Improving Outcome Prediction for Traumatic Brain Injury From Imbalanced Datasets Using RUSBoosted Trees on Electroencephalography Spectral Power

Reliable prediction of traumatic brain injury (TBI) outcomes based on machine learning (ML) that is derived from quantitative electroencephalography (EEG) features has renewed interest in recent years. Nevertheless, the approach has suffered from imbalanced datasets. Hence, to get a reliable predictive model for predicting outcomes, specifically in a high proportion of moderate TBI with good outcomes, could be challenging. This work proposes an improved outcome predictive model that combines the absolute power spectral density (PSD) as input features for training random under-sampling boosting decision trees (RUSBoosted Trees) as a classifier. Resting-state, eyes-closed EEG data were obtained from 27 moderate TBI patients with follow-up visits. Patient outcome at 4–10 weeks to 12-month was dichotomized based on the Glasgow Outcome Scale as poor (GOS score ≤ 4) and good outcomes (GOS score = 5). The predictive values of absolute PSD from five frequency bands: <inline-formula> <tex-math notation="LaTeX">$\delta $ </tex-math></inline-formula> (0.5-4Hz), <inline-formula> <tex-math notation="LaTeX">$\theta $ </tex-math></inline-formula> (4-7Hz), <inline-formula> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> (7-13Hz), <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> (13-30Hz) and <inline-formula> <tex-math notation="LaTeX">$\gamma $ </tex-math></inline-formula> (30–100Hz) were evaluated to identify the most informative predictors for reliable prediction outcomes. RUSBoosted Trees performed best at discriminating patients into two outcomes categories (G-Mean = 92.95%, TP_rate = 100%, TN_rate = 86.4%) of absolute PSD in <inline-formula> <tex-math notation="LaTeX">$\delta $ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$\gamma $ </tex-math></inline-formula> bands, which was excellent compared to the other state-of-the-art methods. The highest area under the curve (AUC) of absolute PSD in <inline-formula> <tex-math notation="LaTeX">$\delta $ </tex-math></inline-formula> (AUC<inline-formula> <tex-math notation="LaTeX">$_\delta =0.97$ </tex-math></inline-formula>) and <inline-formula> <tex-math notation="LaTeX">$\gamma $ </tex-math></inline-formula> (AUC<inline-formula> <tex-math notation="LaTeX">$_\gamma =0.95$ </tex-math></inline-formula>) revealed their predictive values as robust prognostic markers for prediction outcomes. The RUSBoosted Trees presents a promising result in prognosis prediction of highly imbalanced data, making it an accessible prediction tool for clinical decision-making, unlike the black-box approaches.

• Publication year

  2021

• Venue

  IEEE Access

• Publication date

  Unknown publication date

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.1109/ACCESS.2021.3109780
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Evolutionary Computing and Mobile Sustainable Networks

  2021cited by this paper
• Convolutional Neural Network Utilizing Error-Correcting Output Codes Support Vector Machine for Classification of Non-Severe Traumatic Brain Injury From Electroencephalogram Signal

  2021cited by this paper
• Magnetoencephalography in the Detection and Characterization of Brain Abnormalities Associated with Traumatic Brain Injury: A Comprehensive Review

  2021cited by this paper
• Epileptic Seizure Detection With a Reduced Montage: A Way Forward for Ambulatory EEG Devices

  2020cited by this paper
• Detection of Moderate Traumatic Brain Injury from Resting-State Eye-Closed Electroencephalography

  2020influential reference
• Sleep Spindle Detection Using RUSBoost and Synchrosqueezed Wavelet Transform

  2020cited by this paper
• Analysis of epileptic EEG signals by using dynamic mode decomposition and spectrum

  2020cited by this paper
• Classification of the stages of Parkinson’s disease using novel higher-order statistical features of EEG signals

  2020cited by this paper
• Eye movement‐related brain potentials during assisted navigation in real‐world environments

  2020cited by this paper
• Novel approaches to prediction in severe brain injury

  2020cited by this paper
• Ensemble Learning-Based EEG Feature Vector Analysis for Brain Computer Interface

  2020cited by this paper
• Boosting methods for multi-class imbalanced data classification: an experimental review

  2020influential reference
• Integrating old and new complexity measures toward automated seizure detection from long-term video EEG recordings

  2020cited by this paper
• Ensemble Usage for Classification of EEG Signals A Review with Comparison

  2020cited by this paper
• EEG signal varies with different outcomes in comatose patients: a quantitative method of electroencephalography reactivity.

