Adaptive thresholding increases sensitivity to detect changes in the rate of skin conductance responses to psychologically arousing stimuli in both laboratory and ambulatory settings

Psychophysiologists recording electrodermal activity (EDA) often derive measures of slow, tonic activity-skin conductance level (SCL)-and faster, more punctate changes-skin conductance responses (SCRs). A SCR is conventionally considered to have occurred when the local amplitude of the EDA signal exceeds a researcher-determined threshold (e.g., 0.05 μS), typically fixed across study participants and conditions. However, fixed SCR thresholds can preferentially exclude data from individuals with low SCL because their SCRs are smaller on average, thereby reducing statistical power for group-level analyses. Thus, we developed a fixed plus adaptive (FA) thresholding method that adjusts identification of SCRs based on an individual's SC at the onset of the SCR to increase statistical power and include data from more participants. We assess the utility of applying FA thresholding across two independent samples and explore age and race-related associations with EDA outcomes. Study 1 uses wired EDA measurements from 254 healthy adults responding to evocative images and sounds in a laboratory setting. Study 2 uses wireless EDA measurements from 20 children with autism in a clinical environment while they completed behavioral tasks. Compared to a 0.01, 0.03, and 0.05 μS fixed threshold, FA thresholding at 1.9% modestly increases statistical power to detect a difference in SCR rate between tasks with higher vs. lower subjective arousal and reduces exclusion of participants by up to 5% across both samples. This novel method expands the EDA analytical toolbox and may be useful in populations with highly variable basal SCL or when comparing groups with different basal SCL. Future research should test for reproducibility and generalizability in other tasks, samples, and contexts. IMPACT STATEMENTS: This article is important because it introduces a novel method to enhance sensitivity and statistical power in analyses of skin conductance responses from electrodermal data.

Can peripheral psychophysiological markers predict response to exposure-based cognitive behavioral therapy in youth with severely impairing irritability? A study protocol

BACKGROUND

Irritability, an increased proneness to anger, is a primary reason youth present for psychiatric care. While initial evidence supports the efficacy of exposure-based cognitive behavioral therapy (CBT) for youth with clinically impairing irritability, treatment mechanisms remain unclear. Here, we propose to measure peripheral psychophysiological indicators of arousal-heart rate (HR)/electrodermal activity (EDA)-and regulation-heart rate variability (HRV)-during exposures to anger-inducing stimuli as potential predictors of treatment efficacy. The objective of this study is to evaluate whether in-situ biosensing data provides peripheral physiological indicators of in-session response to exposures.

METHODS

Blood volume pulse (BVP; from which HR and HRV canl be derived) and EDA will be collected ambulatorily using the Empatica EmbracePlus from 40 youth (all genders; ages 8-17) undergoing six in-person exposure treatment sessions, as part of a multiple-baseline trial of exposure-based CBT for clinically impairing irritability. Clinical ratings of irritability will be conducted at baseline, weekly throughout treatment, and at 3-month and 6-month follow-ups via the Clinical Global Impressions Scale (CGI) and the Affective Reactivity Index (ARI; clinician-, parent-, and child-report). Multilevel modeling will be used to assess within- and between-person changes in physiological arousal and regulation throughout exposure-based CBT and to determine whether individual differences are predictive of treatment response.

DISCUSSION

This study protocol leverages a wearable biosensor (Empatica) to continuously record HR/HRV (derived from BVP) and EDA during in-person exposure sessions for youth with clinically impairing irritability. Here, the goal is to identify changes in physiological arousal (EDA, HR) and regulation (HRV) over the course of treatment in tandem with changes in clinical symptoms.

TRIAL REGISTRATION

The participants in this study come from an overarching clinical trial (trial registration numbers: NCT02531893 first registered on 8/25/2015; last updated on 8/25/2023). The research project and all related materials were submitted and approved by the appropriate Institutional Review Board of the National Institute of Mental Health (NIMH).

Wearable Biosensing to Predict Imminent Aggressive Behavior in Psychiatric Inpatient Youths With Autism

Importance

Aggressive behavior is a prevalent and challenging issue in individuals with autism.

Objective

To investigate whether changes in peripheral physiology recorded by a wearable biosensor and machine learning can be used to predict imminent aggressive behavior before it occurs in inpatient youths with autism.

Design, Setting, and Participants

This noninterventional prognostic study used data collected from March 2019 to March 2020 from 4 primary care psychiatric inpatient hospitals. Enrolled participants were 86 psychiatric inpatients with confirmed diagnoses of autism exhibiting operationally defined self-injurious behavior, emotion dysregulation, or aggression toward others; 16 individuals were not included (18.6%) because they would not wear the biosensor (8 individuals) or were discharged before an observation could be made (8 individuals). Data were analyzed from March 2020 through October 2023.

Main Outcomes and Measures

Research staff performed live behavioral coding of aggressive behavior while inpatient study participants wore a commercially available biosensor that recorded peripheral physiological signals (cardiovascular activity, electrodermal activity, and motion). Logistic regression, support vector machines, neural networks, and domain adaptation were used to analyze time-series features extracted from biosensor data. Area under the receiver operating characteristic curve (AUROC) values were used to evaluate the performance of population- and person-dependent models.

Results

There were 70 study participants (mean [range; SD] age, 11.9 [5-19; 3.5] years; 62 males [88.6%]; 1 Asian [1.4%], 5 Black [7.1%], 1 Native Hawaiian or Other Pacific Islander [1.4%], and 63 White [90.0%]; 5 Hispanic [7.5%] and 62 non-Hispanic [92.5%] among 67 individuals with ethnicity data). Nearly half of the population (32 individuals [45.7%]) was minimally verbal, and 30 individuals (42.8%) had an intellectual disability. Participant length of inpatient hospital stay ranged from 8 to 201 days, and the mean (SD) length was 37.28 (33.95) days. A total of 429 naturalistic observational coding sessions were recorded, totaling 497 hours, wherein 6665 aggressive behaviors were documented, including self-injury (3983 behaviors [59.8%]), emotion dysregulation (2063 behaviors [31.0%]), and aggression toward others (619 behaviors [9.3%]). Logistic regression was the best-performing overall classifier across all experiments; for example, it predicted aggressive behavior 3 minutes before onset with a mean AUROC of 0.80 (95% CI, 0.79-0.81).

Conclusions and Relevance

This study replicated and extended previous findings suggesting that machine learning analyses of preceding changes in peripheral physiology may be used to predict imminent aggressive behaviors before they occur in inpatient youths with autism. Further research will explore clinical implications and the potential for personalized interventions.

Systematic review: emotion dysregulation and challenging behavior interventions for children and adolescents on the autism spectrum with graded key evidence-based strategy recommendations

Challenging behavior, such as aggression, is highly prevalent in children and adolescents on the autism spectrum and can have a devastating impact. Previous reviews of challenging behavior interventions did not include interventions targeting emotion dysregulation, a common cause of challenging behavior. We reviewed emotion dysregulation and challenging behavior interventions for preschoolers to adolescents to determine which evidence-based strategies have the most empirical support for reducing/preventing emotion dysregulation/challenging behavior. We reviewed 95 studies, including 29 group and 66 single case designs. We excluded non-behavioral/psychosocial interventions and those targeting internalizing symptoms only. We applied a coding system to identify discrete strategies based on autism practice guidelines with the addition of strategies common in childhood mental health disorders, and an evidence grading system. Strategies with the highest quality evidence (multiple randomized controlled trials with low bias risk) were Parent-Implemented Intervention, Emotion Regulation Training, Reinforcement, Visual Supports, Cognitive Behavioral/Instructional Strategies and Antecedent-Based Interventions. Regarding outcomes, most studies included challenging behavior measures, while few included emotion dysregulation measures. This review highlights the importance of teaching emotion regulation skills explicitly, positively reinforcing replacement/alternative behaviors, using visuals and metacognition, addressing stressors proactively, and involving parents. It also calls for more rigorously designed studies and for including emotion dysregulation as an outcome/mediator in future trials.

