Using Language Processing and Speech Analysis for the Identification of Psychosis and Other Disorders.

Increasingly, data-driven methods have been implemented to understand 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 examination. 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 suicide risk and detecting intoxication. Challenges and future directions are discussed, including biomarker development, harmonization, and 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. Finally, clinical neuroscience can inform the development of artificial intelligence.

[1]  Mariano Sigman,et al.  The interpretation of dream meaning: Resolving ambiguity using Latent Semantic Analysis in a small corpus of text , 2017, Consciousness and Cognition.

[2]  G. Cecchi,et al.  Prediction of psychosis across protocols and risk cohorts using automated language analysis , 2018, World psychiatry : official journal of the World Psychiatric Association.

[3]  Minna Lyons,et al.  Mental distress and language use: Linguistic analysis of discussion forum posts , 2018, Comput. Hum. Behav..

[4]  G. Cecchi,et al.  Natural Language Processing: Opportunities and Challenges for Patients, Providers, and Hospital Systems , 2019, Psychiatric Annals.

[5]  Peter F. Liddle,et al.  Speech structure links the neural and socio-behavioural correlates of psychotic disorders , 2019, Progress in Neuro-Psychopharmacology and Biological Psychiatry.

[6]  Arthur C. Graesser,et al.  Automated Evaluation of Text and Discourse with Coh-Metrix: List of Tables , 2014 .

[7]  S. Barker,et al.  “Subject to pain: Ricoeur, Foucault, and emplotting discourses in an illness narrative” , 2017 .

[8]  S. A. Roberts,et al.  Thought disorder in mid-childhood as a predictor of adulthood diagnostic outcome: findings from the New York High-Risk Project , 2012, Psychological Medicine.

[9]  T. Goldberg,et al.  Quantifying incoherence in speech: An automated methodology and novel application to schizophrenia , 2007, Schizophrenia Research.

[10]  S. R. Datta.  Q&A: Understanding the composition of behavior , 2019, BMC Biology.

[11]  Ravi Iyengar,et al.  Ordered cyclic motifs contribute to dynamic stability in biological and engineered networks , 2008, Proceedings of the National Academy of Sciences.

[12]  E. Walker,et al.  A machine learning approach to predicting psychosis using semantic density and latent content analysis , 2019, npj Schizophrenia.

[13]  Gina R. Kuperberg,et al.  A Hierarchical Generative Framework of Language Processing: Linking Language Perception, Interpretation, and Production Abnormalities in Schizophrenia , 2015, Front. Hum. Neurosci..

[14]  D. Barch,et al.  The effect of language production manipulations on negative thought disorder and discourse coherence disturbances in schizophrenia , 1997, Psychiatry Research.

[15]  C. Honey,et al.  Topographic Mapping of a Hierarchy of Temporal Receptive Windows Using a Narrated Story , 2011, The Journal of Neuroscience.

[16]  G. Cecchi,et al.  Self-reference in psychosis and depression: a language marker of illness , 2016, Psychological Medicine.

[17]  Tianxi Cai,et al.  High Throughput Phenotyping for Dimensional Psychopathology in Electronic Health Records , 2018, Biological Psychiatry.

[18]  B. Elvevåg,et al.  Neural correlates of the relationship between discourse coherence and sensory monitoring in schizophrenia , 2014, Cortex.

[19]  Terje B. Holmlund,et al.  Applying speech technologies to assess verbal memory in patients with serious mental illness , 2020, npj Digital Medicine.

[20]  H. Schnack,et al.  Clinical use of semantic space models in psychiatry and neurology: A systematic review and meta-analysis , 2018, Neuroscience & Biobehavioral Reviews.

[21]  Asra F. Rizvi,et al.  Detecting relapse in youth with psychotic disorders utilizing patient-generated and patient-contributed digital data from Facebook , 2019, npj Schizophrenia.

[22]  Xiaoyu Li,et al.  Natural Language Processing for EHR-Based Computational Phenotyping , 2018, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[23]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[24]  N C Andreasen,et al.  A comparative study of manic vs schizophrenic speech disorganization. , 1986, Archives of general psychiatry.

