Machine Learning for Mechanical Ventilation Control
This addresses the challenge of improving ventilator control for sedated patients, offering a data-driven solution that outperforms industry-standard methods, though it is incremental as it builds on existing machine learning techniques.
The paper tackled the problem of controlling invasive mechanical ventilators for pressure-controlled ventilation, showing that deep neural network controllers trained on a simulator from artificial lung data track target pressure waveforms significantly better than traditional PID controllers and generalize more effectively across varying lung characteristics.
We consider the problem of controlling an invasive mechanical ventilator for pressure-controlled ventilation: a controller must let air in and out of a sedated patient's lungs according to a trajectory of airway pressures specified by a clinician. Hand-tuned PID controllers and similar variants have comprised the industry standard for decades, yet can behave poorly by over- or under-shooting their target or oscillating rapidly. We consider a data-driven machine learning approach: First, we train a simulator based on data we collect from an artificial lung. Then, we train deep neural network controllers on these simulators.We show that our controllers are able to track target pressure waveforms significantly better than PID controllers. We further show that a learned controller generalizes across lungs with varying characteristics much more readily than PID controllers do.