A machine learning approach to identify functional biomarkers in human prefrontal cortex for individuals with traumatic brain injury using functional near‐infrared spectroscopy

• Published in: Brain and behavior Vol. 6; no. 11; pp. e00541 - n/a
• Main Authors: Karamzadeh, Nader, Amyot, Franck, Kenney, Kimbra, Anderson, Afrouz, Chowdhry, Fatima, Dashtestani, Hadis, Wassermann, Eric M., Chernomordik, Victor, Boccara, Claude, Wegman, Edward, Diaz‐Arrastia, Ramon, Gandjbakhche, Amir H.
• Format: Journal Article
• Language: English
• Published: United States John Wiley & Sons, Inc 01.11.2016; John Wiley and Sons Inc
• Subjects: Accuracy; Adult; Artificial intelligence; Biomarkers; Biomarkers - metabolism; Blood; Brain Injuries, Traumatic - diagnosis; Brain Injuries, Traumatic - diagnostic imaging; Brain Injuries, Traumatic - metabolism; Case-Control Studies; Childrens health; Classification; feature selection; Female; Funding; Hemodynamics; Hemoglobin; Humans; Machine Learning; Male; Medical imaging; Medical research; near‐infrared spectroscopy; Neurological disorders; Neurosciences; Original Research; Prefrontal Cortex - diagnostic imaging; Prefrontal Cortex - metabolism; Spectroscopy, Near-Infrared - methods; Spectrum analysis; time series feature extraction; Traumatic brain injury; wrapper method; near‐infrared spectroscopy; time series feature extraction; traumatic brain injury; classification; machine learning; wrapper method; feature selection
• ISSN: 2162-3279; 2162-3279
• DOI: 10.1002/brb3.541

Background We have explored the potential prefrontal hemodynamic biomarkers to characterize subjects with Traumatic Brain Injury (TBI) by employing the multivariate machine learning approach and introducing a novel task‐related hemodynamic response detection followed by a heuristic search for optimum set of hemodynamic features. To achieve this goal, the hemodynamic response from a group of 31 healthy controls and 30 chronic TBI subjects were recorded as they performed a complexity task. Methods To determine the optimum hemodynamic features, we considered 11 features and their combinations in characterizing TBI subjects. We investigated the significance of the features by utilizing a machine learning classification algorithm to score all the possible combinations of features according to their predictive power. Results and Conclusions The identified optimum feature elements resulted in classification accuracy, sensitivity, and specificity of 85%, 85%, and 84%, respectively. Classification improvement was achieved for TBI subject classification through feature combination. It signified the major advantage of the multivariate analysis over the commonly used univariate analysis suggesting that the features that are individually irrelevant in characterizing the data may become relevant when used in combination. We also conducted a spatio‐temporal classification to identify regions within the prefrontal cortex (PFC) that contribute in distinguishing between TBI and healthy subjects. As expected, Brodmann areas (BA) 10 within the PFC were isolated as the region that healthy subjects (unlike subjects with TBI), showed major hemodynamic activity in response to the High Complexity task. Overall, our results indicate that identified temporal and spatio‐temporal features from PFC's hemodynamic activity are promising biomarkers in classifying subjects with TBI. The manuscript describes a methodology to explore and identify potential hemodynamic biomarkers to be utilized for classifying subjects with TBI. The proposed approach searches a large set of hemodynamic feature combinations and identifies a set of features that provides the optimum classification between the TBI and healthy populations.