Comparing regression and neural network techniques for personalized predictive analytics to promote lung protective ventilation in Intensive Care Units

Abstract

Mechanical ventilation is a lifesaving tool and provides organ support for patients with respiratory failure. However, injurious ventilation due to inappropriate delivery of high tidal volume can initiate or potentiate lung injury. This could lead to acute respiratory distress syndrome, longer duration of mechanical ventilation, ventilator associated conditions and finally increased mortality. In this study, we explore the viability and compare machine learning methods to generate personalized predictive alerts indicating violation of the safe tidal volume per ideal body weight (IBW) threshold that is accepted as the upper limit for lung protective ventilation (LPV), prior to application to patients. We process streams of patient respiratory data recorded per minute from ventilators in an intensive care unit and apply several state-of-the-art time series prediction methods to forecast the behavior of the tidal volume metric per patient, 1 hour ahead. Our results show that boosted regression delivers better predictive accuracy than other methods that we investigated and requires relatively short execution times. Long short-term memory neural networks can deliver similar levels of accuracy but only after much longer periods of data acquisition, further extended by several hours computing time to train the algorithm. Utilizing Artificial Intelligence, we have developed a personalized clinical decision support tool that can predict tidal volume behavior within accuracy and compare alerts recorded from a real world system to highlight that our models would have predicted violations 1 hour ahead and can therefore conclude that the algorithms can provide clinical decision support.

Developing a machine-learning model for real-time prediction of successful extubation in mechanically ventilated patients using time-series ventilator-derived parameters

“…This study is unique in that it used a time-series dataset that included patients’ ventilatory parameters measured every second. Hagen et al utilized a dataset of tidal volume measurements to develop a personalized clinical prediction model capable of predicting tidal volume behavior and providing alerts with 10% accuracy 1 hour ahead ( 34 ). The primary objective of their model was to prevent the occurrence of lung injury, rather than being used for extubation prediction.…”

Potenzial von KI für die Behandlung des akuten Lungenversagens (ARDS)

“…Auch diese Anwendung wurde zwar wie beschrieben zunächst nur an eigenen Daten überprüft [13], zeigt aber sicherlich das eindeutige Potenzial für eine verbesserte Therapie bei ARDS-Patienten, da selbst erfahrene Intensivmediziner die Therapie nicht mit so einer Genauigkeit erkennen würden.…”

Mechanical ventilation intervention based on machine learning from vital signs monitoring: a scoping review

“…Because of each MLA has a different procedure to transform the time series problems into supervised learning problems. Hagan et al [53] showed that LSTM is faster than the regression model (Bagging, ERTs, RF, ADB, GBM) for the prediction of the event in the order of 1 h prior the event.…”