Predicting and simulating effects of PEEP changes with machine learning
Strodthoff, C.; Frerichs, I.; Weiler, N.; Bergh, B.
Show abstract
Background/ObjectivesChoosing ventilator settings, especially positive end-expiratory pressure (PEEP), is a very common and non-trivial task in intensive care units (ICUs). Established solutions to this problem are either poorly individualised or come with high costs in terms of used material or time. We propose a novel method relying on machine learning utilising only already routinely measured data. MethodsUsing the MIMIC-III (with over 60000 ICU stays) and eICU databases (with over 200000 ICU stays) we built a deep learning model that predicts relevant success parameters of ventilation (oxygenation, carbon dioxide elimination and respiratory mechanics). We compare a random forest, individual neural networks and a multi-tasking neural network. Our final model also allows to simulate the expected effects of PEEP changes. ResultsThe model predicts arterial partial pressures of oxygen and carbon dioxide and respiratory system compliance 30 minutes into the future with mean absolute percentage errors of about 22 %, 10 % and 11 %, respectively. ConclusionsThe deep learning approach to ventilation optimisation is promising and comes with low cost compared to other approaches.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A Machine Learning-Based Prediction of Hospital Mortality in Mechanically Ventilated ICU Patients 96%
- Identification of high-risk COVID-19 patients using machine learning 96%
- Computational simulation to assess patient safety of uncompensated COVID-19 two-patient ventilator sharing using the Pulse Physiology Engine 95%
Similar papers in this journal
- Mitigating Machine Learning Bias Between High Income and Low-Middle Income Countries for Enhanced Model Fairness and Generalizability 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%
- Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements 94%
Similar papers in this journal
- Highly comparative time series analysis of oxygen saturation and heart rate to predict respiratory outcomes in extremely preterm infants 94%
- Prospective validation of clinical deterioration predictive models prior to intensive care unit transfer among patients admitted to acute care cardiology wards 92%
- Comparison of feature-based indices derived from photoplethysmogram recorded from different body locations during lower body negative pressure 92%
Similar papers in this journal
"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.