A Digital Mental Health App Incorporating Wearable Biosensing for Teachers of Children on the Autism Spectrum to Support Emotion Regulation: Protocol for a Pilot Randomized Controlled Trial

BACKGROUND

As much as 80% of children on the autism spectrum exhibit challenging behaviors (ie, behaviors dangerous to the self or others, behaviors that interfere with learning and development, and behaviors that interfere with socialization) that can have a devastating impact on personal and family well-being, contribute to teacher burnout, and even require hospitalization. Evidence-based practices to reduce these behaviors emphasize identifying triggers (events or antecedents that lead to challenging behaviors); however, parents and teachers often report that challenging behaviors surface with little warning. Exciting recent advances in biometric sensing and mobile computing technology allow the measurement of momentary emotion dysregulation using physiological indexes.

OBJECTIVE

We present the framework and protocol for a pilot trial that will test a mobile digital mental health app, the KeepCalm app. School-based approaches to managing challenging behaviors in children on the autism spectrum are limited by 3 key factors: children on the autism spectrum often have difficulties in communicating their emotions; it is challenging to implement evidence-based, personalized strategies for individual children in group settings; and it is difficult for teachers to track which strategies are successful for each child. KeepCalm aims to address those barriers by communicating children's stress to their teachers using physiological signaling (emotion dysregulation detection), supporting the implementation of emotion regulation strategies via smartphone pop-up notifications of top strategies for each child according to their behavior (emotion regulation strategy implementation), and easing the task of tracking outcomes by providing the child's educational team with a tool to track the most effective emotion regulation strategies for that child based on physiological stress reduction data (emotion regulation strategy evaluation).

METHODS

We will test KeepCalm with 20 educational teams of students on the autism spectrum with challenging behaviors (no exclusion based on IQ or speaking ability) in a pilot randomized waitlist-controlled field trial over a 3-month period. We will examine the usability, acceptability, feasibility, and appropriateness of KeepCalm as primary outcomes. Secondary preliminary efficacy outcomes include clinical decision support success, false positives or false negatives of stress alerts, and the reduction of challenging behaviors and emotion dysregulation. We will also examine technical outcomes, including the number of artifacts and the proportion of time children are engaged in high physical movement based on accelerometry data; test the feasibility of our recruitment strategies; and test the response rate and sensitivity to change of our measures, in preparation for a future fully powered large-scale randomized controlled trial.

RESULTS

The pilot trial will begin by September 2023.

CONCLUSIONS

Results will provide key data about important aspects of implementing KeepCalm in preschools and elementary schools and will provide preliminary data about its efficacy to reduce challenging behaviors and support emotion regulation in children on the autism spectrum.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05277194; https://www.clinicaltrials.gov/ct2/show/NCT05277194.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/45852.

Systematic Review: Emotion Dysregulation and Challenging Behavior Interventions for Children andAdolescents with Autism with Graded Key Evidence-Based Strategy Recommendations

Challenging behavior, such as aggression, is highly prevalent in children and adolescents with autism and can have a devastating impact. Previous reviews of challenging behavior interventions did not include interventions targeting emotion dysregulation, a common cause of challenging behavior. We reviewed emotion dysregulation and challenging behavior interventions for preschoolers to adolescents to determine which evidence-based strategies have the most empirical support for reducing/preventing emotion dysregulation/challenging behavior. We reviewed 95 studies, including 29 group and 66 single-case designs. We excluded non-behavioral/psychosocial interventions and those targeting internalizing symptoms only. We applied a coding system to identify discrete strategies based on autism practice guidelines with the addition of strategies common in childhood mental health disorders, and an evidence grading system. Strategies with the highest quality evidence (multiple randomized controlled trials with low bias risk) were Parent-Implemented Intervention, Emotion Regulation Training, Reinforcement, Visual Supports, Cognitive Behavioral/Instructional Strategies and Antecedent-Based Interventions. Regarding outcomes, most studies included challenging behaviors measures while few included emotion dysregulation measures. This review highlights the importance of teaching emotion-regulation skills explicitly, positively reinforcing replacement/alternative behaviors, using visuals and metacognition, addressing stressors proactively, and involving parents. It also calls for more rigorously-designed studies and for including emotion dysregulation as an outcome/mediator in future trials.

Mapping the time course of overt emotion dysregulation, self-injurious behavior, and aggression in psychiatrically hospitalized autistic youth: A naturalistic study

Challenges with emotion dysregulation, self-injurious behavior (SIB), and aggression are common in autistic individuals. Prior research on the relationships between these behaviors is limited mainly to cross-sectional correlations of parent-report data. Understanding how emotion dysregulation, SIB, and aggression present and relate to one another in real-time could add to our understanding of the context and function of these behaviors. The present study examined the real-time occurrence and temporal relationships between these behaviors in 53 psychiatrically hospitalized autistic youth. Over 500 hours of behavioral observation occurred during everyday activities in the hospital. Start and stop times for instances of overt emotion dysregulation, SIB, and aggression were coded live using a custom mobile phone app. Results indicated large individual variability in the frequency and duration of these behaviors and their co-occurrence. Both SIB and aggression co-occurred with overt emotion dysregulation at above-chance levels, suggesting a role for emotional distress in the occurrence of these behaviors. However, there was substantial variability within and between individuals in co-occurrence, and SIB and aggression often (and for some individuals, almost always) occurred without overt emotion dysregulation. Relatedly, cross-recurrence quantitative analysis revealed that SIB and aggression preceded emotion dysregulation more often than emotion dysregulation preceded SIB and aggression. Future research, perhaps using ambulatory psychophysiological measures, is needed to understand whether emotion dysregulation may sometimes be present but not easily observed during SIB and aggression. LAY SUMMARY: This study provides insight into how overt emotion dysregulation (i.e., visible distress), aggression, and self-injury unfold in real-time for autistic individuals. Participants were 53 autistic youth staying in a psychiatric hospital. Research staff observed participants in everyday activities on the hospital unit and noted instances of aggression, self-injurious behavior, and emotion dysregulation. Results suggest that aggression and self-injury sometimes occur with visible signs of distress but also often occur without visible distress. In addition, observable distress was more common in the moments after these behaviors than in the moments before.

Evaluating commercially available wireless cardiovascular monitors for measuring and transmitting real-time physiological responses in children with autism

Commercially available wearable biosensors have the potential to enhance psychophysiology research and digital health technologies for autism by enabling stress or arousal monitoring in naturalistic settings. However, such monitors may not be comfortable for children with autism due to sensory sensitivities. To determine the feasibility of wearable technology in children with autism age 8-12 years, we first selected six consumer-grade wireless cardiovascular monitors and tested them during rest and movement conditions in 23 typically developing adults. Subsequently, the best performing monitors (based on data quality robustness statistics), Polar and Mio Fuse, were evaluated in 32 children with autism and 23 typically developing children during a 2-h session, including rest and mild stress-inducing tasks. Cardiovascular data were recorded simultaneously across monitors using custom software. We administered the Comfort Rating Scales to children. Although the Polar monitor was less comfortable for children with autism than typically developing children, absolute scores demonstrated that, on average, all children found each monitor comfortable. For most children, data from the Mio Fuse (96%-100%) and Polar (83%-96%) passed quality thresholds of data robustness. Moreover, in the stress relative to rest condition, heart rate increased for the Polar, F(1,53) = 135.70, p < 0.001, ηp²  = 0.78, and Mio Fuse, F(1,53) = 71.98, p < 0.001, ηp²  = 0.61, respectively, and heart rate variability decreased for the Polar, F(1,53) = 13.41, p = 0.001, ηp²  = 0.26, and Mio Fuse, F(1,53) = 8.89, p = 0.005, ηp²  = 0.16, respectively. This feasibility study suggests that select consumer-grade wearable cardiovascular monitors can be used with children with autism and may be a promising means for tracking physiological stress or arousal responses in community settings. LAY SUMMARY: Commercially available heart rate trackers have the potential to advance stress research with individuals with autism. Due to sensory sensitivities common in autism, their comfort wearing such trackers is vital to gathering robust and valid data. After assessing six trackers with typically developing adults, we tested the best trackers (based on data quality) in typically developing children and children with autism and found that two of them met criteria for comfort, robustness, and validity.