  2020cited by this paper
• Examining imbalanced classification algorithms in predicting real-time traffic crash risk.

  2020cited by this paper
• Machine Learning Algorithms and Quantitative Electroencephalography Predictors for Outcome Prediction in Traumatic Brain Injury: A Systematic Review

  2020influential reference
• Prognostic Research in Traumatic Brain Injury: Markers, Modeling, and Methodological Principles

  2020cited by this paper
• Empirical Comparison of Area under ROC curve (AUC) and Mathew Correlation Coefficient (MCC) for Evaluating Machine Learning Algorithms on Imbalanced Datasets for Binary Classification

  2019cited by this paper
• A Classification Model For Class Imbalance Dataset Using Genetic Programming

  2019cited by this paper
• Objective Classification of mTBI Using Machine Learning on a Combination of Frontopolar Electroencephalography Measurements and Self-reported Symptoms

  2019cited by this paper
• Frequency-Dependent Changes in Resting State Electroencephalogram Functional Networks after Traumatic Brain Injury in Piglets

  2019cited by this paper
• Machine Learning for Prediction of Posttraumatic Stress and Resilience Following Trauma: An Overview of Basic Concepts and Recent Advances.

  2019cited by this paper
• Patient Nonspecific Epilepsy Detection Using EEG

  2019cited by this paper
• Machine learning in mental health: a scoping review of methods and applications

  2019cited by this paper
• Continuous Electroencephalography After Moderate to Severe Traumatic Brain Injury

  2019cited by this paper
• Practical Guide for Biomedical Signals Analysis Using Machine Learning Techniques

  2019cited by this paper
• The use of machine learning techniques in trauma-related disorders: a systematic review.

  2019cited by this paper
• Predicting outcome in patients with moderate to severe traumatic brain injury using electroencephalography

  2019influential reference
• Low Complexity Automatic Stationary Wavelet Transform for Elimination of Eye Blinks from EEG

  2019cited by this paper
• A Systematic Review on Imbalanced Data Challenges in Machine Learning

  2019cited by this paper
• Sampling Techniques to Overcome Class Imbalance in a Cyberbullying Context

  2019cited by this paper
• A review of feature extraction and performance evaluation in epileptic seizure detection using EEG

  2019cited by this paper
• Predicting Outcomes in Patients with Traumatic Brain Injury Using Machine Learning Models

  2019cited by this paper
• An Evolutionary UnderBagging Approach to Tackle the Survival Prediction of Trauma Patients: A Case Study at the Hospital of Navarre

  2019cited by this paper
• Benchmarking framework for class imbalance problem using novel sampling approach for big data

  2019cited by this paper
• Automatic Seizure Detection Using Multi-Resolution Dynamic Mode Decomposition

  2019cited by this paper
• Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models

  2018cited by this paper
• Natural and Artificial Intelligence in Neurosurgery: A Systematic Review

  2018cited by this paper
• A regularized ensemble framework of deep learning for cancer detection from multi-class, imbalanced training data

  2018cited by this paper
• Moderate Traumatic Brain Injury: Clinical Characteristics and a Prognostic Model of 12-Month Outcome.

