SmartVent: Using algorithms based on physiological signals to personalize care for critically ill patients undergoing mechanical ventilation

Project focused on the development of advanced algorithms applied to physiological signals to improve the monitoring of critically ill patients with mechanical ventilation. It analyzes patient-ventilator interaction through the processing of clinical data in real time, allowing asynchronies and risk patterns to be identified. His approach contributes to more personalized, data-driven intensive medicine aimed at improving clinical outcomes in intensive care settings.

Characterize the asynchronies between patient and ventilator and evaluate their clinical impact using data-based models. The project seeks to develop tools to customize mechanical ventilation, reduce complications and optimize the evolution of critically ill patients. In addition, it aims to facilitate clinical decision-making through objective and automatically processed information based on complex physiological signals.

• Implementation of advanced predictive models for the personalization of critical patient care control.
• Optimization of respiratory interaction to reduce asynchrony
• Development of algorithmic analysis and monitoring tools for advanced critical care environments.