Quantifying tics: Best practices and design considerations for video-based tic coding in research.

Tic disorders (TD), including Tourette Syndrome, are characterized by involuntary, repetitive movements and/or vocalizations that can lead to persistent disability and impairment across the lifespan. Existing research demonstrates that video-based behavioral coding (VBBC) methods can be used to reliably quantify tics, enabling a more objective approach to tic measurement above and beyond standardly used TD questionnaires. VBBC is becoming more popular given the ease and ubiquity of obtaining patient videos. However, rigor and reproducibility of this work has been limited by undescribed and unstandardized approaches to using VBBC methods in TD research. The current paper describes "best practices" for VBBC in TD research, which have been tested and refined in our research over the past 15+ years, including considerations for data acquisition, coding implementation, interrater reliability demonstration, and methods reporting. We also address ethical considerations for researchers using this method.

Treating Tourette Together: An Agenda for Patient-Centered Research Focused on Comprehensive Behavioral Intervention for Tics.

To establish a patient-centered agenda for research that will lead to effective, widespread availability, adoption, and utilization of evidence-based behavioral treatment of Tourette syndrome and other tic disorders (TDs), we planned and executed a multistage, collaborative "Treating Tourette Together" research planning project with researchers, clinicians, patients, families, and other interested parties. Priorities for future behavioral treatment research were solicited from these parties via anonymous community surveys, a 2-day research planning summit with 46 individuals representing key stakeholder groups, and community response to summit reports. Four high-priority research domains were identified: (a) expanding treatment access, (b) improving treatment outcomes, (c) optimizing treatment within a broader care model, and (d) evaluating outcomes beyond tic severity. Community-engaged participatory research models can efficiently delineate clear and actionable priorities for clinical research. This approach holds promise for improving the impact of clinical research in TDs and other neuropsychiatric disorders.

Long-term follow-up of acceptance-enhanced behavior therapy for trichotillomania.

Acceptance-enhanced behavior therapy for trichotillomania (AEBT-TTM) is effective in reducing trichotillomania (TTM) symptoms, but the durability of treatment effects remains in question. This study analyzed 6-month follow-up data from a large randomized clinical trial comparing AEBT-TTM to an active psychoeducation and supportive therapy control (PST). Adults with TTM (N=85; 92% women) received 10 sessions of AEBT-TTM or PST across 12 weeks. Independent evaluators assessed participants at baseline, post-treatment, and 6 months follow-up. For both AEBT-TTM and PST, self-reported and evaluator-rated TTM symptom severity decreased from baseline to follow-up. TTM symptoms did not worsen from post-treatment to follow-up. At follow-up, AEBT-TTM and PST did not differ in rates of treatment response, TTM diagnosis, or symptom severity. High baseline TTM symptom severity was a stronger predictor of high follow-up severity for PST than for AEBT-TTM, suggesting AEBT-TTM may be a better option for more severe TTM. Results support the efficacy of AEBT-TTM and show that treatment gains were maintained over time. Although AEBT-TTM yielded lower symptoms at post-treatment, 6-month follow-up outcomes suggest AEBT-TTM and PST may lead to similar symptom levels in the longer term. Future research should examine mechanisms that contribute to long-term gain maintenance.

Automated Quantification of Eye Tics Using Computer Vision and Deep Learning Techniques.

BACKGROUND: Tourette syndrome (TS) tics are typically quantified using "paper and pencil" rating scales that are susceptible to factors that adversely impact validity. Video-based methods to more objectively quantify tics have been developed but are challenged by reliance on human raters and procedures that are resource intensive. Computer vision approaches that automate detection of atypical movements may be useful to apply to tic quantification. OBJECTIVE: The current proof-of-concept study applied a computer vision approach to train a supervised deep learning algorithm to detect eye tics in video, the most common tic type in patients with TS. METHODS: Videos (N = 54) of 11 adolescent patients with TS were rigorously coded by trained human raters to identify 1.5-second clips depicting "eye tic events" (N = 1775) and "non-tic events" (N = 3680). Clips were encoded into three-dimensional facial landmarks. Supervised deep learning was applied to processed data using random split and disjoint split regimens to simulate model validity under different conditions. RESULTS: Area under receiver operating characteristic curve was 0.89 for the random split regimen, indicating high accuracy in the algorithm's ability to properly classify eye tic vs. non-eye tic movements. Area under receiver operating characteristic curve was 0.74 for the disjoint split regimen, suggesting that algorithm generalizability is more limited when trained on a small patient sample. CONCLUSIONS: The algorithm was successful in detecting eye tics in unseen validation sets. Automated tic detection from video is a promising approach for tic quantification that may have future utility in TS screening, diagnostics, and treatment outcome measurement. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Caregiver Perspectives on the Health Care System for Tic Disorders: Utilization and Barriers.