Cardiovascular reactivity as a measure of irritability in a transdiagnostic sample of youth: Preliminary associations

OBJECTIVES

Irritability is a transdiagnostic symptom in developmental psychopathology, conceptualized as a low threshold for frustration and increased proneness to anger. While central to emotion regulation, there is a vital need for empirical studies to explore the relationship between irritability and underlying physiological mechanisms of cardiovascular arousal.

METHODS

We examined the relationship between irritability and cardiovascular arousal (i.e., heart rate [HR] and heart rate variability [HRV]) in a transdiagnostic sample of 51 youth (M = 12.63 years, SD = 2.25; 62.7% male). Data was collected using the Empatica E4 during a laboratory stop-signal task. In addition, the impact of motion activity, age, medication, and sleep on cardiovascular responses was explored.

RESULTS

Main findings showed that irritability was associated with increased HR and decreased HRV during task performance.

CONCLUSIONS

Findings support the role of peripheral physiological dysregulation in youth with emotion regulation problems and suggest the potential use of available wearable consumer electronics as an objective measure of irritability and physiological arousal in a transdiagnostic sample of youth.

A Tribute to the Mind, Methodology and Mentoring of Wayne Velicer

Wayne Velicer is remembered for a mind where mathematical concepts and calculations intrigued him, behavioral science beckoned him, and people fascinated him. Born in Green Bay, Wisconsin on March 4, 1944, he was raised on a farm, although early influences extended far beyond that beginning. His Mathematics BS and Psychology minor at Wisconsin State University in Oshkosh, and his PhD in Quantitative Psychology from Purdue led him to a fruitful and far-reaching career. He was honored several times as a high-impact author, was a renowned scholar in quantitative and health psychology, and had more than 300 scholarly publications and 54,000+ citations of his work, advancing the arenas of quantitative methodology and behavioral health. In his methodological work, Velicer sought out ways to measure, synthesize, categorize, and assess people and constructs across behaviors and time, largely through principal components analysis, time series, and cluster analysis. Further, he and several colleagues developed a method called Testing Theory-based Quantitative Predictions, successfully applied to predicting outcomes and effect sizes in smoking cessation, diet behavior, and sun protection, with the potential for wider applications. With $60,000,000 in external funding, Velicer also helped engage a large cadre of students and other colleagues to study methodological models for a myriad of health behaviors in a widely applied Transtheoretical Model of Change. Unwittingly, he has engendered indelible memories and gratitude to all who crossed his path. Although Wayne Velicer left this world on October 15, 2017 after battling an aggressive cancer, he is still very present among us.

Visual Preference for Biological Motion in Children and Adults with Autism Spectrum Disorder: An Eye-Tracking Study

Participants with autism spectrum disorder (ASD) (n = 121, mean [SD] age: 14.6 [8.0] years) and typically developing (TD) controls (n = 40, 16.4 [13.3] years) were presented with a series of videos representing biological motion on one side of a computer monitor screen and non-biological motion on the other, while their eye movements were recorded. As predicted, participants with ASD spent less overall time looking at presented stimuli than TD participants (P < 10^-3) and showed less preference for biological motion (P < 10^-5). Participants with ASD also had greater average latencies than TD participants of the first fixation on both biological (P < 0.01) and non-biological motion (P < 0.02). Findings suggest that individuals with ASD differ from TD individuals on multiple properties of eye movements and biological motion preference.

Social attention to activities in children and adults with autism spectrum disorder: effects of context and age

Background

Diminished visual monitoring of faces and activities of others is an early feature of autism spectrum disorder (ASD). It is uncertain whether deficits in activity monitoring, identified using a homogeneous set of stimuli, persist throughout the lifespan in ASD, and thus, whether they could serve as a biological indicator (“biomarker”) of ASD. We investigated differences in visual attention during activity monitoring in children and adult participants with autism compared to a control group of participants without autism.

Methods

Eye movements of participants with autism (n = 122; mean age [SD] = 14.5 [8.0] years) and typically developing (TD) controls (n = 40, age = 16.4 [13.3] years) were recorded while they viewed a series of videos depicting two female actors conversing while interacting with their hands over a shared task. Actors either continuously focused their gaze on each other’s face (mutual gaze) or on the shared activity area (shared focus). Mean percentage looking time was computed for the activity area, actors’ heads, and their bodies.

Results

Compared to TD participants, participants with ASD looked longer at the activity area (mean % looking time: 58.5% vs. 53.8%, p < 0.005) but less at the heads (15.2% vs. 23.7%, p < 0.0001). Additionally, within-group differences in looking time were observed between the mutual gaze and shared focus conditions in both participants without ASD (activity: Δ = − 6.4%, p < 0.004; heads: Δ = + 3.5%, p < 0.02) and participants with ASD (bodies: Δ = + 1.6%, p < 0.002).

Limitations

The TD participants were not as well characterized as the participants with ASD. Inclusion criteria regarding the cognitive ability [intelligence quotient (IQ) > 60] limited the ability to include individuals with substantial intellectual disability.

Conclusions

Differences in attention to faces could constitute a feature discriminative between individuals with and without ASD across the lifespan, whereas between-group differences in looking at activities may shift with development. These findings may have applications in the search for underlying biological indicators specific to ASD.

Trial registration ClinicalTrials.gov identifier NCT02668991.

Atypical Emotional Electrodermal Activity in Toddlers with Autism Spectrum Disorder

Past studies in autism spectrum disorder (ASD) indicate atypical peripheral physiological arousal. However, the conditions under which these atypicalities arise and their link with behavioral emotional expressions and core ASD symptoms remain uncertain. Given the importance of physiological arousal in affective, learning, and cognitive processes, the current study examined changes in skin conductance level (ΔSCL) in 41 toddlers with ASD (mean age: 22.7 months, SD: 2.9) and 32 age-matched toddlers with typical development (TD) (mean age: 21.6 months, SD: 3.6) in response to probes designed to induce anger, joy, and fear emotions. The magnitude of ΔSCL was comparable during anger (P = 0.206, d = 0.30) and joy (P = 0.996, d = 0.01) conditions, but significantly lower during the fear condition (P = 0.001, d = 0.83) in toddlers with ASD compared to TD peers. In the combined samples, ΔSCL positively correlated with intensity of behavioral emotional expressivity during the anger (r[71] = 0.36, P = 0.002) and fear (r[68] = 0.32, P = 0.007) conditions, but not in the joy (r[69] = -0.15, P = 0.226) condition. Finally, ΔSCL did not associate with autism symptom severity in any emotion-eliciting condition in the ASD group. Toddlers with ASD displayed attenuated ΔSCL to situations aimed at eliciting fear, which may forecast the emergence of highly prevalent internalizing and externalizing problems in this population. The study putatively identifies ΔSCL as a dimension not associated with severity of autism but with behavioral responses in negatively emotionally challenging events and provides support for the feasibility, validity, and incipient utility of examining ΔSCL in response to emotional challenges in very young children. LAY SUMMARY: Physiological arousal was measured in toddlers with autism exposed to frustrating, pleasant, and threatening tasks. Compared to typically developing peers, toddlers with autism showed comparable arousal responses to frustrating and pleasant events, but lower responses to threatening events. Importantly, physiological arousal and behavioral expressions were aligned during frustrating and threatening events, inviting exploration of physiological arousal to measure responses to emotional challenges. Furthermore, this study advances the understanding of precursors to emotional and behavioral problems common in older children with autism. Autism Res 2020, 13: 1476-1488. © 2020 International Society for Autism Research, Wiley Periodicals, Inc.

