Autism Spectrum Disorder
Conditions
Keywords
mobile health, autism, ASD, mobile therapy, digital, wearable computing, technology
Brief summary
The purpose of this research is to study the effects of a novel artificial intelligence (AI) tool for automatic facial expression recognition that runs on Google Glass through an Android app to deliver social emotion cues to children with autism during social interactions. This novel device will use a camera, microphone, head motion tracker to analyze the behavior of the subject during interactions with other people. The system is designed to give participants non-interruptive social cues in real-time and will record social responses that can later be used to help aid behavioral therapy. It is hypothesized that the system's ability to provide continuous behavioral therapy during social interactions will enable faster gains in social skills.
Interventions
DEVICEAutism Glass
The intervention uses the outward-facing camera on the google glasses to read facial expressions and provides social cues within the child's natural environment during usual social interaction and during games accessed via the smartphone application. Participants who receive the Google Glass intervention will be asked to use it for around 20 minutes 3 times a week with their parents or during ABA therapy.
Sponsors
Dennis Paul Wall
Study design
Allocation
RANDOMIZED
Intervention model
CROSSOVER
Primary purpose
TREATMENT
Masking
DOUBLE (Investigator, Outcomes Assessor)
Eligibility
Sex/Gender
ALL
Age
6 Years to 12 Years
Healthy volunteers
No
Inclusion criteria
1. the child has been diagnosed professionally with ASD 2. the child is currently receiving ABA therapy at least twice per week at home. 3. The child's family is willing to drive to Stanford University for up to 4 study appointments.
Exclusion criteria
1. The child scores less than 15 on the Social Communication Questionnaire 2. The child's family does not speak English
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Change in Socialization Subscale Scores of the Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) From Baseline to Week 6. | Baseline (week 0), Week 6 | Vineland Adaptive Behavior Scales, 2nd edition (VABS-II) Socialization subscale will be conducted at the university by a trained research team member. Scores from the socialization domain of the VABS-II reflects one's functioning in social situations. The socialization subscale is 32 items, where raw scores are converted to IQ-type standard scores (mean: 100 sd: 15) for each domain and for the composite adaptive behavior score.The socialization subscale is 32 items, where raw scores are converted to IQ-type standard scores--v-scale scores (M=15, SD=3) where scores range from 1 to 24, and factor in age equivalents, growth scale values, and higher scores indicate better adaptive functioning. |
| Change in Parent Rated Social Responsiveness Scale 2 (SRS-2) From Baseline to Week 6 | Baseline (week 0), Week 6 | The SRS-2 is a 65-item measure where parents rate their child selecting responses on a Likert Scale. This measure will be used to measure and identify social impairment associated with Autism Spectrum Disorder (ASD) and to quantify its severity. Social Responsiveness Scale (SRS) raw scores measure social abilities with lower scores indicating better social skills. (Raw Score Range: 0 - 195 and T-Score Range: 37- above 90). |
| Change in Emotion Guessing Game (EGG) Scores From Baseline to Week 6 | Baseline (week 0), Week 6 | The Emotion Guessing Game is a novel test created for purposes of this study to evaluate the child's ability to correctly label emotions expressed by an examiner in real time. EGG is a pre-set list of 8 emotions, listed 5 times each (Happy, Sad, Angry, Afraid, Surprised, Calm, Disgust, and Meh/contempt). During the quick 40-question evaluation, the research coordinator first lists the various emotion choices to the child before beginning the evaluation. Then, the examiner acts out each emotion listed, in order, and waits for a guess from the child, who labels the emotion. The EGG is scored by summing the number of correct responses from the child, higher scores indicated better emotion recognition, where scores can range from 0 to 40. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Change in ASD Symptoms as Measured by Brief Observation of Social Communication Change (BOSCC) From Baseline to Week 6 | Baseline (week 0), week 6 | The Brief Observation of Social Communication Change (BOSCC) is designed to measure change in core symptoms of children with autism. It aims to capture change in social communication, interaction, and eye contact. The BOSCC is a play based assessment that consists of two boxes filled with specific toys and takes about 12 minutes to complete. |