  2018cited by this paper
• Predicting Long-Term Global Outcome after Traumatic Brain Injury: Development of a Practical Prognostic Tool Using the Traumatic Brain Injury Model Systems National Database

  2018influential reference
• Consciousness Indexing and Outcome Prediction with Resting-State EEG in Severe Disorders of Consciousness

  2018influential reference
• Ensemble-classifiers-assisted detection of cerebral microbleeds in brain MRI

  2018cited by this paper
• Covariate shift estimation based adaptive ensemble learning for handling non-stationarity in motor imagery related EEG-based brain-computer interface

  2018cited by this paper
• Machine Learning and Neurosurgical Outcome Prediction: A Systematic Review.

  2018cited by this paper
• Quantitative EEG Parameters for Prediction of Outcome in Severe Traumatic Brain Injury: Development Study

  2018influential reference
• A New Ensemble Classification System For Fracture Zone Prediction Using Imbalanced Micro-CT Bone Morphometrical Data

  2018cited by this paper
• Predicting Age From Brain EEG Signals—A Machine Learning Approach

  2018cited by this paper
• Social power and frontal alpha asymmetry

  2018cited by this paper
• Dynamic Mode Decomposition Based Epileptic Seizure Detection from Scalp EEG

  2018cited by this paper
• Sleep stage classification using single-channel EOG

  2018cited by this paper
• A survey on addressing high-class imbalance in big data

  2018cited by this paper
• Machine learning analyses can differentiate meningioma grade by features on magnetic resonance imaging.

  2018cited by this paper
• Machine learning studies on major brain diseases: 5-year trends of 2014–2018

  2018cited by this paper
• Sleep Stage Scoring of Single-Channel EEG Signal based on RUSBoost Classifier

  2018cited by this paper
• An introduction and overview of machine learning in neurosurgical care

  2017cited by this paper
• A systematic study of the class imbalance problem in convolutional neural networks

  2017cited by this paper
• Impact of Glasgow Coma Scale score and pupil parameters on mortality rate and outcome in pediatric and adult severe traumatic brain injury: a retrospective, multicenter cohort study.

  2017cited by this paper
• A Review of Resting-State Electroencephalography Analysis in Disorders of Consciousness

  2017cited by this paper
• Structural imaging of mild traumatic brain injury may not be enough: overview of functional and metabolic imaging of mild traumatic brain injury

  2017cited by this paper
• Automated identification of sleep states from EEG signals by means of ensemble empirical mode decomposition and random under sampling boosting

  2017cited by this paper
• Increased prognostic accuracy of TBI when a brain electrical activity biomarker is added to loss of consciousness (LOC)

  2017cited by this paper
• Machine Learning for Predicting Outcomes in Trauma

  2017cited by this paper
• “Look at my classifier's result”: Disentangling unresponsive from (minimally) conscious patients

  2017cited by this paper
• Predicting Outcome 12 Months after Mild Traumatic Brain Injury in Patients Admitted to a Neurosurgery Service

  2017cited by this paper
• Traumatic brain injury: An EEG point of view

  2017cited by this paper
• Big Data in traumatic brain injury; promise and challenges

  2017cited by this paper
• A revised glossary of terms most commonly used by clinical electroencephalographers and updated proposal for the report format of the EEG findings. Revision 2017

  2017cited by this paper
• Ensemble Decision Tree Models Using RUSBoost for Estimating Risk of Iron Failure in Drinking Water Distribution Systems

  2017cited by this paper
• A robust approach towards epileptic seizure detection

  2016cited by this paper
• A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral features.