OBJECTIVE: This study aimed to understand health care experiences among a sample of caregivers of children with TDs to inform future directions for improving the health care system. METHODS: We conducted a survey of caregivers of youth with TDs and used descriptive statistics and quantitative analyses to characterize the health care utilization practices of the sample. RESULTS: The majority (70%) of families first consulted their pediatrician/primary care provider, and caregivers reported receiving care in line with current best practice guidelines. However, caregivers in the current sample perceived a lack of knowledgeability on the part of their first providers, which significantly predicted more providers seen and also reported difficulty finding specialty providers (63% of the sample reported difficulty finding a treatment provider who understood tics). CONCLUSION: Results suggest that improving caregiver satisfaction with early health care experiences for their child's TD may help to relieve the burden on families and the health care system more broadly, along with continued efforts to increase the number of specialty providers available.

Evaluating the feasibility, acceptability, and preliminary effectiveness of tele-comprehensive behavior therapy for tics (teleCBIT) for Tourette syndrome in youth and adults.

INTRODUCTION: Comprehensive behavioral intervention for tics (CBIT) is an efficacious, first-line treatment for Tourette syndrome (TS) and other chronic or persistent tic disorders. However, CBIT's public health impact has been limited by suboptimal treatment access. Preliminary research has shown that providing CBIT over videoconference (teleCBIT) is a promising delivery method for patients who cannot access in-person care. However, extant studies have been small efficacy trials focused only on pediatric patients. Replication of these studies is needed in additional treatment settings and across a wider age range of patients, especially in light of advances in telehealth technology and increasing telehealth adoption among practitioners. METHODS: We conducted a single-arm trial to evaluate the feasibility, acceptability, and effectiveness of teleCBIT embedded in comprehensive, medical tic specialty clinics. From October 2016 to September 2018, patients were offered teleCBIT at their usual care appointments. Those who were interested and met inclusion/exclusion criteria received 8 sessions of CBIT guided by a manualized protocol. An independent evaluator, masked to treatment progress, administered assessments at baseline, post-treatment, and 3 and 6 months after treatment. RESULTS: Twenty-five percent of patients who were offered treatment initiated teleCBIT through the study, and all treatment initiators completed treatment. From pre- to post-treatment, decreases in Yale Global Tic Severity Scale (YGTSS) total tic severity scores showed a large effect size among pediatric patients (n = 19; t = 5.72, P < 0.001, d = 1.31) and a medium-to-large effect size for adult patients (n = 10, t = 1.41, P = 0.096, d = 0.664). Thirteen of 19 pediatric patients (68%) and 6 of 10 adult patients (60%) had a positive global treatment response at post-treatment. Patients rated the treatment as highly satisfactory. Ninety-three percent of sessions were free of substantial technical problems. DISCUSSION: Within the context of medical tic specialty clinics, teleCBIT demonstrated strong evidence of feasibility, acceptability, and preliminary effectiveness comparable to in-person treatment for both pediatric and adult patients. TeleCBIT warrants study in future research on enhancing care systems for patients with TS. TRIAL REGISTRY: https://clinicaltrials.gov/ct2/keydates/NCT04007913.

The CBIT+TMS Trial: study protocol for a two-phase randomized controlled trial testing neuromodulation to augment behavior therapy for youth with chronic tics.

