Objective Assessment of Social Skills Using Automated Language Analysis
  for Identification of Schizophrenia and Bipolar Disorder

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Several studies have shown that speech and language features, automatically extracted from clinical interviews or spontaneous discourse, have diagnostic value for mental disorders such as schizophrenia and bipolar disorder. They typically make use of a large feature set to train a classifier for distinguishing between two groups of interest, i.e. a clinical and control group. However, a purely data-driven approach runs the risk of overfitting to a particular data set, especially when sample sizes are limited. Here, we first down-select the set of language features to a small subset that is related to a well-validated test of functional ability, the Social Skills Performance Assessment (SSPA). This helps establish the concurrent validity of the selected features. We use only these features to train a simple classifier to distinguish between groups of interest. Linear regression reveals that a subset of language features can effectively model the SSPA, with a correlation coefficient of 0.75. Furthermore, the same feature set can be used to build a strong binary classifier to distinguish between healthy controls and a clinical group (AUC = 0.96) and also between patients within the clinical group with schizophrenia and bipolar I disorder (AUC = 0.83).

Related collections

Most cited references 7

Record: found
Abstract: found
Article: not found

Prediction of real-world functional disability in chronic mental disorders: a comparison of schizophrenia and bipolar disorder.

Jason J. Luke, Ann Pulver, Brent Mausbach … (2010)

Schizophrenia and bipolar disorder are associated with multidimensional disability. This study examined differential predictors of functional deficits in the two disorders. Community-dwelling individuals with schizophrenia (N=161) or bipolar disorder (N=130) were assessed with neuropsychological tests, symptom measures, and performance-based social and adaptive (i.e., everyday living skills) functional competence measures as well as three domains of real-world functioning: community and household activities; work skills; and interpersonal relationships. The authors used confirmatory path analysis to find the best-fitting models to examine the direct and indirect (as mediated by competence) prediction of the three domains of real-world functioning. In all models for both groups, neurocognition's relationship with outcomes was largely mediated by competence. Symptoms were negatively associated with outcomes but unassociated with competence, with the exception of depression, which was a direct and mediated (through social competence) predictor in bipolar disorder. In both groups, neurocognition was related to activities directly and through a mediated relationship with adaptive competence. Work skills were directly and indirectly (through mediation with social competence) predicted by neurocognition in schizophrenia and entirely mediated by adaptive and social competence in bipolar disorder. Neurocognition was associated with interpersonal relationships directly in the schizophrenia group and mediated by social competence in both groups. Although there was greater disability in schizophrenia, neurocognition predicted worse functioning in all outcome domains in both disorders. These results support the shared role of neurocognition in bipolar disorder and schizophrenia in producing disability, with predictive differences between disorders in domain-specific effects of symptoms and social and adaptive competence.

0 comments Cited 78 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Social skills performance assessment among older patients with schizophrenia.

Thomas L Patterson, Sherry Moscona, Christine L McKibbin … (2001)

Social functioning is an important outcome dimension in schizophrenia. Measures of social skills frequently rely on self-report, and most measures which directly assess social functioning are time consuming. Here we describe a brief performance-based measure, the Social Skills Performance Assessment (SSPA), modified from an instrument published by Bellack et al. (Bellack, A., Morrison, R., Wixted, J., Mueser, K., 1990. An analysis of social competence in schizophrenia. Br. J. Psychiatry 156, 809--818). 83 middle-aged and elderly patients with schizophrenia or schizoaffective disorder, and 52 normal comparison subjects (NCs) were rated on two standardized role plays, one requiring introduction to a stranger and another requiring assertive behavior with their landlord. Ratings in eight areas ranging from 'social appropriateness' to 'grooming' were made. SSPA required about 12 min to complete both role play and ratings, and had excellent interrater reliability, and good test-retest reliability. Patients demonstrated significantly greater disability in all areas of social functioning compared with NCs. Social performance was related to severity of negative symptoms and cognitive deficits, but not that of positive or depressive symptoms. SSPA scores were significantly correlated with health-related quality of well-being and observed performance on activities of daily living, but not to a self-reported measure of social functioning. The SSPA is a reliable and useful instrument. Direct assessment of social skills may provide a more accurate picture of functioning than self-report measures among patients who frequently lack insight into their own behavior.