| Change in NEPSY-II, Affect Recognition Subscale Scores From Baseline to Week 6 | Baseline (week 0), Week 6 Baseline (week 0), Week 6 Baseline (week 0), Week 6 Baseline (week 0), week 6 | The NEPSY-II Affect Recognition subdomain assesses a child's social perception of facial affect recognition. It is designed to assess a child's ability to recognize 6 emotions (happy, sad, angry, fear, disgust, and neutral) from colored photographs of children's faces in four different tasks. Scores range from 1 (well below expected level) to 19 (well above expected level), and have a mean of 10 \[standard deviation= 3\] that is based on a U.S. normative sample. |
| Change in Adaptive Social and Personal Skills as Measured by Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) Full Scale From Baseline to Week 6. | Baseline (week 0), week 6 | The VABS-II is a robust and comprehensive measure of personal and social skills needed in everyday living. The VABS-II covers a child's conceptual, social, and practical skills and can assess children from birth to 90 years. The parent can complete the entire questionnaire in about 20-30 minutes. The raw score in each domain and total raw score are converted to an age-equivalent score. The domain scores are also expressed as standard scores with a mean of 100 and standard deviation of 15. The range for each subscale is from 20 to 140. The subscales are summed to compute a total score, ranging from 80 to 560. The higher the scores are, the better adaptive functioning the children achieve. |
| Change in Child's Emotional, Behavioral, and Social Problems From Baseline (Week 0) to Week 6 as Measured by Child Behavior Checklist (CBCL) Total Score. | Baseline (week 0), Week 6 | The CBCL is a caregiver-directed report that identifies emotional, behavioral, and social problems in children. The patient is rated on 113 items scored on a 3-point Likert-type scale. CBCL total score consists of eight empirically-based syndrome subscales. The total competence score is reported, range: 0-100, where higher scores suggests the more severe symptoms. |
Participant flow
Pre-assignment details
N=3 participants were excluded due to a randomization error.
Participants by arm
| Arm | Count |
|---|---|
| Autism Glass Intervention Participants in the experimental group will receive the autism glass for 6 weeks once they are assigned to the experimental condition. Participants will be asked to use the glasses at least 3 times a week for 20 minutes sessions in addition to continuing Applied Behavior Analysis (ABA) therapy.
Autism Glass: The intervention uses the outward-facing camera on the google glasses to read facial expressions and provides social cues within the child's natural environment during usual social interaction and during games accessed via the smartphone application. Participants who receive the Google Glass intervention will be asked to use it for around 20 minutes 3 times a week with their parents or during ABA therapy. | 40 |
| Crossover Control for Autism Glass Participants randomized to the control arm, will continue treatment as usual (receiving ABA twice a week) while the intervention participants will receive the Autism Glass intervention (while continuing to receive ABA therapy). After 6 weeks, control participants will receive the Autism Glass intervention after which, they will be asked to come in for a second round of follow-up testing following 6 weeks of use (at week 18).
Autism Glass: The intervention uses the outward-facing camera on the google glasses to read facial expressions and provides social cues within the child's natural environment during usual social interaction and during games accessed via the smartphone application. Participants who receive the Google Glass intervention will be asked to use it for around 20 minutes 3 times a week with their parents or during ABA therapy. | 31 |
| Total | 71 |
Baseline characteristics
| Characteristic | Autism Glass Intervention | Crossover Control for Autism Glass | Total |
|---|---|---|---|
| Age, Continuous | 8.64 years STANDARD_DEVIATION 2.52 | 7.94 years STANDARD_DEVIATION 1.69 | 8.38 years STANDARD_DEVIATION 2.46 |
