There is an increasing demand to develop computer-aided diagnosis (CAD) and prognosis (CAP) systems using artificial intelligence (AI) methods in various medical fields for accurate disease diagnosis and prognosis prediction. In particular, psychiatry needs such AI-based CAD and CAP systems to complement the potential misdiagnosis of interview-based diagnosis caused by overlapped symptoms between different psychiatric disorders (e.g., hallucination in schizophrenia and bipolar disorder). A prerequisite of developing reliable AI-based CAD and CAP systems is to find promising endophenotype biomarkers reflecting pathophysiological traits of psychiatric disorders. Early neuroimaging and kinesics studies have revealed functional brain and behavior abnormalities of psychiatric disorders as compared to health individuals, respectively, and recent studies have attempted to use them as endophenotype biomarkers to develop AI-based CAD and CAP systems for psychiatric disorders. Even though some psychiatric studies have reported promising results in terms of the prediction performance of endophenotype biomarkers, there is still abundant room to improve the performance of AI-based CAD and CAP systems for psychiatric disorders. This research topic aims to share the cutting-edge trends and future directions of AI-based CAD and CAP systems for psychiatric disorders, thereby providing useful literature references that encourage the further development of AI-based CAD and CAP systems for psychiatric disorders.
We encourage researchers to submit Original Research, Reviews, Methods, Perspectives, Case Reports, Conceptual Analyses, Data Reports, General Commentaries, and Brief Research Reports that contribute to the advance of AI-based CAD and CAP systems for psychiatric disorders, such as schizophrenia, depression disorder, anxiety disorder, bipolar disorder, post-traumatic stress disorder, attention deficit hyperactivity disorder, addiction, autism spectrum disorder, and so on. The research conducted based on the following neuroimaging and kinesics tools will be considered, but not limited to: neuroimaging - electroencephalography (EEG), magnetoencephalography (MEG), functional near-infrared spectroscopy (fNIRS), functional magnetic resonance imaging (fMRI), and their combinations; kinesics – facial expressions, body movements, language, and other biosignals (e.g.: EOG, ECG, and EMG).
The Research Topic can include, but is not limited to:
• Development of neuroimaging-based CAD/CAP systems
• Development of kinesics-based CAD/CAP systems
• Novel machine learning/deep learning algorithms for developing CAD/CAP systems
• Novel experimental paradigms to find biological biomarkers for psychiatric disorders
• Application of visualization and statistical techniques for biological biomarkers
• Interpretation techniques for biological biomarkers
• Releasing publicly available neuroimaging/kinesics datasets for psychiatric disorders
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Keywords: Computer-aided diagnosis (CAD), computer-aided prognosis (CAP), psychiatric disorders, artificial intelligence (AI), machine learning, electroencephalography (EEG), magnetoencephalography (MEG), functional magnetic resonance imaging (fMRI), kinesics, endophenotype biomarkers
Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
