Machine Learning for Mechanical Ventilation Control
Suo, D.; Zhang, C.; Gradu, P.; Ghai, U.; Chen, X.; Agarwal, N.; Singh, K.; LaChance, J.; Zajdel, T.; Schottdorf, M.; Cohen, D. J.; Hazan, E.
Show abstract
AO_SCPLOWBSTRACTC_SCPLOWWe consider the problem of controlling an invasive mechanical ventilator for pressure-controlled ventilation: a controller must let air in and out of a sedated patients 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.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Reinforcement learning derived chemotherapeutic schedules for robust patient-specific therapy 95%
- Identifying low-dimensional trajectories of mechanically-ventilated patient systems: Empirical phenotypes of joint patient+care processes to enhance temporal analysis in ARDS research 94%
- Explaining COVID-19 Outbreaks with Reactive SEIRD Models 93%
Similar papers in this journal
- Prediction of Covid-19 spreading and optimal coordination of counter-measures: From microscopic to macroscopic models to Pareto fronts 93%
- A Hessian-based decomposition characterizes how performance in complex motor skills depends on individual strategy and variability 93%
- PVP1–The People’s Ventilator Project: A fully open, low-cost, pressure-controlled ventilator 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.