| Mobilized Machine Learning Autism Risk Assessment (MARA) score of autism severity | -5.57 units on a scale STANDARD_DEVIATION 4.08 | -4.33 units on a scale STANDARD_DEVIATION 4.37 | -5.02 units on a scale STANDARD_DEVIATION 4.22 |
| Race/Ethnicity, Customized Race and Ethnicity African American | 1 Participants | 0 Participants | 1 Participants |
| Race/Ethnicity, Customized Race and Ethnicity Caucasian or Euro-American | 12 Participants | 10 Participants | 22 Participants |
| Race/Ethnicity, Customized Race and Ethnicity East Asian or Asian American | 9 Participants | 4 Participants | 13 Participants |
| Race/Ethnicity, Customized Race and Ethnicity Hispanic/Latino/Spanish Origin | 7 Participants | 5 Participants | 12 Participants |
| Race/Ethnicity, Customized Race and Ethnicity Middle Eastern or Arab American | 0 Participants | 0 Participants | 0 Participants |
| Race/Ethnicity, Customized Race and Ethnicity More than one race selected | 2 Participants | 6 Participants | 8 Participants |
| Race/Ethnicity, Customized Race and Ethnicity Native American or Alaskan Native | 0 Participants | 0 Participants | 0 Participants |
| Race/Ethnicity, Customized Race and Ethnicity South Asian or Indian American | 1 Participants | 4 Participants | 5 Participants |
| Race/Ethnicity, Customized Race and Ethnicity Unknown/Not Listed | 8 Participants | 2 Participants | 10 Participants |
| Sex: Female, Male Female | 3 Participants | 5 Participants | 8 Participants |
| Sex: Female, Male Male | 37 Participants | 26 Participants | 63 Participants |
| Social Communication Questionnaire (SCQ) score | 23.43 points STANDARD_DEVIATION 5.13 | 25.06 points STANDARD_DEVIATION 4.81 | 24.14 points STANDARD_DEVIATION 5.03 |
| Stanford-Binet Intelligence Scales, Abbreviated Battery, Fifth Edition (ABIQ) | 75.7 points STANDARD_DEVIATION 20.71 | 80.42 points STANDARD_DEVIATION 22.61 | 77.76 points STANDARD_DEVIATION 21.53 |
Adverse events
| Event type | EG000 affected / at risk | EG001 affected / at risk |
|---|---|---|
| deaths Total, all-cause mortality | 0 / 40 | 0 / 31 |
| other Total, other adverse events | 0 / 40 | 0 / 31 |
| serious Total, serious adverse events | 0 / 40 | 0 / 31 |
Outcome results
Primary
Change in Emotion Guessing Game (EGG) Scores From Baseline to Week 6
The Emotion Guessing Game is a novel test created for purposes of this study to evaluate the child's ability to correctly label emotions expressed by an examiner in real time. EGG is a pre-set list of 8 emotions, listed 5 times each (Happy, Sad, Angry, Afraid, Surprised, Calm, Disgust, and Meh/contempt). During the quick 40-question evaluation, the research coordinator first lists the various emotion choices to the child before beginning the evaluation. Then, the examiner acts out each emotion listed, in order, and waits for a guess from the child, who labels the emotion. The EGG is scored by summing the number of correct responses from the child, higher scores indicated better emotion recognition, where scores can range from 0 to 40.
Time frame: Baseline (week 0), Week 6
Population: Averages at baseline are averages from the original N=40 intervention cohort and N=31 crossover control cohort.
| Arm | Measure | Group | Value (MEAN) | Dispersion |
|---|---|---|---|---|
| Autism Glass Intervention | Change in Emotion Guessing Game (EGG) Scores From Baseline to Week 6 | Baseline (week 0) | 22.80 score on a scale | Standard Deviation 11.52 |
| Autism Glass Intervention | Change in Emotion Guessing Game (EGG) Scores From Baseline to Week 6 | Post-Test 1 (week 6) | 30.03 score on a scale | Standard Deviation 9.44 |
| Crossover Control for Autism Glass | Change in Emotion Guessing Game (EGG) Scores From Baseline to Week 6 | Baseline (week 0) | 24.74 score on a scale | Standard Deviation 11.66 |
| Crossover Control for Autism Glass | Change in Emotion Guessing Game (EGG) Scores From Baseline to Week 6 | Post-Test 1 (week 6) | 26.88 score on a scale | Standard Deviation 11.44 |
Primary
Change in Parent Rated Social Responsiveness Scale 2 (SRS-2) From Baseline to Week 6
The SRS-2 is a 65-item measure where parents rate their child selecting responses on a Likert Scale. This measure will be used to measure and identify social impairment associated with Autism Spectrum Disorder (ASD) and to quantify its severity. Social Responsiveness Scale (SRS) raw scores measure social abilities with lower scores indicating better social skills. (Raw Score Range: 0 - 195 and T-Score Range: 37- above 90).
