Computational phenotyping in psychosis risk: Language, speech acoustics and face expression
Increasingly, data-driven methods have been implemented to understand the structure and causes of psychopathology. Language is the main source of information in psychiatry and represents “big data” at the level of the individual. Language and behavior are amenable to computational “natural language processing” (NLP) analytics, which may help operationalize the mental status exam. In this review, we highlight the application of NLP to schizophrenia and its risk states as an exemplar of its use, operationalizing tangential and concrete speech as reductions in semantic coherence and syntactic complexity, respectively. Other clinical applications are reviewed, including forecasting of suicide risk and detection of intoxication. Future directions include the application of NLP more broadly to behavior, including intonation/prosody, facial expression and gesture, and the integration of these in dyads and during discourse. Similar NLP analytics can also be applied beyond humans to behavioral motifs across species, important for modeling psychopathology in animal models.
Presenter: Cheryl Corcoran
Cheryl Corcoran is Associate Professor and Leader in Psychosis Risk at the Icahn School of Medicine at Mount Sinai. She is a graduate of Harvard College and Harvard Medical School and has a masters in biostatistics. Dr. Corcoran has twenty-five years’ experience in research on “clinical high risk” for psychosis, encompassing natural language processing (NLP), sensory processing (auditory/visual/olfactory), social cognition, neuroimaging, clinical correlates, cannabis/stress exposures, nosology, ethics/stigma, clinical trials, and services.
Her most recent focus has been on using artificial intelligence (AI) for computational phenotyping, including analyses of the semantic and syntactic structure of language across stages of schizophrenia, including psychosis risk. She has federal NIMH grants to study both the associated neural correlates of this language impairment, and the generalizability of these deficits to cohorts worldwide. She is now expanding this use of AI to examine abnormal speech acoustics and pause behavior, and abnormal face expression across stages of schizophrenia, including risk states.