Automated recognition of spontaneous facial expression in individuals with autism spectrum disorder: parsing response variability

BACKGROUND

Reduction or differences in facial expression are a core diagnostic feature of autism spectrum disorder (ASD), yet evidence regarding the extent of this discrepancy is limited and inconsistent. Use of automated facial expression detection technology enables accurate and efficient tracking of facial expressions that has potential to identify individual response differences.

METHODS

Children and adults with ASD (N = 124) and typically developing (TD, N = 41) were shown short clips of "funny videos." Using automated facial analysis software, we investigated differences between ASD and TD groups and within the ASD group in evidence of facial action unit (AU) activation related to the expression of positive facial expression, in particular, a smile.

RESULTS

Individuals with ASD on average showed less evidence of facial AUs (AU12, AU6) relating to positive facial expression, compared to the TD group (p < .05, r = - 0.17). Using Gaussian mixture model for clustering, we identified two distinct distributions within the ASD group, which were then compared to the TD group. One subgroup (n = 35), termed "over-responsive," expressed more intense positive facial expressions in response to the videos than the TD group (p < .001, r = 0.31). The second subgroup (n = 89), ("under-responsive"), displayed fewer, less intense positive facial expressions in response to videos than the TD group (p < .001; r = - 0.36). The over-responsive subgroup differed from the under-responsive subgroup in age and caregiver-reported impulsivity (p < .05, r = 0.21). Reduced expression in the under-responsive, but not the over-responsive group, was related to caregiver-reported social withdrawal (p < .01, r = - 0.3).

LIMITATIONS

This exploratory study does not account for multiple comparisons, and future work will have to ascertain the strength and reproducibility of all results. Reduced displays of positive facial expressions do not mean individuals with ASD do not experience positive emotions.

CONCLUSIONS

Individuals with ASD differed from the TD group in their facial expressions of positive emotion in response to "funny videos." Identification of subgroups based on response may help in parsing heterogeneity in ASD and enable targeting of treatment based on subtypes.

TRIAL REGISTRATION

ClinicalTrials.gov, NCT02299700. Registration date: November 24, 2014.

Relationship Between Sleep and Behavior in Autism Spectrum Disorder: Exploring the Impact of Sleep Variability

Objective

The relationship between sleep (caregiver-reported and actigraphy-measured) and other caregiver-reported behaviors in children and adults with autism spectrum disorder (ASD) was examined, including the use of machine learning to identify sleep variables important in predicting anxiety in ASD.

Methods

Caregivers of ASD (n = 144) and typically developing (TD) (n = 41) participants reported on sleep and other behaviors. ASD participants wore an actigraphy device at nighttime during an 8 or 10-week non-interventional study. Mean and variability of actigraphy measures for ASD participants in the week preceding midpoint and endpoint were calculated and compared with caregiver-reported and clinician-reported symptoms using a mixed effects model. An elastic-net model was developed to examine which sleep measures may drive prediction of anxiety.

Results

Prevalence of caregiver-reported sleep difficulties in ASD was approximately 70% and correlated significantly (p < 0.05) with sleep efficiency measured by actigraphy. Mean and variability of actigraphy measures like sleep efficiency and number of awakenings were related significantly (p < 0.05) to ASD symptom severity, hyperactivity and anxiety. In the elastic net model, caregiver-reported sleep, and variability of sleep efficiency and awakenings were amongst the important predictors of anxiety.

Conclusion

Caregivers report problems with sleep in the majority of children and adults with ASD. Reported problems and actigraphy measures of sleep, particularly variability, are related to parent reported behaviors. Measuring variability in sleep may prove useful in understanding the relationship between sleep problems and behavior in individuals with ASD. These findings may have implications for both intervention and monitoring outcomes in ASD.

Time-Series Prediction of Proximal Aggression Onset in Minimally-Verbal Youth with Autism Spectrum Disorder Using Physiological Biosignals

It has been suggested that changes in physiological arousal precede potentially dangerous aggressive behavior in youth with autism spectrum disorder (ASD) who are minimally verbal (MV-ASD). The current work tests this hypothesis through time-series analyses on biosignals acquired prior to proximal aggression onset. We implement ridge-regularized logistic regression models on physiological biosensor data wirelessly recorded from 15 MV-ASD youth over 64 independent naturalistic observations in a hospital inpatient unit. Our results demonstrate proof-of-concept, feasibility, and incipient validity predicting aggression onset 1 minute before it occurs using global, person-dependent, and hybrid classifier models.

Automated Pain Assessment using Electrodermal Activity Data and Machine Learning

Objective pain assessment is required for appropriate pain management in the clinical setting. However, clinical gold standard pain assessment is based on subjective methods. Automated pain detection from physiological data may provide important objective information to better standardize pain assessment. Specifically, electrodermal activity (EDA) can identify features of stress and anxiety induced by varying pain levels. However, notable variability in EDA measurement exists and research to date has demonstrated sensitivity but lack of specificity in pain assessment. In this paper, we use timescale decomposition (TSD) to extract salient features from EDA signals to identify an accurate and automated EDA pain detection algorithm to sensitively and specifically distinguish pain from no-pain conditions.

Social Robots for Hospitalized Children

BACKGROUND AND OBJECTIVES

Social robots (SRs) are increasingly present in medical and educational contexts, but their use in inpatient pediatric settings has not been demonstrated in studies. In this study, we aimed to (1) describe the introduction of SR technology into the pediatric inpatient setting through an innovative partnership among a pediatric teaching hospital, robotics development, and computational behavioral science laboratories and (2) present feasibility and acceptability data.

METHODS

Fifty-four children ages 3 to 10 years were randomly exposed to 1 of 3 interventions: (1) interactive SR teddy bear; (2) tablet-based avatar version of the bear; or (3) plush teddy bear with human presence. We monitored intervention enrollment and completion patterns, obtained qualitative feedback on acceptability of SR use from child life-specialist stakeholders, and assessed children's positive and negative affect, anxiety, and pain intensity pre- and postintervention.

RESULTS

The intervention was well received and appeared feasible, with 93% of those enrolled completing the study (with 80% complete parent data). Children exposed to the SR reported more positive affect relative to those who received a plush animal. SR interactions were characterized by greater levels of joyfulness and agreeableness than comparison interventions. Child life specialist stakeholders reported numerous potential benefits of SR technology in the pediatric setting.

CONCLUSIONS

The SR appears to be an engaging tool that may provide new ways to address the emotional needs of hospitalized children, potentially increasing access to emotionally targeted interventions. Rigorous development and validation of SR technology in pediatrics could ultimately lead to scalable and cost-effective tools to improve the patient care experience.

Predicting aggression to others in youth with autism using a wearable biosensor

Unpredictable and potentially dangerous aggressive behavior by youth with Autism Spectrum Disorder (ASD) can isolate them from foundational educational, social, and familial activities, thereby markedly exacerbating morbidity and costs associated with ASD. This study investigates whether preceding physiological and motion data measured by a wrist-worn biosensor can predict aggression to others by youth with ASD. We recorded peripheral physiological (cardiovascular and electrodermal activity) and motion (accelerometry) signals from a biosensor worn by 20 youth with ASD (ages 6-17 years, 75% male, 85% minimally verbal) during 69 independent naturalistic observation sessions with concurrent behavioral coding in a specialized inpatient psychiatry unit. We developed prediction models based on ridge-regularized logistic regression. Our results suggest that aggression to others can be predicted 1 min before it occurs using 3 min of prior biosensor data with an average area under the curve of 0.71 for a global model and 0.84 for person-dependent models. The biosensor was well tolerated, we obtained useable data in all cases, and no users withdrew from the study. Relatively high predictive accuracy was achieved using antecedent physiological and motion data. Larger trials are needed to further establish an ideal ratio of measurement density to predictive accuracy and reliability. These findings lay the groundwork for the future development of precursor behavior analysis and just-in-time adaptive intervention systems to prevent or mitigate the emergence, occurrence, and impact of aggression in ASD. Autism Res 2019, 12: 1286-1296. © 2019 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: Unpredictable aggression can create a barrier to accessing community, therapeutic, medical, and educational services. The present study evaluated whether data from a wearable biosensor can be used to predict aggression to others by youth with autism spectrum disorder (ASD). Results demonstrate that aggression to others can be predicted 1 min before it occurs with high accuracy, laying the groundwork for the future development of preemptive behavioral interventions and just-in-time adaptive intervention systems to prevent or mitigate the emergence, occurrence, and impact of aggression to others in ASD.

