During the past 50 years, the exponential rise of data and computing power has rapidly informed how we do science. As a result, massive amounts of data and computational pipelines are generated that have spawned a new era of how we approach understanding and treating various healthcare problems, including those related to neuropsychiatric disorders. Current medical practice is evidence-based, rating the strength of scientific evidence for deciding translation from research to medical implementation. Building evidence for translation is particularly difficult in mental health due to heterogeneous populations and complex syndromes. These factors create a gap in rigorous scientific evidence hampering the management and treatment of neuropsychiatric disorders. Data-intensive research can help overcome some of these limitations through the power of computing, big-data, machine learning (ML), and artificial intelligence (AI) applications to such data. Such tools and support for augmented evidence-based medicine enable novel research paradigms for generating new knowledge from a variety of data resources.
A central goal for research on risk/protective factors concerns the use of this information to determine plausible intervention targets to diminish the likelihood of the expression of neuropsychiatric outcome responses, or to diminish their magnitude, once expressed. For such research to reveal such intervention targets, causal factors for outcomes must be determined. A causal factor is - by definition - a factor that - if changed - changes the likelihood of an outcome. Intervention on a non-causal factor cannot change an outcome. Experimental research is typically considered the near exclusive means for causal inference, but etiological experiments can rarely be conducted with humans: and the vast majority of published human studies on etiology are observational. Recognizing the need to extract actionable knowledge from observational data, powerful Computational Causal Discovery (CCD) methods have been developed and successfully applied to a variety of medical disorders, and new research - which will be the focus of this collection.
We welcome Original Research, Review, and Systematic Review papers and themes of particular interest include
• Causal modeling to aid in diagnosis
• Causal modeling to aid in treatment planning
• Discovery of causal relationships among complex symptoms presented in the same or different mental health disorders
• Discovery of causal neural mechanism from imaging data and their relationships with mental health disorders.
• Precision Medicine aided by causal discovery
During the past 50 years, the exponential rise of data and computing power has rapidly informed how we do science. As a result, massive amounts of data and computational pipelines are generated that have spawned a new era of how we approach understanding and treating various healthcare problems, including those related to neuropsychiatric disorders. Current medical practice is evidence-based, rating the strength of scientific evidence for deciding translation from research to medical implementation. Building evidence for translation is particularly difficult in mental health due to heterogeneous populations and complex syndromes. These factors create a gap in rigorous scientific evidence hampering the management and treatment of neuropsychiatric disorders. Data-intensive research can help overcome some of these limitations through the power of computing, big-data, machine learning (ML), and artificial intelligence (AI) applications to such data. Such tools and support for augmented evidence-based medicine enable novel research paradigms for generating new knowledge from a variety of data resources.
A central goal for research on risk/protective factors concerns the use of this information to determine plausible intervention targets to diminish the likelihood of the expression of neuropsychiatric outcome responses, or to diminish their magnitude, once expressed. For such research to reveal such intervention targets, causal factors for outcomes must be determined. A causal factor is - by definition - a factor that - if changed - changes the likelihood of an outcome. Intervention on a non-causal factor cannot change an outcome. Experimental research is typically considered the near exclusive means for causal inference, but etiological experiments can rarely be conducted with humans: and the vast majority of published human studies on etiology are observational. Recognizing the need to extract actionable knowledge from observational data, powerful Computational Causal Discovery (CCD) methods have been developed and successfully applied to a variety of medical disorders, and new research - which will be the focus of this collection.
We welcome Original Research, Review, and Systematic Review papers and themes of particular interest include
• Causal modeling to aid in diagnosis
• Causal modeling to aid in treatment planning
• Discovery of causal relationships among complex symptoms presented in the same or different mental health disorders
• Discovery of causal neural mechanism from imaging data and their relationships with mental health disorders.
• Precision Medicine aided by causal discovery