Using Automated Metaphor Identification to Aid in Detection and Prediction of First-Episode Schizophrenia

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2923–2930 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Using Automated Metaphor Identification to Aid in Detection and Prediction of First-Episode Schizophrenia E. Dar´ıo Guti´errez1 Philip R. Corlett2 Cheryl M. Corcoran3 Guillermo A. Cecchi1 1 IBM Research 2 Yale University 3 New York State Psychiatric Institute at Columbia University edg@icsi.berkeley.edu philip.corlett@yale.edu cheryl.corcoran@nyspi.columbia.edu guillermo.cecchi@ibm.com Abstract The diagnosis of serious mental health conditions such as schizophrenia is based on the judgment of clinicians whose train- ing takes many years and cannot be easily formalized into objective measures. How- ever, clinical research suggests there are disturbances in aspects of the language use of patients with schizophrenia, which opens a door for the use of NLP tools in schizophrenia diagnosis and progno- sis. Using metaphor-identification and sentiment-analysis algorithms to automat- ically generate features, we create a clas- sifier that, with high accuracy, can predict which patients will develop (or currently suffer from) schizophrenia. To our knowl- edge, this study is the first to demonstrate the utility of automated metaphor identifi- cation algorithms for detection or predic- tion of disease. 1 Introduction Schizophrenia is a severe mental disorder that has a devastating impact on those who suffer from it, as well as on their families and communities. Schizophrenia is characterized by psychotic be- haviors (hallucinations, delusions, thought disor- ders, movement disorders), flat affect and anhedo- nia, and trouble with focusing and executive func- tioning, among other symptoms (American Psy- chiatric Association, 2013). It afflicts over 21 mil- lion people worldwide, and is associated with a 100-150 percent increase in early mortality (Goff et al., 2005; World Health Organization, 2016; Simeone et al., 2015). As a result, diagnosis and treatment of schizophrenia has important public health consequences. Unfortunately, practition- ers who are qualified to diagnose and treat seri- ous mental health issues such as schizophrenia are in chronically short supply, and their accumulated knowledge cannot be easily formalized into repro- ducible metrics (Patel et al., 2007). However, clinical research into the symptoms and mechanisms of schizophrenia suggests that disturbances in language use, and especially in metaphor use and affect, characterize schizophre- nia. This suggests that automated NLP meth- ods may have the potential to help in diagnosis and prognosis of schizophrenia. In this paper, we work from open-ended transcripts of patients in- terviewed by non-specialists. We then apply NLP algorithms for metaphor identification and senti- ment analysis to automatically generate features for a classifier that, with high accuracy, can pre- dict which patients will develop schizophrenia and which patients would currently be diagnosed with schizophrenia by psychiatrists. 2 Background & Related work 2.1 NLP and Computational Psychiatry Several recent studies have proven that NLP text- analysis techniques can be successfully applied to predict mental illness. Vincze et al. (2016) use linguistic and demographic features to pre- dict whether a speech transcript was produced by an individual with mild cognitive impairment or by a healthy control. To our knowledge, Elvev˚ag et al. …

Content truncated to 500 words