Modern artificial intelligence approaches have been largely inspired by biological neural networks, and thus to no surprise, they found extensive applications in the understanding of neurological disorders. Nowadays highly efficient diagnostic methods are largely based on deep learning procedures which, due to their inherent complexity, could hardly be understood any longer, being increasingly represented by black-box-style solutions, that appear among key limitations preventing their further translation into clinical practice. Finding successful integrative solutions where modern artificial intelligence approaches are complemented by functional models with few parameters that could be directly interpreted by medical practitioners represents one of the key challenges. Potential approaches to the problem include, while are not limited to, the combination of unsupervised data-driven with supervised knowledge-driven models, functional models with few directly interpretable parameters obtained using statistical analysis and/or dimensionality reduction methods, with applications ranging from retrospective analysis to experimental conditions and clinical applications.
The goal of this Research Topic is to bring together analytical, computational, and statistical approaches to facilitate the development of both efficient and interpretable neurophysiological models, leading to a better understanding of neurological disorders, while aiming at the improvement of their early diagnostic and management control strategies, altogether contributing to the increased effectiveness of experimental and clinical data interpretation.
Research articles, surveys, and technical notes are welcome to this Topic including, but not limited to, the following:
– Data-driven and knowledge-driven approaches to the diagnosis and modeling of neurodegenerative disorders
– Modelling concepts and their applications from retrospective analysis to experimental animal models and clinical applications
– AI-based integrative solutions including practically oriented support systems for both experimental research and clinical diagnostics of neurological disorders
Modern artificial intelligence approaches have been largely inspired by biological neural networks, and thus to no surprise, they found extensive applications in the understanding of neurological disorders. Nowadays highly efficient diagnostic methods are largely based on deep learning procedures which, due to their inherent complexity, could hardly be understood any longer, being increasingly represented by black-box-style solutions, that appear among key limitations preventing their further translation into clinical practice. Finding successful integrative solutions where modern artificial intelligence approaches are complemented by functional models with few parameters that could be directly interpreted by medical practitioners represents one of the key challenges. Potential approaches to the problem include, while are not limited to, the combination of unsupervised data-driven with supervised knowledge-driven models, functional models with few directly interpretable parameters obtained using statistical analysis and/or dimensionality reduction methods, with applications ranging from retrospective analysis to experimental conditions and clinical applications.
The goal of this Research Topic is to bring together analytical, computational, and statistical approaches to facilitate the development of both efficient and interpretable neurophysiological models, leading to a better understanding of neurological disorders, while aiming at the improvement of their early diagnostic and management control strategies, altogether contributing to the increased effectiveness of experimental and clinical data interpretation.
Research articles, surveys, and technical notes are welcome to this Topic including, but not limited to, the following:
– Data-driven and knowledge-driven approaches to the diagnosis and modeling of neurodegenerative disorders
– Modelling concepts and their applications from retrospective analysis to experimental animal models and clinical applications
– AI-based integrative solutions including practically oriented support systems for both experimental research and clinical diagnostics of neurological disorders