Synergy in Respiration: Improving Patient-Ventilator Interaction via AI-based Monitoring

Synergy in Respiration: Improving Patient-Ventilator Interaction via AI-based Monitoring (SIREN)

This project brings together a unique public-private partnership (Erasmus MC Intensive Care department & Deep Breath B.V.) to improve outcomes of patients admitted to the intensive care unit (ICU). By validating and implementing innovative AI-based monitoring software, we aim to enhance patient comfort and reduce complications associated with mechanical ventilation.

Mechanical ventilation is the cornerstone of organ-support therapy for patients admitted to the ICU. In the Netherlands, approximately 35,000 patients are mechanically ventilated every year. Although life-saving, it often causes further lung injury and long-term damage. Many ventilated patients show excessive breathing efforts and abnormal, irregular breathing. This patient-ventilator asynchrony (PVA) is associated with serious discomfort, lung injury, sleep disruption and higher mortality, escalating healthcare costs. Identifying and resolving PVA is challenging and time-consuming as it necessitates exhaustive visual inspection of ventilator waveforms by clinicians and additional diagnostics. Technical innovations are essential to address these issues and improve patient outcomes.

Our consortium of clinical/scientific experts (Erasmus MC) and data-science engineers (Deep Breath B.V.) will co-create robust and scalable software with important diagnostic and clinical value. Our approach involves real-time artificial intelligence (AI)-based analytics of ventilator waveforms to detect and mitigate harmful PVA. By studying the clinical impact of PVA, we will provide clinicians with actionable insights to adjust ventilator settings precisely, enhancing patient comfort and reducing the risk of complications. We build towards tailoring care for the individual patient using an evidence-based and data-driven approach that can be directly integrated into the clinical workflow.

Upon project completion, we will deliver a validated AI-based decision-support system that is ready for clinical integration. We expect our solution to be implemented in hospitals nationwide, ultimately improving the quality of care for thousands of patients and reducing healthcare costs.

More information

Summary
Mechanical ventilation is a life-saving therapy for patients admitted to the intensive care unit, but can also cause further injury and long-term complications. This project validates and implements real-time AI-based software aimed at personalizing mechanical ventilation to reduce the injurious effects and enhance patient comfort.
Technology Readiness Level (TRL)
4 - 7
Time period
48 months
Partners