Automatic speaker diarization for natural conversation analysis in autism clinical trials.

Challenges in social communication is one of the core symptom domains in autism spectrum disorder (ASD). Novel therapies are under development to help individuals with these challenges, however the ability to show a benefit is dependent on a sensitive and reliable measure of treatment effect. Currently, measuring these deficits requires the use of time-consuming and subjective techniques. Objective measures extracted from natural conversations could be more ecologically relevant, and administered more frequently-perhaps giving them added sensitivity to change. While several studies have used automated analysis methods to study autistic speech, they require manual transcriptions. In order to bypass this time-consuming process, an automated speaker diarization algorithm must first be applied. In this paper, we are testing whether a speaker diarization algorithm can be applied to natural conversations between autistic individuals and their conversational partner in a natural setting at home over the course of a clinical trial. We calculated the average duration that a participant would speak for within their turn. We found a significant correlation between this feature and the Vineland Adaptive Behaviour Scales (VABS) expressive communication score (r = 0.51, p = 7 × 10-5). Our results show that natural conversations can be used to obtain measures of talkativeness, and that this measure can be derived automatically, thus showing the promise of objectively evaluating communication challenges in ASD.

The Montefiore-Einstein Rigidity Scale-Revised (MERS-R): Development, administration, reliability, and validity in child and adult Autism Spectrum Disorder (ASD).

BACKGROUND: Rigidity contributes to severity and functional impairment in autism spectrum disorder (ASD). There is an unmet need for a valid, reliable, and sensitive outcome measure to assess rigidity in ASD. OBJECTIVE: To develop and validate the Montefiore-Einstein Rigidity Scale-Revised (MERS-R) to assess the Behavioral Rigidity Domain (BRD), Cognitive Rigidity Domain (CRD), and Protest Domain (PD). MATERIALS AND METHODS: The MERS-R was administered to 93 individuals with ASD (children and adults, high and low IQ) at baseline, Week 2, and Week 12. Internal consistency was assessed for domain scores, Total Rigidity Composite (TRC = BRD + CRD), and Total Composite (TC = BRD + CRD + PD) with Cronbach's α. Intraclass correlation coefficients (ICCs) assessed test-retest reliability from baseline to weeks 2 and 12. Pearson's correlations assessed the relationship between the MERS-R and age, sex, and IQ. Convergent validity assessed the correlation of MERS-R scores to the Children's Yale-Brown Obsessive-Compulsive Scale-ASD (CY-BOCS-ASD). RESULTS: Good internal consistency was demonstrated for the BRD, PD, TRC and TC (Cronbach's α = 0.83, 0.88, 0.82, and 0.89, respectively) and adequate internal consistency for the CRD (α = .72). Good or excellent test-test reliability was demonstrated over two weeks (ICC: 0.66─.79), and fair or good reliability over 12 weeks (ICC: 0.56-66). MERS-R scores did not differ by age, sex, or IQ (p: 0.16─.99) with the exception that higher PD scores were associated with younger age (correlation = -0.25, p = 0.01). Significant convergent validity was demonstrated between all MERS-R scores and the CY-BOCS-ASD (p < 0.0001). DISCUSSION: The MERS-R demonstrated internal consistency, test-retest reliability, convergent validity and applicability to autistic children and adults of different sexes and IQ levels. It is a valid, sensitive, and reliable instrument to measure behavioral and cognitive rigidity in ASD.