[25]  Bradley S Peterson,et al.  Semantic mapping reveals distinct patterns in descriptions of social relations in adults with autism spectrum disorder , 2016, Autism research : official journal of the International Society for Autism Research.

[26]  P. McGuire,et al.  Disorganization/cognitive and negative symptom dimensions in the at-risk mental state predict subsequent transition to psychosis. , 2012, Schizophrenia bulletin.

[27]  D. Malaspina,et al.  Symptom trajectories and psychosis onset in a clinical high-risk cohort: The relevance of subthreshold thought disorder , 2014, Schizophrenia Research.

[28]  Susan J. Hespos,et al.  Automated analysis of written narratives reveals abnormalities in referential cohesion in youth at ultra high risk for psychosis , 2017, Schizophrenia Research.

[29]  M. Copelli,et al.  Thought disorder measured as random speech structure classifies negative symptoms and schizophrenia diagnosis 6 months in advance , 2017, npj Schizophrenia.

[30]  Justin T Baker.  Toward Expert Systems in Mental Health Assessment: A Computational Approach to the Face and Voice in Dyadic Patient-Doctor Interactions , 2016 .

[31]  E. Cibelli,et al.  Clinical correlates of aberrant conversational turn-taking in youth at clinical high-risk for psychosis , 2019, Schizophrenia Research.

[32]  T. McCoy,et al.  Improving Prediction of Suicide and Accidental Death After Discharge From General Hospitals With Natural Language Processing. , 2016, JAMA psychiatry.

[33]  C. Rovelli,et al.  Relational Quantum Mechanics , 2006 .

[34]  Gina R. Kuperberg,et al.  Priming production: Neural evidence for enhanced automatic semantic activity preceding language production in schizophrenia , 2017, NeuroImage: Clinical.

[35]  Ryan L. Boyd,et al.  The Development and Psychometric Properties of LIWC2015 , 2015 .

[36]  Harriet de Wit,et al.  A Window into the Intoxicated Mind? Speech as an Index of Psychoactive Drug Effects , 2014, Neuropsychopharmacology.

[37]  Larry Davidson,et al.  The subjective experience of youths at clinically high risk of psychosis: a qualitative study. , 2014, Psychiatric services.

[38]  Guillermo A. Cecchi,et al.  Using Automated Metaphor Identification to Aid in Detection and Prediction of First-Episode Schizophrenia , 2017, EMNLP.

[39]  Linguistic determinants of formal thought disorder in first episode psychosis , 2020, Early intervention in psychiatry.

[40]  Carla Agurto,et al.  Predictive Linguistic Markers of Suicidality in Poets , 2018, 2018 IEEE 12th International Conference on Semantic Computing (ICSC).

[41]  N C Andreasen,et al.  Thought, language, and communication in schizophrenia: diagnosis and prognosis. , 1986, Schizophrenia bulletin.

[42]  R. Norel,et al.  Detection of acute 3,4-methylenedioxymethamphetamine (MDMA) effects across protocols using automated natural language processing , 2020, Neuropsychopharmacology.

[43]  Cora Diamond,et al.  Wittgenstein's Lectures on the Foundations of Mathematics. , 1977 .

[44]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[45]  C. Correll,et al.  Psychosis Prevention: A Modified Clinical High Risk Perspective From the Recognition and Prevention (RAP) Program. , 2015, The American journal of psychiatry.

[46]  Michelle P. Salyers,et al.  Language and hope in schizophrenia-spectrum disorders , 2016, Psychiatry Research.

[47]  Elmar Nöth,et al.  How language flows when movements don’t: An automated analysis of spontaneous discourse in Parkinson’s disease , 2016, Brain and Language.

[48]  Tianxi Cai,et al.  Genome-wide Association Study of Dimensional Psychopathology Using Electronic Health Records , 2018, Biological Psychiatry.

[49]  M. Covington,et al.  Schizophrenia and the structure of language: The linguist's view , 2005, Schizophrenia Research.

