Quantifying abnormal emotion processing: A novel computational assessment method and application in schizophrenia.

Abnormal emotion processing is a core feature of schizophrenia spectrum disorders (SSDs) that encompasses multiple operations. While deficits in some areas have been well-characterized, we understand less about abnormalities in the emotion processing that happens through language, which is highly relevant for social life. Here, we introduce a novel method using deep learning to estimate emotion processing rapidly from spoken language, testing this approach in male-identified patients with SSDs (n = 37) and healthy controls (n = 51). Using free responses to evocative stimuli, we derived a measure of appropriateness, or "emotional alignment" (EA). We examined psychometric characteristics of EA and its sensitivity to a single-dose challenge of oxytocin, a neuropeptide shown to enhance the salience of socioemotional information in SSDs. Patients showed impaired EA relative to controls, and impairment correlated with poorer social cognitive skill and more severe motivation and pleasure deficits. Adding EA to a logistic regression model with language-based measures of formal thought disorder (FTD) improved classification of patients versus controls. Lastly, oxytocin administration improved EA but not FTD among patients. While additional validation work is needed, these initial results suggest that an automated assay using spoken language may be a promising approach to assess emotion processing in SSDs.

Fully automated detection of formal thought disorder with Time-series Augmented Representations for Detection of Incoherent Speech (TARDIS).

Formal thought disorder (ThD) is a clinical sign of schizophrenia amongst other serious mental health conditions. ThD can be recognized by observing incoherent speech - speech in which it is difficult to perceive connections between successive utterances and lacks a clear global theme. Automated assessment of the coherence of speech in patients with schizophrenia has been an active area of research for over a decade, in an effort to develop an objective and reliable instrument through which to quantify ThD. However, this work has largely been conducted in controlled settings using structured interviews and depended upon manual transcription services to render audio recordings amenable to computational analysis. In this paper, we present an evaluation of such automated methods in the context of a fully automated system using Automated Speech Recognition (ASR) in place of a manual transcription service, with "audio diaries" collected in naturalistic settings from participants experiencing Auditory Verbal Hallucinations (AVH). We show that performance lost due to ASR errors can often be restored through the application of Time-Series Augmented Representations for Detection of Incoherent Speech (TARDIS), a novel approach that involves treating the sequence of coherence scores from a transcript as a time-series, providing features for machine learning. With ASR, TARDIS improves average AUC across coherence metrics for detection of severe ThD by 0.09; average correlation with human-labeled derailment scores by 0.10; and average correlation between coherence estimates from manual and ASR-derived transcripts by 0.29. In addition, TARDIS improves the agreement between coherence estimates from manual transcripts and human judgment and correlation with self-reported estimates of AVH symptom severity. As such, TARDIS eliminates a fundamental barrier to the deployment of automated methods to detect linguistic indicators of ThD to monitor and improve clinical care in serious mental illness.

The Centroid Cannot Hold: Comparing Sequential and Global Estimates of Coherence as Indicators of Formal Thought Disorder.

Thought disorder (TD) as reflected in incoherent speech is a cardinal symptom of schizophrenia and related disorders. Quantification of the degree ofTD can inform diagnosis, monitoring, and timely intervention. Consequently, there has been an interest in applying methods ofdistributional semantics to quantify incoherence ofspoken language. Prior studies have generally involved few participants and utilized speech data collected in on-site structured interviews. In this paper we conduct a comprehensive evaluation ofapproaches to quantify incoherence using distributional semantics, including a novel variant that measures the global coherence oftext. This evaluation is conducted in the context of "audio diaries" collected from participants experiencing auditory verbal hallucinations using a smartphone application. Results reveal our novel global coherence metric using the centroid (weighted vector average) outperforms established approaches in their agreement with human annotators, supporting their preferential use in the context of short recordings ofunstructured and largely spontaneous speech.

aer2vec: Distributed Representations of Adverse Event Reporting System Data as a Means to Identify Drug/Side-Effect Associations.

Adverse event report (AER) data are a key source of signal for post marketing drug surveillance. The standard methodology to analyze AER data applies disproportionality metrics, which estimate the strength of drug/side-effect associations from discrete counts of their occurrence at report level. However, in other domains, improvements in predictive modeling accuracy have been obtained through representation learning, where discrete features are replaced by distributed representations learned from unlabeled data. This paper describes aer2vec, a novel representational approach for AER data in which concept embeddings emerge from neural networks trained to predict drug/side-effect co-occurrence. Trained models are evaluated for their utility in identifying drug/side-effect relationships, with improvements over disproportionality metrics in most cases. In addition, we evaluate the utility of an otherwise-untapped resource in the Food and Drug Administration (FDA) AER system - reporter designations of suspected causality - and find that incorporating this information enhances performance of all models evaluated.