Matches in SemOpenAlex for { <https://semopenalex.org/work/W3196371155> ?p ?o ?g. }
- W3196371155 endingPage "121631" @default.
- W3196371155 startingPage "121608" @default.
- W3196371155 abstract "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: δ (0.5-4Hz), θ (4-7Hz), α (7-13Hz), β (13-30Hz) and γ (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%, TPrate =100%, TNrate= 86.4%) of absolute PSD in δ and γ bands, which was excellent compared to the other state-of-the-art methods. The highest area under the curve (AUC) of absolute PSD in δ (AUCδ = 0.97) and γ (AUCγ = 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." @default.
- W3196371155 created "2021-09-13" @default.
- W3196371155 creator A5000835810 @default.
- W3196371155 creator A5005069953 @default.
- W3196371155 creator A5034307266 @default.
- W3196371155 creator A5059580206 @default.
- W3196371155 date "2021-01-01" @default.
- W3196371155 modified "2023-10-10" @default.
- W3196371155 title "Improving Outcome Prediction for Traumatic Brain Injury From Imbalanced Datasets Using RUSBoosted Trees on Electroencephalography Spectral Power" @default.
- W3196371155 cites W1551909886 @default.
- W3196371155 cites W1563938718 @default.
- W3196371155 cites W1588282782 @default.
- W3196371155 cites W1594364707 @default.
- W3196371155 cites W1605688901 @default.
- W3196371155 cites W1874700596 @default.
- W3196371155 cites W1941659294 @default.
- W3196371155 cites W1963797793 @default.
- W3196371155 cites W1965002564 @default.
- W3196371155 cites W1974928465 @default.
- W3196371155 cites W1988790447 @default.
- W3196371155 cites W1991109199 @default.
- W3196371155 cites W2001935101 @default.
- W3196371155 cites W2015452969 @default.
- W3196371155 cites W2017693147 @default.
- W3196371155 cites W2021345747 @default.
- W3196371155 cites W2022856590 @default.
- W3196371155 cites W2026177857 @default.
- W3196371155 cites W2031990580 @default.
- W3196371155 cites W2052220822 @default.
- W3196371155 cites W2053724458 @default.
- W3196371155 cites W2055603681 @default.
- W3196371155 cites W2059624626 @default.
- W3196371155 cites W2065347985 @default.
- W3196371155 cites W2067448822 @default.
- W3196371155 cites W2092241603 @default.
- W3196371155 cites W2096945460 @default.
- W3196371155 cites W2099454382 @default.
- W3196371155 cites W2100017480 @default.
- W3196371155 cites W2103367163 @default.
- W3196371155 cites W2128495200 @default.
- W3196371155 cites W2132029553 @default.
- W3196371155 cites W2134489982 @default.
- W3196371155 cites W2135107501 @default.
- W3196371155 cites W2149298154 @default.
- W3196371155 cites W2149308034 @default.
- W3196371155 cites W2149881706 @default.
- W3196371155 cites W2152761983 @default.
- W3196371155 cites W2155653793 @default.
- W3196371155 cites W2165740328 @default.
- W3196371155 cites W2189368561 @default.
- W3196371155 cites W2193627466 @default.
- W3196371155 cites W2230683965 @default.
- W3196371155 cites W2289075896 @default.
- W3196371155 cites W2301460319 @default.
- W3196371155 cites W2323662613 @default.
- W3196371155 cites W2328444280 @default.
- W3196371155 cites W2472628610 @default.
- W3196371155 cites W2482168716 @default.
- W3196371155 cites W2516299774 @default.
- W3196371155 cites W2516769407 @default.
- W3196371155 cites W2520599539 @default.
- W3196371155 cites W2520959200 @default.
- W3196371155 cites W2555125760 @default.
- W3196371155 cites W2563514688 @default.
- W3196371155 cites W2565543439 @default.
- W3196371155 cites W2588761628 @default.
- W3196371155 cites W2591294903 @default.
- W3196371155 cites W2592953314 @default.
- W3196371155 cites W2605946936 @default.
- W3196371155 cites W2606183213 @default.
- W3196371155 cites W2612337648 @default.
- W3196371155 cites W2731187515 @default.
- W3196371155 cites W2735428336 @default.
- W3196371155 cites W2744012576 @default.
- W3196371155 cites W2754118176 @default.
- W3196371155 cites W2761529114 @default.
- W3196371155 cites W2762418274 @default.
- W3196371155 cites W2763556273 @default.
- W3196371155 cites W2767106145 @default.
- W3196371155 cites W2768878216 @default.
- W3196371155 cites W2768899399 @default.
- W3196371155 cites W2778854158 @default.
- W3196371155 cites W2791286326 @default.
- W3196371155 cites W2795137940 @default.
- W3196371155 cites W2799162396 @default.
- W3196371155 cites W2802328741 @default.
- W3196371155 cites W2804785658 @default.
- W3196371155 cites W2805766146 @default.
- W3196371155 cites W2874253909 @default.
- W3196371155 cites W2883443154 @default.
- W3196371155 cites W2888087868 @default.
- W3196371155 cites W2899434936 @default.
- W3196371155 cites W2900166205 @default.
- W3196371155 cites W2901140917 @default.
- W3196371155 cites W2902620820 @default.
- W3196371155 cites W2910261017 @default.
- W3196371155 cites W2911033054 @default.
- W3196371155 cites W2911119486 @default.