[50]  O. Kinouchi,et al.  Speech Graphs Provide a Quantitative Measure of Thought Disorder in Psychosis , 2012, PloS one.

[51]  David J. Anderson,et al.  Computational Neuroethology: A Call to Action , 2019, Neuron.

[52]  P. Foltz,et al.  A computational language approach to modeling prose recall in schizophrenia , 2014, Cortex.

[53]  Hoffman Re,et al.  Neural network simulations, cortical connectivity, and schizophrenic psychosis. , 1997 .

[54]  J. Willits,et al.  Measuring disorganized speech in schizophrenia: automated analysis explains variance in cognitive deficits beyond clinician-rated scales , 2018, Psychological Medicine.

[55]  Peter W. Foltz,et al.  Latent semantic variables are associated with formal thought disorder and adaptive behavior in older inpatients with schizophrenia , 2014, Cortex.

[56]  M. Sigman,et al.  Automated analysis of free speech predicts psychosis onset in high-risk youths , 2015, npj Schizophrenia.

[57]  P. Gordon,et al.  What’s the story? A computational analysis of narrative competence in autism , 2018, Autism : the international journal of research and practice.

[58]  Tyrone D. Cannon,et al.  Thought disorder and communication deviance as predictors of outcome in youth at clinical high risk for psychosis. , 2011, Journal of the American Academy of Child and Adolescent Psychiatry.

[59]  G. Cecchi,et al.  S19. ANALYZING NEGATIVE SYMPTOMS AND LANGUAGE IN YOUTHS AT RISK FOR PSYCHOSIS USING AUTOMATED LANGUAGE ANALYSIS , 2019, Schizophrenia Bulletin.

[60]  R. Miikkulainen,et al.  Using Computational Patients to Evaluate Illness Mechanisms in Schizophrenia , 2011, Biological Psychiatry.

[61]  S. Cleary,et al.  Computational linguistic analysis applied to a semantic fluency task to measure derailment and tangentiality in schizophrenia , 2018, Psychiatry Research.

[62]  Brita Elvevåg,et al.  What do we really know about blunted vocal affect and alogia? A meta-analysis of objective assessments , 2014, Schizophrenia Research.

[63]  Peter W. Foltz,et al.  An introduction to latent semantic analysis , 1998 .

[64]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[65]  Hok Pan Yuen,et al.  Long-term follow-up of a group at ultra high risk ("prodromal") for psychosis: the PACE 400 study. , 2013, JAMA psychiatry.

[66]  Domenic V. Cicchetti,et al.  Apprehending schizophrenic discourse: A structural analysis of the Listener's task , 1982, Brain and Language.

[67]  Tyrone D. Cannon,et al.  North American Prodrome Longitudinal Study (NAPLS 2): The Prodromal Symptoms , 2015, The Journal of nervous and mental disease.

[68]  Alex B. Fine,et al.  Natural Language Processing of Social Media as Screening for Suicide Risk , 2018, Biomedical informatics insights.

[69]  Mariano Sigman,et al.  Global organization of the Wordnet lexicon , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[70]  Zhen-Hua Ling,et al.  Enhanced LSTM for Natural Language Inference , 2016, ACL.

[71]  M. Sigman,et al.  The maturation of speech structure in psychosis is resistant to formal education , 2018, npj Schizophrenia.

[72]  P. Gordon,et al.  Quantifying Narrative Ability in Autism Spectrum Disorder: A Computational Linguistic Analysis of Narrative Coherence , 2014, Journal of Autism and Developmental Disorders.

[73]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[74]  R. Hoffman,et al.  Message disruptions during syntactic processing in schizophrenia. , 1985, Journal of communication disorders.

[75]  D. Poeppel,et al.  Coupled neural systems underlie the production and comprehension of naturalistic narrative speech , 2014, Proceedings of the National Academy of Sciences.

[76]  L. DeLisi,et al.  An automated method to analyze language use in patients with schizophrenia and their first-degree relatives , 2010, Journal of Neurolinguistics.