Despite a century of research in psychiatry, diagnoses for such disorders are still challenging, and psychotherapeutic or pharmaceutical treatments are often ineffective for the definite patients. Given the high morbidity and social burden, there is an urgent need for innovative techniques to help identify high-risk individuals and provide precise prediction of the progression, which would be helpful for the prevention and intervention at early stage.
At present, artificial intelligence (AI), especially deep learning, has been widely applied to the analysis of multimodal medical data. Besides, more accurate and quantitative methods for neuroimaging data acquisition are emerging, such as diffusion spectrum imaging for tracking the orientation of crossed fibers in the brain, portable electroencephalogram (EEG) with high temporal resolution to detect brain electrical activity in real world, and brain-computer interface (BCI) for study the relationship between the brain and behavior. The crosstalk between the AI analytical techniques and the data acquisition methods provides a prerequisite for more precise diagnosis and prediction for the psychiatric disorders.
AI algorithm can be used to diagnose and classify different psychiatric disorders, such as autism spectrum disorder, bipolar disorder, schizophrenia, etc. Studies have shown that different AI algorithms and data modalities are crucial to the classification of such disorders, and AI can provide more accurate prediction for the progression and prognosis.
Therefore, the current topic focuses on AI statistical functions from multidimensional data sets to make generalizable diagnosis and prediction about individuals with mental illness. It is designed to provide an accessible understanding of why this approach is important and useful for future clinical practice, and advance our understanding of the mechanisms and pathogenesis of psychiatric disorders.
The scope of the topic includes AI innovation and application in the diagnosis, prediction, and treatment of people suffering from mental illness using clinical and biological data. We welcome submissions of the following sub-topics (but not limited to):
--AI prediction or diagnosis for the psychiatric disorders across the preclinical, prodrome, clinical and remission stage, including:
1) Depression
2) Schizophrenia
3) Autism pectrum disorder
4) bipolar disorder
5) Attention deficit hyperactivity disorder (ADHD)
6) etc
--AI techniques in data processing associated with psychiatric disorders
1) Detection or classification of anatomical structures, lesions or lesion subtypes/stages
2) Biomedical image segmentation, reconstruction, or fusion
3) Explainable AI
4) Reinforcement learning
5) Natural language processing
6) Semi-supervised and unsupervised learning algorithms
7) Federated Learning algorithms
Despite a century of research in psychiatry, diagnoses for such disorders are still challenging, and psychotherapeutic or pharmaceutical treatments are often ineffective for the definite patients. Given the high morbidity and social burden, there is an urgent need for innovative techniques to help identify high-risk individuals and provide precise prediction of the progression, which would be helpful for the prevention and intervention at early stage.
At present, artificial intelligence (AI), especially deep learning, has been widely applied to the analysis of multimodal medical data. Besides, more accurate and quantitative methods for neuroimaging data acquisition are emerging, such as diffusion spectrum imaging for tracking the orientation of crossed fibers in the brain, portable electroencephalogram (EEG) with high temporal resolution to detect brain electrical activity in real world, and brain-computer interface (BCI) for study the relationship between the brain and behavior. The crosstalk between the AI analytical techniques and the data acquisition methods provides a prerequisite for more precise diagnosis and prediction for the psychiatric disorders.
AI algorithm can be used to diagnose and classify different psychiatric disorders, such as autism spectrum disorder, bipolar disorder, schizophrenia, etc. Studies have shown that different AI algorithms and data modalities are crucial to the classification of such disorders, and AI can provide more accurate prediction for the progression and prognosis.
Therefore, the current topic focuses on AI statistical functions from multidimensional data sets to make generalizable diagnosis and prediction about individuals with mental illness. It is designed to provide an accessible understanding of why this approach is important and useful for future clinical practice, and advance our understanding of the mechanisms and pathogenesis of psychiatric disorders.
The scope of the topic includes AI innovation and application in the diagnosis, prediction, and treatment of people suffering from mental illness using clinical and biological data. We welcome submissions of the following sub-topics (but not limited to):
--AI prediction or diagnosis for the psychiatric disorders across the preclinical, prodrome, clinical and remission stage, including:
1) Depression
2) Schizophrenia
3) Autism pectrum disorder
4) bipolar disorder
5) Attention deficit hyperactivity disorder (ADHD)
6) etc
--AI techniques in data processing associated with psychiatric disorders
1) Detection or classification of anatomical structures, lesions or lesion subtypes/stages
2) Biomedical image segmentation, reconstruction, or fusion
3) Explainable AI
4) Reinforcement learning
5) Natural language processing
6) Semi-supervised and unsupervised learning algorithms
7) Federated Learning algorithms