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 -ve frequency bands: delta (0.5-4Hz), theta (4-7Hz), alpha (7-13Hz), beta (13-30Hz) and gamma (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 D 92.95%, TPrate = 100%, TNrate = 86.4%) of absolute PSD in alpha and gamma bands, which was excellent compared to the other state-of-the-art methods. The highest area under the curve (AUC) of absolute PSD in delta (AUC(delta) = 0.97) and gamma (AUC(gamma) = 0.95) 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.

Automated summary

This study introduces an improved outcome predictive model using absolute power spectral density as input features for training, with RUSBoosted Trees as the classifier. The research found that the absolute PSD in the alpha and gamma bands had higher predictive values for outcomes compared to other methods.