Time frame: Baseline (week 0), Week 6
Population: Averages at baseline are averages from the original N=40 intervention cohort and N=31 crossover control cohort.
| Arm | Measure | Group | Value (MEAN) | Dispersion |
|---|---|---|---|---|
| Autism Glass Intervention | Change in Parent Rated Social Responsiveness Scale 2 (SRS-2) From Baseline to Week 6 | Post-Test 1 (week 6) | 78.4 score on a scale | Standard Deviation 8.65 |
| Autism Glass Intervention | Change in Parent Rated Social Responsiveness Scale 2 (SRS-2) From Baseline to Week 6 | Baseline (week 0) | 80.68 score on a scale | Standard Deviation 8.41 |
| Crossover Control for Autism Glass | Change in Parent Rated Social Responsiveness Scale 2 (SRS-2) From Baseline to Week 6 | Baseline (week 0) | 80.76 score on a scale | Standard Deviation 10.98 |
| Crossover Control for Autism Glass | Change in Parent Rated Social Responsiveness Scale 2 (SRS-2) From Baseline to Week 6 | Post-Test 1 (week 6) | 81.79 score on a scale | Standard Deviation 8.38 |
Primary
Change in Socialization Subscale Scores of the Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) From Baseline to Week 6.
Vineland Adaptive Behavior Scales, 2nd edition (VABS-II) Socialization subscale will be conducted at the university by a trained research team member. Scores from the socialization domain of the VABS-II reflects one's functioning in social situations. The socialization subscale is 32 items, where raw scores are converted to IQ-type standard scores (mean: 100 sd: 15) for each domain and for the composite adaptive behavior score.The socialization subscale is 32 items, where raw scores are converted to IQ-type standard scores--v-scale scores (M=15, SD=3) where scores range from 1 to 24, and factor in age equivalents, growth scale values, and higher scores indicate better adaptive functioning.
Time frame: Baseline (week 0), Week 6
Population: Averages at baseline are averages from the original N=40 intervention cohort and N=31 crossover control cohort.
| Arm | Measure | Group | Value (MEAN) | Dispersion |
|---|---|---|---|---|
| Autism Glass Intervention | Change in Socialization Subscale Scores of the Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) From Baseline to Week 6. | Baseline (week 0) | 68.75 score on a scale | Standard Deviation 16.63 |
| Autism Glass Intervention | Change in Socialization Subscale Scores of the Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) From Baseline to Week 6. | Post-Test 1 (week 6) | 71.72 score on a scale | Standard Deviation 15.24 |
| Crossover Control for Autism Glass | Change in Socialization Subscale Scores of the Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) From Baseline to Week 6. | Baseline (week 0) | 70.40 score on a scale | Standard Deviation 13.26 |
| Crossover Control for Autism Glass | Change in Socialization Subscale Scores of the Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) From Baseline to Week 6. | Post-Test 1 (week 6) | 68.6 score on a scale | Standard Deviation 10.8 |
Secondary
Change in Adaptive Social and Personal Skills as Measured by Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) Full Scale From Baseline to Week 6.
The VABS-II is a robust and comprehensive measure of personal and social skills needed in everyday living. The VABS-II covers a child's conceptual, social, and practical skills and can assess children from birth to 90 years. The parent can complete the entire questionnaire in about 20-30 minutes. The raw score in each domain and total raw score are converted to an age-equivalent score. The domain scores are also expressed as standard scores with a mean of 100 and standard deviation of 15. The range for each subscale is from 20 to 140. The subscales are summed to compute a total score, ranging from 80 to 560. The higher the scores are, the better adaptive functioning the children achieve.
