Latest publications

New study on basic self-disturbance and spontaneous speech published in Biological Psychiatry: Cognitive Neuroscience and Neuroimaging.

Background: Basic self disturbance, or anomalous self experiences (ASEs), is a core feature of the schizophrenia spectrum. We propose a novel method of natural language processing (NLP) to quantify ASE’s in spoken language by direct comparison to an inventory of self-disturbance, the Inventory of Psychotic-Like Anomalous Self-Experiences (IPASE). We hypothesized increased similarity in open-ended speech to the IPASE items in early course psychosis (PSY) compared to healthy individuals, with clinical high risk (CHR) intermediate in similarity.

Methods: Open-ended interviews were obtained in 170 healthy controls, 167 CHR participants, and 89 PSY participants. We calculated the semantic similarity between IPASE items and ‘I’ sentences from transcribed speech samples using Sentence Bidirectional Encoder Representation from Text (S-BERT). Kolmogorov-Smirnov tests were used to compare distributions across groups. A non-negative matrix factorization (NNMF) of cosine similarity was performed to rank IPASE items.

Results: Spoken language of CHR individuals had the greatest semantic similarity to IPASE items as compared to both controls (s=0.44, p < 10-14) and PSY (s= 0.36, p < 10-6) individuals, while IPASE scores were higher among PSY than CHR. Additionally, the NNMF approach produced a ‘data-driven domain’ that differentiated the CHR group from others.

Conclusions: We found that open-ended interview elicits language with increased semantic similarity to the IPASE by CHR compared to psychosis patients. This demonstrates the utility of these methods to differentiate patients from healthy controls. This complementary approach has the capacity to scale to large studies investigating phenomenological features of schizophrenia and potentially other clinical populations.