Background: Comprehensive Behavioral Intervention for Tics (CBIT) is a first-line treatment for tic disorders that aims to improve controllability over tics that an individual finds distressing or impairing. However, it is only effective for approximately half of patients. Supplementary motor area (SMA)-directed neurocircuitry plays a strong role in motor inhibition, and activity in this region is thought to contribute to tic expression. Targeted modulation of SMA using transcranial magnetic stimulation (TMS) may increase CBIT efficacy by improving patient ability to implement tic controllability behaviors. Methods: The CBIT+TMS trial is a two-phase, milestone driven early-stage randomized controlled trial. The trial will test whether augmenting CBIT with inhibitory, noninvasive stimulation of SMA with TMS modifies activity in SMA-mediated circuits and enhances tic controllability in youth ages 12-21 years with chronic tics. Phase 1 will directly compare two rTMS augmentation strategies (1Hz rTMS vs. cTBS) vs. sham in N = 60 participants. Quantifiable, a priori "Go/No Go Criteria" guide the decision to proceed to Phase 2 and selection of the optimal TMS regimen. Phase 2 will compare the optimal regimen vs. sham and test the link between neural target engagement and clinical outcomes in a new sample of N = 60 participants. Discussion: This clinical trial is one of few to date testing TMS augmentation of therapy in a pediatric sample. Results will provide insight into whether TMS is a potentially viable strategy for enhancing CBIT efficacy and reveal potential neural and behavioral mechanisms of change. Trial registration: ClinicalTrials.gov Identifier: NCT04578912.

A Mobile Application Adjunct to Augment Cognitive-Behavioral Group Therapy for Adolescents with Social Anxiety: Feasibility and Acceptability Results from the Wiring Adolescents with Social Anxiety via Behavioral Interventions Pilot Trial.

Objective: Cognitive-Behavioral Group Therapy (CBGT) is an established treatment for Social Anxiety (SA). However, diagnostic recovery rate is only 20.5% in CBGT, and up to 50% of patients remain symptomatic posttreatment. Using videocalls to deliver digital CBGT (dCBGT) is feasible, cost-effective, and efficacious. Yet, the impact of dCBGT on social functioning remains limited, as dCBGT does not offer opportunities for monitoring cognition and behavior in social situations. Wiring Adolescents with Social Anxiety via Behavioral Interventions (WASABI), a clinician-assisted application that uses ecological momentary assessments (EMAs), cognitive bias tests, and clinical self-reports, was investigated as an adjunct to dCBGT. Methods: A prospective, parallel arm, double-blind randomized controlled trial was employed in 24 SA adolescents randomly assigned to dCBGT versus dCBGT plus WASABI. Results: Study completion rates (83%) and exit survey data indicated that WASABI is feasible and acceptable. Engagement with EMAs varied from four to 244 EMAs completed per person. Cognitive bias tests and clinical self-reports were completed at least weekly by 53% and 69% of participants, respectively. While standard tests did not reveal statistically significant differences between dCBGT plus WASABI and dCBGT alone, effect sizes were greater for dCBGT plus WASABI on symptom severity, social skills, and functioning. Conclusions: Despite the small sample, preliminary results suggest that WASABI is feasible, acceptable, and may be an effective augmentation tool for treating SA in teenagers.

The CBIT + TMS trial: study protocol for a two-phase randomized controlled trial testing neuromodulation to augment behavior therapy for youth with chronic tics.

BACKGROUND: Comprehensive Behavioral Intervention for Tics (CBIT) is a first-line treatment for tic disorders that aims to improve controllability over tics that an individual finds distressing or impairing. However, it is only effective for approximately half of patients. Supplementary motor area (SMA)-directed neurocircuitry plays a strong role in motor inhibition, and activity in this region is thought to contribute to tic expression. Targeted modulation of SMA using transcranial magnetic stimulation (TMS) may increase CBIT efficacy by improving patients' ability to implement tic controllability behaviors. METHODS: The CBIT + TMS trial is a two-phase, milestone-driven early-stage randomized controlled trial. The trial will test whether augmenting CBIT with inhibitory, non-invasive stimulation of SMA with TMS modifies activity in SMA-mediated circuits and enhances tic controllability in youth ages 12-21 years with chronic tics. Phase 1 will directly compare two rTMS augmentation strategies (1 Hz rTMS vs. cTBS) vs. sham in N = 60 participants. Quantifiable, a priori "Go/No Go Criteria" guide the decision to proceed to phase 2 and the selection of the optimal TMS regimen. Phase 2 will compare the optimal regimen vs. sham and test the link between neural target engagement and clinical outcomes in a new sample of N = 60 participants. DISCUSSION: This clinical trial is one of few to date testing TMS augmentation of therapy in a pediatric sample. The results will provide insight into whether TMS is a potentially viable strategy for enhancing CBIT efficacy and reveal potential neural and behavioral mechanisms of change. TRIAL REGISTRATION: ClinicalTrials.gov NCT04578912 . Registered on October 8, 2020.