Caregiver Daily Reporting of Symptoms in Autism Spectrum Disorder: Observational Study Using Web and Mobile Apps

BACKGROUND

Currently, no medications are approved to treat core symptoms of autism spectrum disorder (ASD). One barrier to ASD medication development is the lack of validated outcome measures able to detect symptom change. Current ASD interventions are often evaluated using retrospective caregiver reports that describe general clinical presentation but often require recall of specific behaviors weeks after they occur, potentially reducing accuracy of the ratings. My JAKE, a mobile and Web-based mobile health (mHealth) app that is part of the Janssen Autism Knowledge Engine-a dynamically updated clinical research system-was designed to help caregivers of individuals with ASD to continuously log symptoms, record treatments, and track progress, to mitigate difficulties associated with retrospective reporting.

OBJECTIVE

My JAKE was deployed in an exploratory, noninterventional clinical trial to evaluate its utility and acceptability to monitor clinical outcomes in ASD. Hypotheses regarding relationships among daily tracking of symptoms, behavior, and retrospective caregiver reports were tested.

METHODS

Caregivers of individuals with ASD aged 6 years to adults (N=144) used the My JAKE app to make daily reports on their child's sleep quality, affect, and other self-selected specific behaviors across the 8- to 10-week observational study. The results were compared with commonly used paper-and-pencil scales acquired over a concurrent period at regular 4-week intervals.

RESULTS

Caregiver reporting of behaviors in real time was successfully captured by My JAKE. On average, caregivers made reports 2-3 days per week across the study period. Caregivers were positive about their use of the system, with over 50% indicating that they would like to use My JAKE to track behavior outside of a clinical trial. More positive average daily reporting of overall type of day was correlated with 4 weekly reports of lower caregiver burden made at 4-week intervals (r=-0.27, P=.006, n=88) and with ASD symptoms (r=-0.42, P<.001, n=112).

CONCLUSIONS

My JAKE reporting aligned with retrospective Web-based or paper-and-pencil scales. Use of mHealth apps, such as My JAKE, has the potential to increase the validity and accuracy of caregiver-reported outcomes and could be a useful way of identifying early changes in response to intervention. Such systems may also assist caregivers in tracking symptoms and behavior outside of a clinical trial, help with personalized goal setting, and monitoring of progress, which could collectively improve understanding of and quality of life for individuals with ASD and their families.

TRIAL REGISTRATION

ClinicalTrials.gov NCT02668991; https://clinicaltrials.gov/ct2/show/NCT02668991.

Clinical Validation of the Autism Behavior Inventory: Caregiver-Rated Assessment of Core and Associated Symptoms of Autism Spectrum Disorder

There is a need for measures to track symptom change in autism spectrum disorder (ASD). We conducted a validation study on a revised version of the Autism Behavior Inventory (ABI), and a short form (ABI-S). Caregivers of individuals (6–54 years) with confirmed diagnoses of ASD (N = 144) completed the ABI and other rating scales at 4 time points. Scale consistency for each domain, 3–5 day test–retest reliability, and construct validity, determined by comparison to pre-specified scales, were all good. Change in the ABI was congruent with changes in other instruments. Collectively, results suggest incipient suitability of the ABI as a measure of changes in core and associated symptoms of ASD.

Trial Registration NCT02299700.

An Observational Study With the Janssen Autism Knowledge Engine (JAKE®) in Individuals With Autism Spectrum Disorder

Objective: The Janssen Autism Knowledge Engine (JAKE®) is a clinical research outcomes assessment system developed to more sensitively measure treatment outcomes and identify subpopulations in autism spectrum disorder (ASD). Here we describe JAKE and present results from its digital phenotyping (My JAKE) and biosensor (JAKE Sense) components. Methods: An observational, non-interventional, prospective study of JAKE in children and adults with ASD was conducted at nine sites in the United States. Feedback on JAKE usability was obtained from caregivers. JAKE Sense included electroencephalography, eye tracking, electrocardiography, electrodermal activity, facial affect analysis, and actigraphy. Caregivers of individuals with ASD reported behaviors using My JAKE. Results from My JAKE and JAKE Sense were compared to traditional ASD symptom measures. Results: Individuals with ASD (N = 144) and a cohort of typically developing (TD) individuals (N = 41) participated in JAKE Sense. Most caregivers reported that overall use and utility of My JAKE was "easy" (69%, 74/108) or "very easy" (74%, 80/108). My JAKE could detect differences in ASD symptoms as measured by traditional methods. The majority of biosensors included in JAKE Sense captured sizable amounts of quality data (i.e., 93-100% of eye tracker, facial affect analysis, and electrocardiogram data was of good quality), demonstrated differences between TD and ASD individuals, and correlated with ASD symptom scales. No significant safety events were reported. Conclusions: My JAKE was viewed as easy or very easy to use by caregivers participating in research outside of a clinical study. My JAKE sensitively measured a broad range of ASD symptoms. JAKE Sense biosensors were well-tolerated. JAKE functioned well when used at clinical sites previously inexperienced with some of the technologies. Lessons from the study will optimize JAKE for use in clinical trials to assess ASD interventions. Additionally, because biosensors were able to detect features differentiating TD and ASD individuals, and also were correlated with standardized symptom scales, these measures could be explored as potential biomarkers for ASD and as endpoints in future clinical studies. Clinical Trial Registration: https://clinicaltrials.gov/ct2/show/NCT02668991 identifier: NCT02668991.

Predicting Imminent Aggression Onset in Minimally-Verbal Youth with Autism Spectrum Disorder Using Preceding Physiological Signals

We test the hypothesis that changes in preceding physiological arousal can be used to predict imminent aggression proximally before it occurs in youth with autism spectrum disorder (ASD) who are minimally verbal (MV-ASD). We evaluate this hypothesis through statistical analyses performed on physiological biosensor data wirelessly recorded from 20 MV-ASD youth over 69 independent naturalistic observations in a hospital inpatient unit. Using ridge-regularized logistic regression, results demonstrate that, on average, our models are able to predict the onset of aggression 1 minute before it occurs using 3 minutes of prior data with a 0.71 AUC for global, and a 0.84 AUC for person-dependent models.

Visual Exploration in Autism Spectrum Disorder: Exploring Age Differences and Dynamic Features Using Recurrence Quantification Analysis

Eye-tracking studies have demonstrated that individuals with autism spectrum disorder sometimes show differences in attention and gaze patterns. This includes preference for certain nonsocial objects, heightened attention to detail, and more difficulty with attention shifting and disengagement, which may be associated with restricted and repetitive behaviors. This study utilized a visual exploration task and replicates findings of reduced number of objects explored and increased fixation duration on high autism interest objects in a large sample of individuals with autism spectrum disorder (n = 129, age 6-54 years) in comparison with a typically developing group. These findings correlated with parent-reported repetitive behaviors. Additionally, we applied recurrent quantification analysis to enable identification of new eye-tracking features, which accounted for temporal and spatial differences in viewing patterns. These new features were found to discriminate between autism spectrum disorder and typically developing groups and were correlated with parent-reported repetitive behaviors. Original and novel eye-tracking features identified by recurrent quantification analysis differed in their relationships to reported behaviors and were dependent on age. Trial Registration: NCT02299700. Autism Research 2018, 11: 1554-1566. © 2018 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: Using eye-tracking technology and a visual exploration task, we showed that people with autism spectrum disorder (ASD) spend more time looking at particular kinds of objects, like trains and clocks, and look at fewer objects overall than people without ASD. Where people look and the order in which they look at objects were related to the restricted and repetitive behaviors reported by parents. Eye-tracking may be a useful addition to parent reports for measuring changes in behavior in individuals with ASD.

