Back to Search
Start Over
Using machine learning models to predict oxygen saturation following ventilator support adjustment in critically ill children: A single center pilot study
- Source :
- PLoS ONE, PLoS ONE, Vol 14, Iss 2, p e0198921 (2019)
- Publication Year :
- 2019
- Publisher :
- Public Library of Science, 2019.
-
Abstract
- BackgroundIn an intensive care units, experts in mechanical ventilation are not continuously at patient's bedside to adjust ventilation settings and to analyze the impact of these adjustments on gas exchange. The development of clinical decision support systems analyzing patients' data in real time offers an opportunity to fill this gap.ObjectiveThe objective of this study was to determine whether a machine learning predictive model could be trained on a set of clinical data and used to predict transcutaneous hemoglobin oxygen saturation 5 min (5min SpO2) after a ventilator setting change.Data sourcesData of mechanically ventilated children admitted between May 2015 and April 2017 were included and extracted from a high-resolution research database. More than 776,727 data rows were obtained from 610 patients, discretized into 3 class labels (< 84%, 85% to 91% and c92% to 100%).Performance metrics of predictive modelsDue to data imbalance, four different data balancing processes were applied. Then, two machine learning models (artificial neural network and Bootstrap aggregation of complex decision trees) were trained and tested on these four different balanced datasets. The best model predicted SpO2 with area under the curves < 0.75.ConclusionThis single center pilot study using machine learning predictive model resulted in an algorithm with poor accuracy. The comparison of machine learning models showed that bagged complex trees was a promising approach. However, there is a need to improve these models before incorporating them into a clinical decision support systems. One potentially solution for improving predictive model, would be to increase the amount of data available to limit over-fitting that is potentially one of the cause for poor classification performances for 2 of the three class labels.
- Subjects :
- Male
Decision Analysis
Computer science
Bootstrap aggregating
medicine.medical_treatment
Pilot Projects
computer.software_genre
law.invention
Machine Learning
Families
0302 clinical medicine
Mathematical and Statistical Techniques
law
Ventilator settings
Child
Children
Multidisciplinary
Artificial neural network
Applied Mathematics
Simulation and Modeling
Statistics
Quebec
Intensive care unit
Laboratory Equipment
Chemistry
Child, Preschool
Physical Sciences
Medicine
Engineering and Technology
Female
Management Engineering
Algorithms
Research Article
Chemical Elements
Computer and Information Sciences
Science
Critical Illness
Ventilators
Decision tree
Hemoglobin oxygen saturation
Equipment
Machine learning
Research and Analysis Methods
Intensive Care Units, Pediatric
Clinical decision support system
Set (abstract data type)
03 medical and health sciences
Machine Learning Algorithms
Artificial Intelligence
Intensive care
medicine
Humans
Statistical Methods
Oxygen saturation
Artificial Neural Networks
Retrospective Studies
Mechanical ventilation
Computational Neuroscience
Ventilators, Mechanical
business.industry
Decision Trees
Biology and Life Sciences
Computational Biology
030208 emergency & critical care medicine
Decision Support Systems, Clinical
Oxygen
030228 respiratory system
Age Groups
People and Places
Population Groupings
Artificial intelligence
business
computer
Mathematics
Neuroscience
Forecasting
Subjects
Details
- Language :
- English
- ISSN :
- 19326203
- Volume :
- 14
- Issue :
- 2
- Database :
- OpenAIRE
- Journal :
- PLoS ONE
- Accession number :
- edsair.doi.dedup.....dbaee5c1e4aab14138de57eb11dad6c2