Multimodal assessment of communicative-pragmatic features in schizophrenia: a machine learning approach.

An impairment in pragmatic communication is a core feature of schizophrenia, often associated with difficulties in social interactions. The pragmatic deficits regard various pragmatic phenomena, e.g., direct and indirect communicative acts, deceit, irony, and include not only the use of language but also other expressive means such as non-verbal/extralinguistic modalities, e.g., gestures and body movements, and paralinguistic cues, e.g., prosody and tone of voice. The present paper focuses on the identification of those pragmatic features, i.e., communicative phenomena and expressive modalities, that more reliably discriminate between individuals with schizophrenia and healthy controls. We performed a multimodal assessment of communicative-pragmatic ability, and applied a machine learning approach, specifically a Decision Tree model, with the aim of identifying the pragmatic features that best separate the data into the two groups, i.e., individuals with schizophrenia and healthy controls, and represent their configuration. The results indicated good overall performance of the Decision Tree model, with mean Accuracy of 82%, Sensitivity of 76%, and Precision of 91%. Linguistic irony emerged as the most relevant pragmatic phenomenon in distinguishing between the two groups, followed by violation of the Gricean maxims, and then extralinguistic deceitful and sincere communicative acts. The results are discussed in light of the pragmatic theoretical literature, and their clinical relevance in terms of content and design of both assessment and rehabilitative training.

Pragmatics, Theory of Mind and executive functions in schizophrenia: Disentangling the puzzle using machine learning.

OBJECTIVE: Schizophrenia is associated with a severe impairment in the communicative-pragmatic domain. Recent research has tried to disentangle the relationship between communicative impairment and other domains usually impaired in schizophrenia, i.e. Theory of Mind (ToM) and cognitive functions. However, the results are inconclusive and this relationship is still unclear. Machine learning (ML) provides novel opportunities for studying complex relationships among phenomena and representing causality among multiple variables. The present research explored the potential of applying ML, specifically Bayesian network (BNs) analysis, to characterize the relationship between cognitive, ToM and pragmatic abilities in individuals with schizophrenia and healthy controls, and to identify the cognitive and pragmatic abilities that are most informative in discriminating between schizophrenia and controls. METHODS: We provided a comprehensive assessment of different aspects of pragmatic performance, i.e. linguistic, extralinguistic, paralinguistic, contextual and conversational, ToM and cognitive functions, i.e. Executive Functions (EF)-selective attention, planning, inhibition, cognitive flexibility, working memory and speed processing-and general intelligence, in a sample of 32 individuals with schizophrenia and 35 controls. RESULTS: The results showed that the BNs classifier discriminated well between patients with schizophrenia and healthy controls. The network structure revealed that only pragmatic Linguistic ability directly influenced the classification of patients and controls, while diagnosis determined performance on ToM, Extralinguistic, Paralinguistic, Selective Attention, Planning, Inhibition and Cognitive Flexibility tasks. The model identified pragmatic, ToM and cognitive abilities as three distinct domains independent of one another. CONCLUSION: Taken together, our results confirmed the importance of considering pragmatic linguistic impairment as a core dysfunction in schizophrenia, and demonstrated the potential of applying BNs in investigating the relationship between pragmatic ability and cognition.

The Ability of Patients With Schizophrenia to Comprehend and Produce Sincere, Deceitful, and Ironic Communicative Intentions: The Role of Theory of Mind and Executive Functions.

Patients with schizophrenia are often described as impaired in several cognitive domains. Specifically, patients with schizophrenia often exhibit problems in solving tasks requiring theory of mind (ToM), i.e., the ability to ascribe mental states to oneself and others, communicative-pragmatic ability, i.e., the ability to use language and non-verbal expressive means to convey meaning in a given context, and executive functions (EF). This study aims to investigate the role of cognitive functions, such as general intelligence, selective attention, processing speed, and especially EF (working memory, cognitive flexibility, inhibition, and planning), and ToM in explaining the performance of individual with schizophrenia in comprehending and producing communicative acts expressed with different communicative intentions (i.e., sincere, deceitful, and ironic), and realized through linguistic and extralinguistic/non-verbal expressive means. Thirty-two patients with schizophrenia and an equal number of healthy controls performed tasks aiming to investigate their capacity to comprehend and produce sincere, deceitful, and ironic communicative acts in addition to a series of cognitive tasks evaluating EF and ToM. The results indicated that individuals with schizophrenia performed worse than the controls in the comprehension and production of all pragmatic phenomena investigated, as well as in all the cognitive functions examined. The patients with schizophrenia also exhibited an increasing trend of difficulty in comprehending and producing sincere, deceitful, and ironic communicative acts expressed through either linguistic or extralinguistic means. Furthermore, a multiple regression analysis of the patients' performance on the pragmatic tasks revealed that overall, the role of attention, general intelligence, and processing speed did not appear to significantly explain the patients' communicative-pragmatic performance. The inclusion of EF into the analysis did not contribute to increase the explained variance of the patients' ability to comprehend and produce the various pragmatic phenomena investigated. Only the addition of ToM could significantly increase the explained variance, but only in the comprehension and production of deceit expressed by language and the production of sincere communicative acts, also limited to linguistic production. We conclude that neither EF nor ToM are able to explain the decreasing trend detected in the patients' pragmatic performance.

Cognitive abilities and theory of mind in explaining communicative-pragmatic disorders in patients with schizophrenia.

Patients with schizophrenia usually show an impairment in their communicative-pragmatic performance; they also have difficulties in cognitive functioning and Theory of Mind (ToM). In the literature it has been proposed that ToM and cognitive deficits have a role in explaining the communicative-pragmatic difficulties of patients with schizophrenia. However, the exact interplay of these functions is still not completely clear. The present research investigates the relationship between communicative-pragmatic, ToM and cognitive impairments (i.e. general intelligence, selective attention, speed processing and EF -working memory, inhibition and flexibility-) in a sample of 26 individuals with schizophrenia and matched controls. The linguistic and extralinguistic scales of the Assessment Battery of Communication (ABaCo), and a series of ToM and cognitive tasks were administered to patients and healthy controls. The results showed that individuals with schizophrenia performed less well than controls in all the tasks investigated. However, a hierarchical regression analysis showed that only ToM, and not cognitive functions, seems to be a predictive variable of patients' performance. Finally, a Fisher's exact test showed that there was not a stable significant relationship between ToM or EF and pragmatic impairment.