Cardiovascular Reactivity During Marital Conflict in Laboratory and Naturalistic Settings: Differential Associations with Relationship and Individual Functioning Across Contexts

Cardiovascular reactivity during spousal conflict is considered to be one of the main pathways for relationship distress to impact physical, mental, and relationship health. However, the magnitude of association between cardiovascular reactivity during laboratory marital conflict and relationship functioning is small and inconsistent given the scope of its importance in theoretical models of intimate relationships. This study tests the possibility that cardiovascular data collected in laboratory settings downwardly bias the magnitude of these associations when compared to measures obtained in naturalistic settings. Ambulatory cardiovascular reactivity data were collected from 20 couples during two relationship conflicts in a research laboratory, two planned relationship conflicts at couples' homes, and two spontaneous relationship conflicts during couples' daily lives. Associations between self-report measures of relationship functioning, individual functioning, and cardiovascular reactivity across settings are tested using multilevel models. Cardiovascular reactivity was significantly larger during planned and spontaneous relationship conflicts in naturalistic settings than during planned relationship conflicts in the laboratory. Similarly, associations with relationship and individual functioning variables were statistically significantly larger for cardiovascular data collected in naturalistic settings than the same data collected in the laboratory. Our findings suggest that cardiovascular reactivity during spousal conflict in naturalistic settings is statistically significantly different from that elicited in laboratory settings both in magnitude and in the pattern of associations with a wide range of inter- and intrapersonal variables. These differences in findings across laboratory and naturalistic physiological responses highlight the value of testing physiological phenomena across interaction contexts in romantic relationships.

The voluntary control of piloerection

Autonomic nervous systems in the human body are named for their operation outside of conscious control. One rare exception is voluntarily generated piloerection (VGP)-the conscious ability to induce goosebumps-whose physiological study, to our knowledge, is confined to three single-individual case studies. Very little is known about the physiological nature and emotional correlates of this ability. The current manuscript assesses physiological, emotional, and personality phenomena associated with VGP in a sample of thirty-two individuals. Physiological descriptions obtained from the sample are consistent with previous reports, including stereotypical patterns of sensation and action. Most participants also reported that their VGP accompanies psychological states associated with affective states (e.g., awe) and experience (e.g., listening to music), and higher than typical openness to new experiences. These preliminary findings suggest that this rare and unusual physiological ability interacts with emotional and personality factors, and thus merits further study.

Towards Automated Pain Detection in Children using Facial and Electrodermal Activity

Accurately determining pain levels in children is difficult, even for trained professionals and parents. Facial activity and electro- dermal activity (EDA) provide rich information about pain, and both have been used in automated pain detection. In this paper, we discuss preliminary steps towards fusing models trained on video and EDA features respectively. We compare fusion models using original video features and those using transferred video features which are less sensitive to environmental changes. We demonstrate the benefit of the fusion and the transferred video features with a special test case involving domain adaptation and improved performance relative to using EDA and video features alone.

Automated Pain Detection in Facial Videos of Children using Human-Assisted Transfer Learning

Accurately determining pain levels in children is difficult, even for trained professionals and parents. Facial activity provides sensitive and specific information about pain, and computer vision algorithms have been developed to automatically detect Facial Action Units (AUs) defined by the Facial Action Coding System (FACS). Our prior work utilized information from computer vision, i.e., automatically detected facial AUs, to develop classifiers to distinguish between pain and no-pain conditions. However, application of pain/no-pain classifiers based on automated AU codings across different environmental domains results in diminished performance. In contrast, classifiers based on manually coded AUs demonstrate reduced environmentally-based variability in performance. In this paper, we train a machine learning model to recognize pain using AUs coded by a computer vision system embedded in a software package called iMotions. We also study the relationship between iMotions (automatically) and human (manually) coded AUs. We find that AUs coded automatically are different from those coded by a human trained in the FACS system, and that the human coder is less sensitive to environmental changes. To improve classification performance in the current work, we applied transfer learning by training another machine learning model to map automated AU codings to a subspace of manual AU codings to enable more robust pain recognition performance when only automatically coded AUs are available for the test data. With this transfer learning method, we improved the Area Under the ROC Curve (AUC) on independent data from new participants in our target domain from 0.67 to 0.72.

Dense home-based recordings reveal typical and atypical development of tense/aspect in a child with delayed language development

Studies investigating the development of tense/aspect in children with developmental disorders have focused on production frequency and/or relied on short spontaneous speech samples. How children with developmental disorders use future forms/constructions is also unknown. The current study expands this literature by examining frequency, consistency, and productivity of past, present, and future usage, using the Speechome Recorder, which enables collection of dense, longitudinal audio-video recordings of children's speech. Samples were collected longitudinally in a child who was previously diagnosed with autism spectrum disorder, but at the time of the study exhibited only language delay [Audrey], and a typically developing child [Cleo]. While Audrey was comparable to Cleo in frequency and productivity of tense/aspect use, she was atypical in her consistency and production of an unattested future form. Examining additional measures of densely collected speech samples may reveal subtle atypicalities that are missed when relying on only few typical measures of acquisition.

Autism Behavior Inventory: A Novel Tool for Assessing Core and Associated Symptoms of Autism Spectrum Disorder

OBJECTIVE

Autism Behavior Inventory (ABI) is a new measure for assessing changes in core and associated symptoms of autism spectrum disorder (ASD) in participants (ages: 3 years-adulthood) diagnosed with ASD. It is a web-based tool with five domains (two ASD core domains: social communication, restrictive and repetitive behaviors; three associated domains: mental health, self-regulation, and challenging behavior). This study describes design, development, and initial psychometric properties of the ABI.

METHODS

ABI items were generated following review of existing measures and inputs from expert clinicians. Initial ABI scale contained 161 items that were reduced to fit a factor analytic model, retaining items of adequate reliability. Two versions of the scale, ABI-full (ABI-F; 93 items) and ABI-short version (ABI-S; 36 items), were developed and evaluated for psychometric properties, including validity comparisons with commonly used measures. Both scales were administered to parents and healthcare professionals (HCPs) involved with study participants.

RESULTS

Test-retest reliability (intraclass correlation coefficient [ICC] = 0.79) for parent ratings on ABI was robust and compared favorably to existing scales. Test-retest correlations for HCP ratings were generally lower versus parent ratings. ABI core domains and comparison measures strongly correlated (r ≥ 0.70), demonstrating good concurrent validity.

CONCLUSIONS

Overall, ABI demonstrates promise as a tool for measuring change in core symptoms of autism in ASD clinical studies, with further validation required.

Simple, Transparent, and Flexible Automated Quality Assessment Procedures for Ambulatory Electrodermal Activity Data

OBJECTIVE

Electrodermal activity (EDA) is a noninvasive measure of sympathetic activation often used to study emotions, decision making, and health. The use of "ambulatory" EDA in everyday life presents novel challenges-frequent artifacts and long recordings-with inconsistent methods available for efficiently and accurately assessing data quality. We developed and validated a simple, transparent, flexible, and automated quality assessment procedure for ambulatory EDA data.

METHODS

A total of 20 individuals with autism (5 females, 5-13 years) provided a combined 181 h of EDA data in their home using the Affectiva Q Sensor across 8 weeks. Our procedure identified invalid data using four rules: First, EDA out of range; second, EDA changes too quickly; third, temperature suggests the sensor is not being worn; and fourth, transitional data surrounding segments identified as invalid via the preceding rules. We identified invalid portions of a pseudorandom subset of our data (32.8 h, 18%) using our automated procedure and independent visual inspection by five EDA experts.

RESULTS

Our automated procedure identified 420 min (21%) of invalid data. The five experts agreed strongly with each other (agreement: 98%, Cohen's κ: 0.87) and, thus, were averaged into a "consensus" rating. Our procedure exhibited excellent agreement with the consensus rating (sensitivity: 91%, specificity: 99%, accuracy: 92%, κ: 0.739 [95% CI = 0.738, 0.740]).