Optimizing Individual Targeting of Fronto-Amygdala Network with Transcranial Magnetic Stimulation (TMS): Biophysical, Physiological and Behavioral Variations in People with Methamphetamine Use Disorder.

Background: Previous studies in people with substance use disorders (SUDs) have implicated both the frontopolar cortex and amygdala in drug cue reactivity and craving, and amygdala-frontopolar coupling is considered a marker of early relapse risk. Accumulating data highlight that the frontopolar cortex can be considered a promising therapeutic target for transcranial magnetic stimulation (TMS) in SUDs. However, one-size-fits-all approaches to TMS targets resulted in substantial variation in both physiological and behavioral outcomes. Individualized TMS approaches to target cortico-subcortical circuits like amygdala-frontopolar have not yet been investigated in SUDs. Objective: Here, we (1) defined individualized TMS target location based on functional connectivity of the amygdala-frontopolar circuit while people were exposed to drug-related cues, (2) optimized coil orientation based on maximizing electric field (EF) perpendicular to the individualized target, and (3) harmonized EF strength in targeted brain regions across a population. Method: MRI data including structural, resting-state, and task-based fMRI data were collected from 60 participants with methamphetamine use disorders (MUDs). Craving scores based on a visual analog scale were collected immediately before and after the MRI session. We analyzed inter-subject variability in the location of TMS targets based on the maximum task-based connectivity between the left medial amygdala (with the highest functional activity among subcortical areas during drug cue exposure) and frontopolar cortex using psychophysiological interaction (PPI) analysis. Computational head models were generated for all participants and EF simulations were calculated for fixed vs. optimized coil location (Fp1/Fp2 vs. individualized maximal PPI location), orientation (AF7/AF8 vs. orientation optimization algorithm), and stimulation intensity (constant vs. adjusted intensity across the population). Results: Left medial amygdala with the highest (mean ± SD: 0.31±0.29) functional activity during drug cue exposure was selected as the subcortical seed region. Amygdala-to-whole brain PPI analysis showed a significant cluster in the prefrontal cortex (cluster size: 2462 voxels, cluster peak in MNI space: [25 39 35]) that confirms cortico-subcortical connections. The location of the voxel with the most positive amygdala-frontopolar PPI connectivity in each participant was considered as the individualized TMS target (mean ± SD of the MNI coordinates: [12.6 64.23 -0.8] ± [13.64 3.50 11.01]). Individual amygdala-frontopolar PPI connectivity in each participant showed a significant correlation with VAS scores after cue exposure (R=0.27, p=0.03). Averaged EF strength in a sphere with r = 5mm around the individualized target location was significantly higher in the optimized (mean ± SD: 0.99 ± 0.21) compared to the fixed approach (Fp1: 0.56 ± 0.22, Fp2: 0.78 ± 0.25) with large effect sizes (Fp1: p = 1.1e-13, Hedges'g = 1.5, Fp2: p = 1.7e-5, Hedges'g = 1.26). Adjustment factor to have identical 1 V/m EF strength in a 5mm sphere around the individualized targets ranged from 0.72 to 2.3 (mean ± SD: 1.07 ± 0.29). Conclusion: Our results show that optimizing coil orientation and stimulation intensity based on individualized TMS targets led to stronger electric fields in the targeted brain regions compared to a one-size-fits-all approach. These findings provide valuable insights for refining TMS therapy for SUDs by optimizing the modulation of cortico-subcortical circuits.

Response Inhibition in Youth Undergoing Intensive Treatment for Obsessive Compulsive Disorder.

Response Inhibition (RI) is the ability to suppress behaviors that are inappropriate for a given context. Obsessive-compulsive disorder (OCD) has been associated with impaired RI in adults as measured by the Stop Signal Task (SST). Conflicting results have been found in terms of the relationship between OCD severity and SST performance, and no studies to date have examined the relationship between SST and response to OCD treatment. Also relatively unknown is whether RI performance in OCD is associated with developmental or gender differences. This naturalistic study examined the relationship between SST performance, OCD severity, and OCD treatment response in a pediatric sample undergoing intensive treatment involving exposure and response prevention and medication management (n = 36). The SST and Children's Yale-Brown Obsessive Compulsive Scale (CYBOCS) were administered at admission and program discharge. OCD severity was not significantly related to stop signal reaction time (SSRT) in the whole sample and among subgroups divided by age and gender. Baseline SSRT and SSRT change did not predict CYBOCS change across treatment in the whole sample, but exploratory analyses indicated both were significant predictors among female adolescents. Results suggest there may be developmental gender differences in the relationship between RI and clinical improvement in pediatric OCD.

