Supervised Machine Learning Applied to Automate Flash and Prolonged Capillary Refill Detection by Pulse Oximetry

Develop an automated approach to detect flash (2.0 s) capillary refill time (CRT) that correlates with clinician judgment by applying several supervised machine learning (ML) techniques to pulse oximeter plethysmography data. Data was collected in the Pediatric Intensive Care Unit (ICU), Cardiac ICU...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in physiology 2020-10, Vol.11, p.564589-564589
Main Authors: Hunter, Ryan Brandon, Jiang, Shen, Nishisaki, Akira, Nickel, Amanda J, Napolitano, Natalie, Shinozaki, Koichiro, Li, Timmy, Saeki, Kota, Becker, Lance B, Nadkarni, Vinay M, Masino, Aaron J
Format: Article
Language:English
Subjects:
gradient boosting
intensive care units
oximetry
pediatrics
perfusion
Physiology
supervised machine learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Develop an automated approach to detect flash (2.0 s) capillary refill time (CRT) that correlates with clinician judgment by applying several supervised machine learning (ML) techniques to pulse oximeter plethysmography data. Data was collected in the Pediatric Intensive Care Unit (ICU), Cardiac ICU, Progressive Care Unit, and Operating Suites in a large academic children's hospital. Ninety-nine children and 30 adults were enrolled in testing and validation cohorts, respectively. Patients had 5 paired CRT measurements by a modified pulse oximeter device and a clinician, generating 485 waveform pairs for model training. Supervised ML models using gradient boosting (XGBoost), logistic regression (LR), and support vector machines (SVMs) were developed to detect flash (
ISSN:1664-042X
1664-042X
DOI:10.3389/fphys.2020.564589