CONCLUSION

We developed a simple, transparent, flexible, and automated quality assessment procedure for ambulatory EDA data.

SIGNIFICANCE

Our procedure can be used beyond this study to enhance efficiency, transparency, and reproducibility of EDA analyses, with free software available at http://www.cbslab.org/EDAQA.

JAKE® Multimodal Data Capture System: Insights from an Observational Study of Autism Spectrum Disorder

Objective: To test usability and optimize the Janssen Autism Knowledge Engine (JAKE®) system's components, biosensors, and procedures used for objective measurement of core and associated symptoms of autism spectrum disorder (ASD) in clinical trials.

Methods: A prospective, observational study of 29 children and adolescents with ASD using the JAKE system was conducted at three sites in the United States. This study was designed to establish the feasibility of the JAKE system and to learn practical aspects of its implementation. In addition to information collected by web and mobile components, wearable biosensor data were collected both continuously in natural settings and periodically during a battery of experimental tasks administered in laboratory settings. This study is registered at clinicaltrials.gov, NCT02299700.

Results: Feedback collected throughout the study allowed future refinements to be planned for all components of the system. The Autism Behavior Inventory (ABI), a parent-reported measure of ASD core and associated symptoms, performed well. Among biosensors studied, the eye-tracker, sleep monitor, and electrocardiogram were shown to capture high quality data, whereas wireless electroencephalography was difficult to use due to its form factor. On an exit survey, the majority of parents rated their overall reaction to JAKE as positive/very positive. No significant device-related events were reported in the study.

Conclusion: The results of this study, with the described changes, demonstrate that the JAKE system is a viable, useful, and safe platform for use in clinical trials of ASD, justifying larger validation and deployment studies of the optimized system.

The relationship between autism symptoms and arousal level in toddlers with autism spectrum disorder, as measured by electrodermal activity

Electrodermal activity was examined as a measure of physiological arousal within a naturalistic play context in 2-year-old toddlers ( N = 27) with and without autism spectrum disorder. Toddlers with autism spectrum disorder were found to have greater increases in skin conductance level than their typical peers in response to administered play activities. In the autism spectrum disorder group, a positive relationship was observed between restrictive and repetitive behaviors and skin conductance level increases in response to mechanical toys, whereas the opposite pattern was observed for passive toys. This preliminary study is the first to examine electrodermal activity levels in toddlers with autism spectrum disorder during play-based, naturalistic settings, and it highlights the potential for electrodermal activity as a measure of individual variability within autism spectrum disorder and early development.

Automated Detection of Stereotypical Motor Movements in Autism Spectrum Disorder Using Recurrence Quantification Analysis

A number of recent studies using accelerometer features as input to machine learning classifiers show promising results for automatically detecting stereotypical motor movements (SMM) in individuals with Autism Spectrum Disorder (ASD). However, replicating these results across different types of accelerometers and their position on the body still remains a challenge. We introduce a new set of features in this domain based on recurrence plot and quantification analyses that are orientation invariant and able to capture non-linear dynamics of SMM. Applying these features to an existing published data set containing acceleration data, we achieve up to 9% average increase in accuracy compared to current state-of-the-art published results. Furthermore, we provide evidence that a single torso sensor can automatically detect multiple types of SMM in ASD, and that our approach allows recognition of SMM with high accuracy in individuals when using a person-independent classifier.

A systematic review of physiological reactivity to stimuli in autism

OBJECTIVE

The prevalence of abnormal behavioural responses to a variety of stimuli among individuals with autism has led researchers to examine whether physiological reactivity (PR) is typical in this population. This article reviewed studies assessing PR to sensory, social and emotional, and stressor stimuli in individuals with autism.

METHODS

Systematic searches of electronic databases identified 57 studies that met our inclusion criteria. Studies were analysed to determine: (a) participant characteristics; (b) physiological measures used; (c) PR to sensory, social and emotional or stressor stimuli; (d) the relation between PR and behavioural or psychological variables and (e) baseline physiological activity. A novel measure of methodological quality suitable for use with non-randomized, non-interventional, psychophysiological studies was also developed and applied.

RESULTS

Individuals with autism were found to respond differently than typically developing controls in 78.6%, 66.7% and 71.4% of sensory, social and emotional, and stressor stimulus classes, respectively. However, this extant literature is characterized by variable and inconsistent findings, which do not appear to be accounted for by varying methodological quality, making it difficult to determine what specific factors differentiate individuals with autism who present with atypical PR from those who do not.

CONCLUSIONS

Despite this uncertainty, individual differences in PR are clearly present in autism, suggesting additional research is needed to determine the variables relating to PR among those with ASD and to examine the possible existence of physiological subtype responders in the population.

Use of machine learning to improve autism screening and diagnostic instruments: effectiveness, efficiency, and multi-instrument fusion

BACKGROUND

Machine learning (ML) provides novel opportunities for human behavior research and clinical translation, yet its application can have noted pitfalls (Bone et al., 2015). In this work, we fastidiously utilize ML to derive autism spectrum disorder (ASD) instrument algorithms in an attempt to improve upon widely used ASD screening and diagnostic tools.

METHODS

The data consisted of Autism Diagnostic Interview-Revised (ADI-R) and Social Responsiveness Scale (SRS) scores for 1,264 verbal individuals with ASD and 462 verbal individuals with non-ASD developmental or psychiatric disorders, split at age 10. Algorithms were created via a robust ML classifier, support vector machine, while targeting best-estimate clinical diagnosis of ASD versus non-ASD. Parameter settings were tuned in multiple levels of cross-validation.

RESULTS

The created algorithms were more effective (higher performing) than the current algorithms, were tunable (sensitivity and specificity can be differentially weighted), and were more efficient (achieving near-peak performance with five or fewer codes). Results from ML-based fusion of ADI-R and SRS are reported. We present a screener algorithm for below (above) age 10 that reached 89.2% (86.7%) sensitivity and 59.0% (53.4%) specificity with only five behavioral codes.

CONCLUSIONS

ML is useful for creating robust, customizable instrument algorithms. In a unique dataset comprised of controls with other difficulties, our findings highlight the limitations of current caregiver-report instruments and indicate possible avenues for improving ASD screening and diagnostic tools.

Interpersonal Autonomic Physiology: A Systematic Review of the Literature

Interpersonal autonomic physiology is defined as the relationship between people’s physiological dynamics, as indexed by continuous measures of the autonomic nervous system. Findings from this field of study indicate that physiological activity between two or more people can become associated or interdependent, often referred to as physiological synchrony. Physiological synchrony has been found in both new and established relationships across a range of contexts, and it correlates with a number of psychosocial constructs. Given these findings, interpersonal physiological interactions are theorized to be ubiquitous social processes that co-occur with observable behavior. However, this scientific literature is fragmented, making it difficult to evaluate consistency across reports. In an effort to facilitate more standardized scholarly approaches, this systematic review provides a description of existing work in the area and highlights theoretical, methodological, and statistical issues to be addressed in future interpersonal autonomic physiology research.

Applying machine learning to facilitate autism diagnostics: pitfalls and promises

Machine learning has immense potential to enhance diagnostic and intervention research in the behavioral sciences, and may be especially useful in investigations involving the highly prevalent and heterogeneous syndrome of autism spectrum disorder. However, use of machine learning in the absence of clinical domain expertise can be tenuous and lead to misinformed conclusions. To illustrate this concern, the current paper critically evaluates and attempts to reproduce results from two studies (Wall et al. in Transl Psychiatry 2(4):e100, 2012a; PloS One 7(8), 2012b) that claim to drastically reduce time to diagnose autism using machine learning. Our failure to generate comparable findings to those reported by Wall and colleagues using larger and more balanced data underscores several conceptual and methodological problems associated with these studies. We conclude with proposed best-practices when using machine learning in autism research, and highlight some especially promising areas for collaborative work at the intersection of computational and behavioral science.