Integrating Causal Discovery and Clinically-Relevant Insights to Explore Directional Relationships between Autistic Features, Sex at Birth, and Cognitive Abilities.

Prevalence in autism spectrum disorder (ASD) diagnosis has long been strongly male-biased. Yet, consensus has not been reached on mechanisms and clinical features that underlie sex-based discrepancies. Whereas females may be under-diagnosed because of inconsistencies in diagnostic/ascertainment procedures (sex-biased criteria, social camouflaging), diagnosed males may have exhibited more overt behaviors (e.g., hyperactivity, aggression) that prompted clinical evaluation. Applying a novel network-theory-based approach, we extracted data-driven, clinically-relevant insights from a large, well-characterized sample (Simons Simplex Collection) of 2175 autistic males (Ages = 8.9±3.5 years) and 334 autistic females (Ages = 9.2±3.7 years). Exploratory factor analysis (EFA) and expert clinical review reduced data dimensionality to 15 factors of interest. To offset inherent confounds of an imbalanced sample, we identified a subset of males (N=331) matched to females on key variables (Age, IQ) and applied data-driven CDA using Greedy Fast Causal Inference (GFCI) for three groups (All Females, All Males, and Matched Males). Structural equation modeling (SEM) extracted measures of model fit and effect sizes for causal relationships between sex, age, and, IQ on EFA-selected factors capturing phenotypic representations of autism across sensory, social, and restricted and repetitive behavior domains. Our methodology unveiled sex-specific directional relationships to inform developmental outcomes and targeted interventions.

Differential extrinsic brain network connectivity and social cognitive task-specific demands in Autism Spectrum Disorder (ASD).

Few studies have used task-based functional connectivity (FC) magnetic resonance imaging to examine emotion-processing during the critical neurodevelopmental period of adolescence in Autism Spectrum Disorders (ASDs). Moreover, task designs with pervasive confounds (e.g., lack of appropriate controls) persist because they activate neural circuits of interest reliably. As an alternative approach to "subtracting" activity from putative control conditions, we propose examining FC across an entire task run. By pivoting our analysis and interpretation of existing paradigms, we may better understand neural response to non-focal instances of socially-relevant stimuli that approximate real-world experiences more closely. Hence, using two well-established affective tasks (face-viewing, face-matching) with diverging social-cognitive demands, we investigated extrinsic FC from amygdala (AMG) and fusiform gyrus (FG) seeds in typically-developing (TD; N = 17) and ASD (N = 17) male adolescents (10-18 yo) and clinical correlations (Social Communication Questionnaire; SCQ) of group FC differences. Participant data (4TD, 6ASD) with excessive head-motion were excluded from final analysis. Direct between-group comparisons revealed significant differences between groups for neural response but not task performance (accuracy, reaction time). During face-viewing, we found greater FC from AMG and FG seeds for ASD participants (ASD > TD) in regions involved in the Default Mode and Fronto-Parietal Task Control Networks. During face-matching, we found greater FC from AMG and FG seeds for TD participants (TD > ASD), in regions associated with the Salience, Dorsal Attention, and Somatosensory Networks. SCQ scores correlated positively with regions with group differences on the face-viewing task and negatively with regions identified for the face-matching task. Task-dependent group differences in FC despite comparable behavioral performance suggest that high-functioning ASD may wield compensatory strategies; clinically-correlated FC patterns may associate with differential task-demands, ecological validity, and context-dependent processing. Employing this novel approach may further the development of targeted therapeutic interventions informed by individual differences in the highly heterogeneous ASD population.

Rapid onset of functional tic-like behaviors among adolescent girls-Minnesota, September-November 2021.