Time frame: Baseline (week 0), week 6
| Arm | Measure | Group | Value (MEAN) | Dispersion |
|---|---|---|---|---|
| Autism Glass Intervention | Change in Adaptive Social and Personal Skills as Measured by Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) Full Scale From Baseline to Week 6. | Baseline (week 0) | 71.45 score on a scale | Standard Deviation 12.66 |
| Autism Glass Intervention | Change in Adaptive Social and Personal Skills as Measured by Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) Full Scale From Baseline to Week 6. | Post-Test 1 (week 6) | 72.29 score on a scale | Standard Deviation 15.46 |
| Crossover Control for Autism Glass | Change in Adaptive Social and Personal Skills as Measured by Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) Full Scale From Baseline to Week 6. | Baseline (week 0) | 74.63 score on a scale | Standard Deviation 10.48 |
| Crossover Control for Autism Glass | Change in Adaptive Social and Personal Skills as Measured by Vineland Adaptive Behavior Scales, 2nd Edition (VABS-II) Full Scale From Baseline to Week 6. | Post-Test 1 (week 6) | 74.48 score on a scale | Standard Deviation 9.79 |
Secondary
Change in ASD Symptoms as Measured by Brief Observation of Social Communication Change (BOSCC) From Baseline to Week 6
The Brief Observation of Social Communication Change (BOSCC) is designed to measure change in core symptoms of children with autism. It aims to capture change in social communication, interaction, and eye contact. The BOSCC is a play based assessment that consists of two boxes filled with specific toys and takes about 12 minutes to complete.
Time frame: Baseline (week 0), week 6
Population: While the framework for administration of BOSCC has been published, the scoring algorithm and validation of use in independent replicate samples has not yet been published. Therefore, we were unable to use the BOSCC as initially planned.
Secondary
Change in Child's Emotional, Behavioral, and Social Problems From Baseline (Week 0) to Week 6 as Measured by Child Behavior Checklist (CBCL) Total Score.
The CBCL is a caregiver-directed report that identifies emotional, behavioral, and social problems in children. The patient is rated on 113 items scored on a 3-point Likert-type scale. CBCL total score consists of eight empirically-based syndrome subscales. The total competence score is reported, range: 0-100, where higher scores suggests the more severe symptoms.
Time frame: Baseline (week 0), Week 6
Population: CBCL Total Score Averages at baseline are averages from the original N=40 intervention cohort and N=31 crossover control cohort.
| Arm | Measure | Group | Value (MEAN) | Dispersion |
|---|---|---|---|---|
| Autism Glass Intervention | Change in Child's Emotional, Behavioral, and Social Problems From Baseline (Week 0) to Week 6 as Measured by Child Behavior Checklist (CBCL) Total Score. | Baseline (week 0) | 65.95 score on a scale | Standard Deviation 7.16 |
| Autism Glass Intervention | Change in Child's Emotional, Behavioral, and Social Problems From Baseline (Week 0) to Week 6 as Measured by Child Behavior Checklist (CBCL) Total Score. | Post-Test 1 (week 6) | 63.77 score on a scale | Standard Deviation 6.84 |
| Crossover Control for Autism Glass | Change in Child's Emotional, Behavioral, and Social Problems From Baseline (Week 0) to Week 6 as Measured by Child Behavior Checklist (CBCL) Total Score. | Baseline (week 0) | 69.04 score on a scale | Standard Deviation 7.39 |
| Crossover Control for Autism Glass | Change in Child's Emotional, Behavioral, and Social Problems From Baseline (Week 0) to Week 6 as Measured by Child Behavior Checklist (CBCL) Total Score. | Post-Test 1 (week 6) | 65.55 score on a scale | Standard Deviation 8.94 |
Secondary
Change in NEPSY-II, Affect Recognition Subscale Scores From Baseline to Week 6
The NEPSY-II Affect Recognition subdomain assesses a child's social perception of facial affect recognition. It is designed to assess a child's ability to recognize 6 emotions (happy, sad, angry, fear, disgust, and neutral) from colored photographs of children's faces in four different tasks. Scores range from 1 (well below expected level) to 19 (well above expected level), and have a mean of 10 \[standard deviation= 3\] that is based on a U.S. normative sample.
Time frame: Baseline (week 0), Week 6 Baseline (week 0), Week 6 Baseline (week 0), Week 6 Baseline (week 0), week 6
| Arm | Measure | Value (MEAN) | Dispersion |
|---|---|---|---|
| Autism Glass Intervention | Change in NEPSY-II, Affect Recognition Subscale Scores From Baseline to Week 6 | .099 units on a scale | Standard Deviation 0.57 |
| Crossover Control for Autism Glass | Change in NEPSY-II, Affect Recognition Subscale Scores From Baseline to Week 6 | -.068 units on a scale | Standard Deviation 0.439 |