Automated Assessment of Children's Postoperative Pain Using Computer Vision

BACKGROUND

Current pain assessment methods in youth are suboptimal and vulnerable to bias and underrecognition of clinical pain. Facial expressions are a sensitive, specific biomarker of the presence and severity of pain, and computer vision (CV) and machine-learning (ML) techniques enable reliable, valid measurement of pain-related facial expressions from video. We developed and evaluated a CVML approach to measure pain-related facial expressions for automated pain assessment in youth.

METHODS

A CVML-based model for assessment of pediatric postoperative pain was developed from videos of 50 neurotypical youth 5 to 18 years old in both endogenous/ongoing and exogenous/transient pain conditions after laparoscopic appendectomy. Model accuracy was assessed for self-reported pain ratings in children and time since surgery, and compared with by-proxy parent and nurse estimates of observed pain in youth.

RESULTS

Model detection of pain versus no-pain demonstrated good-to-excellent accuracy (Area under the receiver operating characteristic curve 0.84-0.94) in both ongoing and transient pain conditions. Model detection of pain severity demonstrated moderate-to-strong correlations (r = 0.65-0.86 within; r = 0.47-0.61 across subjects) for both pain conditions. The model performed equivalently to nurses but not as well as parents in detecting pain versus no-pain conditions, but performed equivalently to parents in estimating pain severity. Nurses were more likely than the model to underestimate youth self-reported pain ratings. Demographic factors did not affect model performance.

CONCLUSIONS

CVML pain assessment models derived from automatic facial expression measurements demonstrated good-to-excellent accuracy in binary pain classifications, strong correlations with patient self-reported pain ratings, and parent-equivalent estimation of children's pain levels over typical pain trajectories in youth after appendectomy.

Harnessing repetitive behaviours to engage attention and learning in a novel therapy for autism: an exploratory analysis

Rigorous, quantitative examination of therapeutic techniques anecdotally reported to have been successful in people with autism who lack communicative speech will help guide basic science toward a more complete characterisation of the cognitive profile in this underserved subpopulation, and show the extent to which theories and results developed with the high-functioning subpopulation may apply. This study examines a novel therapy, the “Rapid Prompting Method” (RPM). RPM is a parent-developed communicative and educational therapy for persons with autism who do not speak or who have difficulty using speech communicatively. The technique aims to develop a means of interactive learning by pointing amongst multiple-choice options presented at different locations in space, with the aid of sensory “prompts” which evoke a response without cueing any specific response option. The prompts are meant to draw and to maintain attention to the communicative task – making the communicative and educational content coincident with the most physically salient, attention-capturing stimulus – and to extinguish the sensory–motor preoccupations with which the prompts compete. Video-recorded RPM sessions with nine autistic children ages 8–14 years who lacked functional communicative speech were coded for behaviours of interest. An analysis controlled for age indicates that exposure to the claimed therapy appears to support a decrease in repetitive behaviours and an increase in the number of multiple-choice response options without any decrease in successful responding. Direct gaze is not related to successful responding, suggesting that direct gaze might not be any advantage for this population and need not in all cases be a precondition to communication therapies.

Automated detection of stereotypical motor movements

To overcome problems with traditional methods for measuring stereotypical motor movements in persons with Autism Spectrum Disorders (ASD), we evaluated the use of wireless three-axis accelerometers and pattern recognition algorithms to automatically detect body rocking and hand flapping in children with ASD. Findings revealed that, on average, pattern recognition algorithms correctly identified approximately 90% of stereotypical motor movements repeatedly observed in both laboratory and classroom settings. Precise and efficient recording of stereotypical motor movements could enable researchers and clinicians to systematically study what functional relations exist between these behaviors and specific antecedents and consequences. These measures could also facilitate efficacy studies of behavioral and pharmacologic interventions intended to replace or decrease the incidence or severity of stereotypical motor movements.

Maternal smoking during pregnancy and neonatal behavior: a large-scale community study

OBJECTIVE

To investigate the influence of prospectively measured smoking during pregnancy on aspects of neonatal behavior in a large community sample.

METHODS

Participants were mothers and infants from the Providence, Rhode Island, cohort of the National Collaborative Perinatal Project enrolled between 1960 and 1966. Mothers with pregnancy/medical complications and infants with medical complications and/or born premature or of low birth weight were excluded. The final sample included 962 mother-infant pairs, 23% of whom were black. Maternal smoking was measured prospectively at each prenatal visit. Neonatal behavior was assessed by using the Graham-Rosenblith Behavioral Examination of the Neonate. Items from the examination were reduced to 3 subscales: irritability, muscle tone, and response to respiratory challenge.

RESULTS

Sixty-two percent of the sample reported smoking during pregnancy, with 24% of smokers reporting smoking 1 pack per day or more. We found a significant influence of maternal smoking exposure (none, moderate/less than 1 pack per day, heavy/1 pack per day or more) on irritability and muscle tone in the neonate, with exposed infants showing greater irritability and hypertonicity. Effects remained significant after controlling for significant covariates: maternal socioeconomic status, age, and race and infant birth weight and age. Posthoc tests suggested particular effects of heavy smoking on increased infant irritability and both moderate and heavy smoking exposure on increased muscle tone.

CONCLUSIONS

In a large community sample, exposure to maternal smoking was associated with increased irritability and hypertonicity in neonates. Exposure to maternal smoking did not influence neonatal response to respiratory challenge. This study is the largest-scale investigation to date of the effects of maternal smoking (heavy and moderate) on examiner-assessed neonatal behavior. Given the associations between both maternal smoking and infant irritability and later behavioral dysregulation, results have important implications for early identification and intervention with at-risk offspring.

Time series analysis of treatment adherence patterns in individuals with obstructive sleep apnea

BACKGROUND

Adherence to medical recommendations is often suboptimal, making examination of adherence data an important scientific concern. Studies that attempt to predict or modify adherence often face the problem that adherence as a dependent variable is complex and non-normally distributed. Traditional statistical approaches to adherence data may mask individual variability that may guide clinician and researcher's development of adherence interventions. In this study, we employ time series analysis to examine adherence patterns objectively in patients with obstructive sleep apnea (OSA). Although treatment adherence is poor in OSA, state-of-the-art adherence monitoring allows a comprehensive examination of objective data.

PURPOSE

The purpose of the study is to determine the number and types of adherence patterns seen in a sample of patients with OSA receiving positive airway pressure (PAP).

METHODS

Seventy-one moderate to severe OSA participants with 365 days of treatment data were studied.

RESULTS

Adherence patterns could be classified into seven categories: (1) Good Users (24%), (2) Slow Improvers (13%), (3) Slow Decliners (14%), (4) Variable Users (17%), (5) Occasional Attempters (8%), (6) Early Drop-outs (13%), and (7) Non-Users (11%).

CONCLUSIONS

Time series analysis provides a useful method for examining adherence while maintaining a focus on individual differences. Implications for future research are discussed.

Detecting longitudinal patterns of daily smoking following drastic cigarette reduction

To enhance prolonged smoking cessation or reduction, a better understanding of the process of change is needed. This study examines daily smoking rates following the end of an intensive smoking reduction program originally designed to evaluate the relationship of tobacco biomarkers with reduced levels of smoking. A novel pattern-oriented approach called time series-based typology is used to detect homogeneous smoking patterns in time-intensively (i.e., 40 occasions) observed smokers (n=57), who were predominantly Caucasian (94.7%), male (52.6%), and on average 47.9 years old (SD=11.3). The majority of the smokers exhibited a change in their daily smoking behavior over the course of 40 days with 47.4% increasing and 40.4% decreasing the number of cigarettes smoked per day, which is contrary to the results a group level approach would have found. Very few smokers (12.3%) maintained their average smoking rate, and exhibited an externally controlled smoking pattern. Trajectory type could be predicted by temporally proximal motivation and self-efficacy variables ((F(4, 106)=3.46, p=.011, eta2=.115), underscoring their importance in maintaining reduced smoking rates. Time series-based typology demonstrated good sensitivity to the identification of meaningfully different trajectories.