Exploratory use of decision tree analysis in classification of outcome in hypoxic-ischemic brain injury

Thanh G. Phan, Jian Chen, Shaloo Singhal, Henry Ma, Benjamin B. Clissold, John Ly, Richard Beare

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Background: Prognostication following hypoxic ischemic encephalopathy (brain injury) is important for clinical management. The aim of this exploratory study is to use a decision tree model to find clinical and MRI associates of severe disability and death in this condition. We evaluate clinical model and then the added value of MRI data. Method: The inclusion criteria were as follows: age ≥17 years, cardio-respiratory arrest, and coma on admission (2003-2011). Decision tree analysis was used to find clinical [Glasgow Coma Score (GCS), features about cardiac arrest, therapeutic hypothermia, age, and sex] and MRI (infarct volume) associates of severe disability and death. We used the area under the ROC (auROC) to determine accuracy of model. There were 41 (63.7% males) patients having MRI imaging with the average age 51.5 ± 18.9 years old. The decision trees showed that infarct volume and age were important factors for discrimination between mild to moderate disability and severe disability and death at day 0 and day 2. The auROC for this model was 0.94 (95% CI 0.82-1.00). At day 7, GCS value was the only predictor; the auROC was 0.96 (95% CI 0.86-1.00). Conclusion: Our findings provide proof of concept for further exploration of the role of MR imaging and decision tree analysis in the early prognostication of hypoxic ischemic brain injury.

Original languageEnglish
Article number126
Number of pages6
JournalFrontiers in Neurology
Volume9
Issue numberMAR
DOIs
Publication statusPublished - 6 Mar 2018

Keywords

  • Cardiac arrest
  • Classification
  • Decision tree analysis
  • Hypoxic ischemic encephalopathy
  • Prediction

Cite this

@article{dd605cdd69e345e5bf62ad113096073e,
title = "Exploratory use of decision tree analysis in classification of outcome in hypoxic-ischemic brain injury",
abstract = "Background: Prognostication following hypoxic ischemic encephalopathy (brain injury) is important for clinical management. The aim of this exploratory study is to use a decision tree model to find clinical and MRI associates of severe disability and death in this condition. We evaluate clinical model and then the added value of MRI data. Method: The inclusion criteria were as follows: age ≥17 years, cardio-respiratory arrest, and coma on admission (2003-2011). Decision tree analysis was used to find clinical [Glasgow Coma Score (GCS), features about cardiac arrest, therapeutic hypothermia, age, and sex] and MRI (infarct volume) associates of severe disability and death. We used the area under the ROC (auROC) to determine accuracy of model. There were 41 (63.7{\%} males) patients having MRI imaging with the average age 51.5 ± 18.9 years old. The decision trees showed that infarct volume and age were important factors for discrimination between mild to moderate disability and severe disability and death at day 0 and day 2. The auROC for this model was 0.94 (95{\%} CI 0.82-1.00). At day 7, GCS value was the only predictor; the auROC was 0.96 (95{\%} CI 0.86-1.00). Conclusion: Our findings provide proof of concept for further exploration of the role of MR imaging and decision tree analysis in the early prognostication of hypoxic ischemic brain injury.",
keywords = "Cardiac arrest, Classification, Decision tree analysis, Hypoxic ischemic encephalopathy, Prediction",
author = "Phan, {Thanh G.} and Jian Chen and Shaloo Singhal and Henry Ma and Clissold, {Benjamin B.} and John Ly and Richard Beare",
year = "2018",
month = "3",
day = "6",
doi = "10.3389/fneur.2018.00126",
language = "English",
volume = "9",
journal = "Frontiers in Neurology",
issn = "1664-2295",
publisher = "Frontiers Media",
number = "MAR",

}

Exploratory use of decision tree analysis in classification of outcome in hypoxic-ischemic brain injury. / Phan, Thanh G.; Chen, Jian; Singhal, Shaloo; Ma, Henry; Clissold, Benjamin B.; Ly, John; Beare, Richard.

In: Frontiers in Neurology, Vol. 9, No. MAR, 126, 06.03.2018.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Exploratory use of decision tree analysis in classification of outcome in hypoxic-ischemic brain injury

AU - Phan, Thanh G.

AU - Chen, Jian

AU - Singhal, Shaloo

AU - Ma, Henry

AU - Clissold, Benjamin B.

AU - Ly, John

AU - Beare, Richard

PY - 2018/3/6

Y1 - 2018/3/6

N2 - Background: Prognostication following hypoxic ischemic encephalopathy (brain injury) is important for clinical management. The aim of this exploratory study is to use a decision tree model to find clinical and MRI associates of severe disability and death in this condition. We evaluate clinical model and then the added value of MRI data. Method: The inclusion criteria were as follows: age ≥17 years, cardio-respiratory arrest, and coma on admission (2003-2011). Decision tree analysis was used to find clinical [Glasgow Coma Score (GCS), features about cardiac arrest, therapeutic hypothermia, age, and sex] and MRI (infarct volume) associates of severe disability and death. We used the area under the ROC (auROC) to determine accuracy of model. There were 41 (63.7% males) patients having MRI imaging with the average age 51.5 ± 18.9 years old. The decision trees showed that infarct volume and age were important factors for discrimination between mild to moderate disability and severe disability and death at day 0 and day 2. The auROC for this model was 0.94 (95% CI 0.82-1.00). At day 7, GCS value was the only predictor; the auROC was 0.96 (95% CI 0.86-1.00). Conclusion: Our findings provide proof of concept for further exploration of the role of MR imaging and decision tree analysis in the early prognostication of hypoxic ischemic brain injury.

AB - Background: Prognostication following hypoxic ischemic encephalopathy (brain injury) is important for clinical management. The aim of this exploratory study is to use a decision tree model to find clinical and MRI associates of severe disability and death in this condition. We evaluate clinical model and then the added value of MRI data. Method: The inclusion criteria were as follows: age ≥17 years, cardio-respiratory arrest, and coma on admission (2003-2011). Decision tree analysis was used to find clinical [Glasgow Coma Score (GCS), features about cardiac arrest, therapeutic hypothermia, age, and sex] and MRI (infarct volume) associates of severe disability and death. We used the area under the ROC (auROC) to determine accuracy of model. There were 41 (63.7% males) patients having MRI imaging with the average age 51.5 ± 18.9 years old. The decision trees showed that infarct volume and age were important factors for discrimination between mild to moderate disability and severe disability and death at day 0 and day 2. The auROC for this model was 0.94 (95% CI 0.82-1.00). At day 7, GCS value was the only predictor; the auROC was 0.96 (95% CI 0.86-1.00). Conclusion: Our findings provide proof of concept for further exploration of the role of MR imaging and decision tree analysis in the early prognostication of hypoxic ischemic brain injury.

KW - Cardiac arrest

KW - Classification

KW - Decision tree analysis

KW - Hypoxic ischemic encephalopathy

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=85043315275&partnerID=8YFLogxK

U2 - 10.3389/fneur.2018.00126

DO - 10.3389/fneur.2018.00126

M3 - Article

VL - 9

JO - Frontiers in Neurology

JF - Frontiers in Neurology

SN - 1664-2295

IS - MAR

M1 - 126

ER -