Predicting the age of brain from EEG data holds significant promise for advancing healthcare diagnostics. By comparing predicted brain age with the biological age of patients, clinicians can gain valuable insights into the overall health status of individuals. To assist clinical decision making, the latest advance in AI research shows promise in the analysis of routine clinical data; however, challenges including limited availability of high-quality training data are limiting the full capacity of AI in neurology and clinical workflow. Therefore, this work proposes a novel approach using generative machine learning models to augment the training dataset for building models to predict brain age from EEG recordings. Our findings reveal that integrating synthetic data significantly boosts the performance of models. The study holds significant implications for neurological engineering, in particular for EEG-based age prediction tasks.
Paper
Full text
Enhancing Brain Age Prediction: A Generative AI Approach for EEG Machine Learning Models
Semantic Scholar · Computer Science · 2024
Abstract
Predicting the age of brain from EEG data holds significant promise for advancing healthcare diagnostics. By comparing predicted brain age with the biological age of patients, clinicians can gain valuable insights into the overall health status of individuals. To assist clinical decision making, the latest advance in AI research shows promise in the analysis of routine clinical data; however, challenges including limited availability of high-quality training data are limiting the full capacity of AI in neurology and clinical workflow. Therefore, this work proposes a novel approach using generative machine learning models to augment the training dataset for building models to predict brain age from EEG recordings. Our findings reveal that integrating synthetic data significantly boosts the performance of models. The study holds significant implications for neurological engineering, in particular for EEG-based age prediction tasks.