Machine Learning for Mechanical Ventilation Control (Extended Abstract)
This addresses a critical issue for ICU patients by improving ventilator control, though it appears incremental as it builds on existing data-driven methods for a specific domain.
The paper tackles the problem of controlling mechanical ventilators in the ICU, which are currently based on suboptimal PID methods, by proposing a data-driven approach that learns from a simulator trained on ventilator data; the result is a method that outperforms reinforcement learning algorithms and achieves more accurate and robust control than PID on physical ventilators.
Mechanical ventilation is one of the most widely used therapies in the ICU. However, despite broad application from anaesthesia to COVID-related life support, many injurious challenges remain. We frame these as a control problem: ventilators must let air in and out of the patient's lungs according to a prescribed trajectory of airway pressure. Industry-standard controllers, based on the PID method, are neither optimal nor robust. Our data-driven approach learns to control an invasive ventilator by training on a simulator itself trained on data collected from the ventilator. This method outperforms popular reinforcement learning algorithms and even controls the physical ventilator more accurately and robustly than PID. These results underscore how effective data-driven methodologies can be for invasive ventilation and suggest that more general forms of ventilation (e.g., non-invasive, adaptive) may also be amenable.