  2016cited by this paper
• Adapted ensemble classification algorithm based on multiple classifier system and feature selection for classifying multi-class imbalanced data

  2016influential reference
• Adapted ensemble classification algorithm based on multiple classifier system and feature selection for classifying multi-class imbalanced data

  2016influential reference
• Machine learning identification of EEG features predicting working memory performance in schizophrenia and healthy adults

  2016cited by this paper
• Identifying Important Attributes for Prognostic Prediction in Traumatic Brain Injury Patients

  2016influential reference
• Comparison of EEG signal features and ensemble learning methods for motor imagery classification

  2016cited by this paper
• Early prediction of outcome after severe traumatic brain injury: a simple and practical model

  2016cited by this paper
• The Glasgow Outcome Scale — 40 years of application and refinement

  2016influential reference
• Coherence in resting-state EEG as a predictor for the recovery from unresponsive wakefulness syndrome

  2016cited by this paper
• Automatic EEG processing for the early diagnosis of Traumatic Brain Injury

  2016cited by this paper
• Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques

  2015cited by this paper
• Classification with class imbalance problem: A review

  2015influential reference
• Traumatic Brain Injury Detection Using Electrophysiological Methods

  2015cited by this paper
• EEG artifact elimination by extraction of ICA-component features using image processing algorithms.

  2015cited by this paper
• Prediction of outcome in traumatic brain injury patients using long-term qEEG features

  2015influential reference
• Performance analysis of ensemble methods for multi-class classification of motor imagery EEG signal

  2014cited by this paper
• Methods of EEG Signal Features Extraction Using Linear Analysis in Frequency and Time-Frequency Domains

  2014cited by this paper
• [EEG-correlates of consciousness recovery after traumatic brain injury].

  2014influential reference
• Predictability of intracranial pressure level in traumatic brain injury: features extraction, statistical analysis and machine learning-based evaluation

  2013influential reference
• Outcome Prediction in Moderate and Severe Traumatic Brain Injury: A Focus on Computed Tomography Variables

  2013cited by this paper
• Online Bagging and Boosting for Imbalanced Data Streams

  2013cited by this paper
• A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches

  2012cited by this paper
• Predicting outcomes after traumatic brain injury: The development and validation of prognostic models based on admission characteristics

  2012cited by this paper
• Does the Extended Glasgow Outcome Scale Add Value to the Conventional Glasgow Outcome Scale?

  2012cited by this paper
• Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation

  2011cited by this paper
• Epidemiology, Severity Classification, and Outcome of Moderate and Severe Traumatic Brain Injury: A Prospective Multicenter Study

  2011cited by this paper
• Outcome measures for traumatic brain injury.

  2011cited by this paper
• RUSBoost: A Hybrid Approach to Alleviating Class Imbalance

  2010cited by this paper
• PATIENTS WITH MODERATE HEAD INJURY: A PROSPECTIVE MULTICENTER STUDY OF 315 PATIENTS

  2009cited by this paper

• Insights into computer-aided EEG signal processing for traumatic brain injury assessment: A review

  2025cites this paper
• BiLSTM-Based Power Spectral Density Prediction in Low Sub-Band Wire Environments

  2025cites this paper
• Multivariate modeling and prediction of cerebral physiology in acute traumatic neural injury: A scoping review

  2024cites this paper
• Ensemble Techniques Based Risk Classification for Maternal Health During Pregnancy

  2024cites this paper
• Predicting return to work after traumatic brain injury using machine learning and administrative data

  2023cites this paper
• Quantitative Electroencephalography Objectivity and Reliability in the Diagnosis and Management of Traumatic Brain Injury: A Systematic Review

  2023cites this paper
• Spectrum Evaluation in CR-Based Smart Healthcare Systems Using Optimizable Tree Machine Learning Approach

  2023cites this paper
• A Long Short-Term Memory Network Using Resting-State Electroencephalogram to Predict Outcomes Following Moderate Traumatic Brain Injury

  2023cites this paper
• Detection of emotional and behavioural changes after traumatic brain injury: A comprehensive survey

  2023cites this paper
• Perbandingan Metoda K-NN, Random Forest dan 1D CNN untuk Mengklasifikasi Data EEG Eye State

  2023cites this paper
• Prediction of Recovery from Traumatic Brain Injury with EEG Power Spectrum in Combination of Independent Component Analysis and RUSBoost Model

  2022influential citation
• A novel Random Forest integrated model for imbalanced data classification problem

  2022cites this paper