Next Article in Journal
Increased First Pass Success with C-MAC Videolaryngoscopy in Prehospital Endotracheal Intubation—A Randomized Controlled Trial
Next Article in Special Issue
Adsorption of Blood Components to Extracorporeal Membrane Oxygenation (ECMO) Surfaces in Humans: A Systematic Review
Previous Article in Journal
Intracranial Hemorrhage Complicating Acute Myocardial Infarction: An 18-Year National Study of Temporal Trends, Predictors, and Outcomes
Previous Article in Special Issue
Same-Day Versus Non-Simultaneous Extracorporeal Membrane Oxygenation Support for In-Hospital Cardiac Arrest Complicating Acute Myocardial Infarction
Open AccessArticle

Neural Networks to Predict Radiographic Brain Injury in Pediatric Patients Treated with Extracorporeal Membrane Oxygenation

1
Department of Pediatrics, Division of Pediatric Critical Care, Washington University School of Medicine, St. Louis, MO 63110, USA
2
Department of Pediatrics, Pediatrix Medical Group, Orem, UT 84057, USA
3
Children’s Health Dallas, Dallas, TX 75201, USA
4
Department of Mechanical Engineering, The University of Texas at Dallas, Dallas, TX 75080, USA
5
Department of Bioinformatics, University of Texas Southwestern, Dallas, TX 75390, USA
6
Department of Radiation Oncology, University of Texas Southwestern, Dallas, TX 75390, USA
7
Department of Computer Science, The University of Texas at Dallas, Dallas, TX 75080, USA
8
Department of Bioengineering, University of Texas at Arlington, Arlington, TX 76019, USA
9
Department of Cardiology, Boston Children’s Hospital, Boston, MA 02115, USA
10
Department of Pediatrics, Division of Pediatric Critical Care, University of Texas Southwestern, Dallas, TX 75390, USA
*
Author to whom correspondence should be addressed.
J. Clin. Med. 2020, 9(9), 2718; https://doi.org/10.3390/jcm9092718
Received: 15 July 2020 / Revised: 7 August 2020 / Accepted: 19 August 2020 / Published: 22 August 2020
Brain injury is a significant source of morbidity and mortality for pediatric patients treated with Extracorporeal Membrane Oxygenation (ECMO). Our objective was to utilize neural networks to predict radiographic evidence of brain injury in pediatric ECMO-supported patients and identify specific variables that can be explored for future research. Data from 174 ECMO-supported patients were collected up to 24 h prior to, and for the duration of, the ECMO course. Thirty-five variables were collected, including physiological data, markers of end-organ perfusion, acid-base homeostasis, vasoactive infusions, markers of coagulation, and ECMO-machine factors. The primary outcome was the presence of radiologic evidence of moderate to severe brain injury as established by brain CT or MRI. This information was analyzed by a neural network, and results were compared to a logistic regression model as well as clinician judgement. The neural network model was able to predict brain injury with an Area Under the Curve (AUC) of 0.76, 73% sensitivity, and 80% specificity. Logistic regression had 62% sensitivity and 61% specificity. Clinician judgment had 39% sensitivity and 69% specificity. Sequential feature group masking demonstrated a relatively greater contribution of physiological data and minor contribution of coagulation factors to the model's performance. These findings lay the foundation for further areas of research directions. View Full-Text
Keywords: ECMO; neurologic injury; brain injury; machine learning; neural networks; pediatrics ECMO; neurologic injury; brain injury; machine learning; neural networks; pediatrics
Show Figures

Figure 1

MDPI and ACS Style

Shah, N.; Farhat, A.; Tweed, J.; Wang, Z.; Lee, J.; McBeth, R.; Skinner, M.; Tian, F.; Thiagarajan, R.; Raman, L. Neural Networks to Predict Radiographic Brain Injury in Pediatric Patients Treated with Extracorporeal Membrane Oxygenation. J. Clin. Med. 2020, 9, 2718. https://doi.org/10.3390/jcm9092718

AMA Style

Shah N, Farhat A, Tweed J, Wang Z, Lee J, McBeth R, Skinner M, Tian F, Thiagarajan R, Raman L. Neural Networks to Predict Radiographic Brain Injury in Pediatric Patients Treated with Extracorporeal Membrane Oxygenation. Journal of Clinical Medicine. 2020; 9(9):2718. https://doi.org/10.3390/jcm9092718

Chicago/Turabian Style

Shah, Neel; Farhat, Abdelaziz; Tweed, Jefferson; Wang, Ziheng; Lee, Jeon; McBeth, Rafe; Skinner, Michael; Tian, Fenghua; Thiagarajan, Ravi; Raman, Lakshmi. 2020. "Neural Networks to Predict Radiographic Brain Injury in Pediatric Patients Treated with Extracorporeal Membrane Oxygenation" J. Clin. Med. 9, no. 9: 2718. https://doi.org/10.3390/jcm9092718

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop