Affordable Access

Publisher Website

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

  • Hagan, Rachael1
  • Gillan, Charles J.1
  • Spence, Ivor1
  • McAuley, Danny2
  • Shyamsundar, Murali2
  • 1 School of Electrical and Electronic Engineering and Computer Science, Queen's University Belfast, Queen's Road, Queen's Island, Belfast, Northern Ireland, BT9 3DT, United Kingdom
  • 2 The Centre for Experimental Medicine, School of Medicine, Dentistry and Biological Sciences, Queen's University Belfast, 97 Lisburn Road, Belfast, Northern Ireland, BT9 7BL, United Kingdom
Published Article
Computers in Biology and Medicine
Elsevier Ltd.
Publication Date
Oct 08, 2020
DOI: 10.1016/j.compbiomed.2020.104030
PMID: 33068808
PMCID: PMC7543875
PubMed Central


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 10 % 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.

Report this publication


Seen <100 times