Background: On October 15, 2021, the Minnesota Department of Health began investigating a school cluster of students experiencing tic-like behaviors thought to be related to recent COVID-19. The objective of this report is to describe the investigation, key findings, and public health recommendations. Methods: Affected students and proxies were interviewed with a standardized questionnaire including validated depression and anxiety screens. Results: Eight students had tic-like behaviors lasting >24 h after initial report with onset during September 26-October 30, 2021. All eight students were females aged 15-17 years. All students either had a history of depression or anxiety or scored as having more than minimal anxiety or depression on validated screens. Four students previously had confirmed COVID-19: the interval between prior COVID-19 and tic symptom onset varied from more than a year prior to tic symptom onset to at the time of tic symptom onset. Conclusion: The onset of tic-like behaviors at one school in Minnesota appeared to be related more to underlying mental health conditions than recent COVID-19. These findings highlight the need to better understand functional tic-like behaviors and adolescent mental health.

Distinguishing and Managing Acute-Onset Complex Tic-like Behaviors in Adolescence.

Consistent with international reports,1 this group of Tourette syndrome (TS) experts has noticed a recent increase in adolescents presenting with tic-like symptoms that show a markedly atypical onset and course. These sudden-onset motor movements and vocalizations are often associated with significant impairment and disability, resulting in emergency department visits and hospitalizations for some affected youths.

Considerations for Pairing Cognitive Behavioral Therapies and Non-invasive Brain Stimulation: Ignore at Your Own Risk.

Multimodal approaches combining cognitive behavioral therapies (CBT) with non-invasive brain stimulation (NIBS) hold promise for improving the treatment of neuropsychiatric disorders. As this is a relatively new approach, it is a critical time to identify guiding principles and methodological considerations to enhance research rigor. In the current paper, we argue for a principled approach to CBT and NIBS pairings based on synergistic activation of neural circuits and identify key considerations about CBT that may influence pairing with NIBS. Careful consideration of brain-state interactions and CBT-related nuances will increase the potential for these combinations to be positively synergistic.

Predictors and Prospective Course of PANS: A Pilot Study Using Electronic Platforms for Data Collection.

Objectives: Little is known about the longitudinal course of pediatric acute-onset neuropsychiatric syndrome (PANS) because existing literature is primarily cross-sectional. To begin to address this gap, two digital platforms were used to prospectively monitor neuropsychiatric symptoms in children with PANS. The aim was to identify baseline clinical characteristics that would predict the course of neuropsychiatric symptoms over 12 weeks. We compared relative compliance between two electronic data acquisition platforms and evaluated agreement between parent-child ratings of symptoms. Methods: For 12 weeks, 20 children with PANS and their parents completed weekly rating scales of neuropsychiatric symptoms on Research Electronic Data Capture (REDCap) and concurrently parents completed tri-weekly ratings on My Pediatric Autoimmune Neuropsychiatric Disorders Associated with Streptococcal Infections (PANDAS) Chart, a symptom monitoring website. Longitudinal data were analyzed by using regression analyses. Results: Greater duration of time between onset of PANS and study enrollment was associated with worsening of parent-rated neuropsychiatric symptoms over 12 weeks (p = 0.05). Higher scores on parents' Caregiver Burden Inventory at baseline predicted that children would report more severe symptoms over the 12-week period (p = 0.01). Compliance rates for parents were 86.3% for the weekly REDCap PANS Symptoms Rating Scale compared with 53.8% for the tri-weekly My PANDAS Chart ratings. There was moderate agreement between children and parents on the PANS Symptom Rating Scale (r = 0.55, p < 0.0001). Conclusion: Our study highlights the utility of electronic methods for tracking longitudinal symptoms in children with PANS and suggests that particular baseline characteristics (e.g., delay in identification and treatment of PANS, greater caregiver burden) may be indicative of a differential trajectory of PANS course, with more severe symptoms over the short term. clinicaltrials.gov NCT04382716.

Predicting Core Characteristics of ASD Through Facial Emotion Recognition and Eye Tracking in Youth.

Autism Spectrum Disorder (ASD) is a heterogeneous neurodevelopmental disorder (NDD) with a high rate of comorbidity. The implementation of eye-tracking methodologies has informed behavioral and neurophysiological patterns of visual processing across ASD and comorbid NDDs. In this study, we propose a machine learning method to predict measures of two core ASD characteristics: impaired social interactions and communication, and restricted, repetitive, and stereotyped behaviors and interests. Our method extracts behavioral features from task performance and eye-tracking data collected during a facial emotion recognition paradigm. We achieved high regression accuracy using a Random Forest regressor trained to predict scores on the SRS-2 and RBS-R assessments; this approach may serve as a classifier for ASD diagnosis.