU patients aged 18 or older who have received invasive mechanical ventilation for more than 4 hours. The study involves reviewing ventilator settings and patient data during their ICU stay. Researchers measure how often the AIs recommended settings align with those chosen by clinicians. This observational study does not involve active treatment changes but focuses on the analysis of existing patient data to improve future ventilation support.

Evaluation and Further Development of an Artificial Intelligence-based Algorithm for Clinical Decision Support