Investigating systematic bias in brain age estimation with application to post‐traumatic stress disorders

• Published in: Human brain mapping Vol. 40; no. 11; pp. 3143 - 3152
• Main Authors: Liang, Hualou, Zhang, Fengqing, Niu, Xin
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.08.2019
• Subjects: Adolescent; Adult; Age; Age determination; Aged; Aged, 80 and over; Aging; Anatomy; Artificial neural networks; Bias; Biomarkers; Brain; Brain - diagnostic imaging; brain age prediction; Brain architecture; Child; Chronology; Datasets; Disorders; Evaluation; Humans; Learning algorithms; Machine Learning; Magnetic Resonance Imaging; Medical imaging; Mental disorders; Middle Aged; Nervous system diseases; Neural networks; Neurodevelopmental disorders; Neuroimaging; Neuroimaging - methods; Neurology; Post-traumatic stress disorder; Predictions; PTSD; regression to the mean; Stress Disorders, Post-Traumatic - diagnostic imaging; Traumatic brain injury; Young Adult; PTSD; machine-learning; regression to the mean; bias; brain age prediction

Brain age prediction using machine‐learning techniques has recently attracted growing attention, as it has the potential to serve as a biomarker for characterizing the typical brain development and neuropsychiatric disorders. Yet one long‐standing problem is that the predicted brain age is overestim...