AI Modules for Improving Social Communication in Autism

Overseen By Monica Lam, PhD

Age: < 65

Sex: Any

Trial Phase: Academic

Sponsor: Stanford University

Disqualifiers: Intellectual impairment, Non English speaking, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 3

Duration: 4 weeks

540 Participants Needed

Trial Summary

Will I have to stop taking my current medications?

The trial does not specify whether you need to stop taking your current medications. Participants with ADHD, depression, or social anxiety are not excluded, suggesting that continuing these medications might be allowed.

What data supports the effectiveness of the treatment AI Modules for Improving Social Communication in Autism?

Research shows that computer-based social skills training, which includes audiovisual features like smiling and head movements, significantly improves social skills in people with autism. Additionally, virtual conversation simulations and social robots have been well-received and show promise in enhancing social communication for individuals with autism. ^{1 2 3 4 5}

Is the AI-based social communication training safe for humans?

The studies reviewed did not report any safety concerns related to the use of AI-based social communication training for individuals with autism spectrum disorders. Participants generally found the systems helpful and engaging, suggesting they are safe for use in humans. ^{1 3 6 7 8}

How is the treatment 'AI Modules for Improving Social Communication in Autism' different from other treatments for autism?

This treatment is unique because it uses AI-powered modules to provide social skills training through interaction with computer avatars, incorporating audiovisual features like smiling and head movements, which traditional human-based training may not fully utilize. It offers a more accessible and cost-effective alternative to human trainers, allowing for consistent and replicable training anytime and anywhere. ^{1 2 4 7 9}

What is the purpose of this trial?

The purpose of this study is to identify whether researched and commonly used face-to-face interventions can be effectively implemented through artificial intelligence (AI) using an application on the phone or computer. The investigators plan to recruit verbal individuals diagnosed with autism spectrum disorder who demonstrate challenges with socialization. Modules focusing on various difficulties experienced by autistic individuals will provide practice and feedback using voice recognition and feedback. If effective, this intervention can be scaled up to provide cost-effective accessible assistance to individuals, particularly those who do not have access to care or prefer to secure services in the comfort of their own homes.

Eligibility Criteria

This trial is for verbal individuals aged 11 to 35 with autism spectrum disorder who struggle with social conversations. Participants must be able to speak in full sentences and have specific communication challenges, like empathy. Those with ADHD, depression, or social anxiety can also join.

Inclusion Criteria

I can talk in full sentences for 20 minutes.

I am between 11 and 35 years old.

I have been diagnosed with autism spectrum disorder.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

1-2 weeks

1 visit (phone/zoom)

Baseline Assessment

Eligibility is confirmed and baseline social conversation samples are collected

1 week

1 visit (phone/zoom)

Treatment

Participants engage in AI-based social communication modules for 4 weeks

4 weeks

Daily practice sessions (remote)

Post Intervention

Post-intervention social conversation samples and surveys are collected

1 week

1 visit (phone/zoom)

Follow-up

Participants are monitored for sustained improvements in social communication

4 weeks

Treatment Details

Interventions

• AI Modules for Improving Social Conversation

Trial Overview The study tests if AI modules on phones or computers can improve social conversation skills in people with ASD. It uses voice recognition and feedback to practice real-life interactions and aims to offer accessible care at home.

Participant Groups

Group I: Intervention Group Experimental Treatment 1 Intervention

This group will receive the treatment (AI conversation modules) available through the application.

Group II: Control Group Active Control 1 Intervention

This waitlist control group will not receive treatment until the experimental group completes their intervention.

Who Is Running the Clinical Trial?

Stanford University

Lead Sponsor

Trials

2,527

Recruited

17,430,000+

Findings from Research

A new social skills training system that incorporates audiovisual features, such as smiling ratio and head pose, was developed and tested on 10 individuals with autism spectrum disorders and 18 from the general population, showing significant improvements in social skills after training.

This computer-based system can effectively supplement traditional human-led social skills training, making it a valuable tool for teachers and therapists to help individuals with social difficulties anytime and anywhere.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Embodied conversational agents for multimodal automated social skills training in people with autism spectrum disorders. Tanaka, H., Negoro, H., Iwasaka, H., et al.[2018]

The CRETA system, a novel collaborative virtual environment with intelligent agents, shows promise for assessing social communication and collaboration skills in individuals with autism spectrum disorder (ASD) with moderate to high accuracy.

This technology provides a replicable and low-cost alternative to traditional human rating methods, potentially improving the generalizability of outcomes in real-world settings for ASD interventions.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Assessing Social Communication and Collaboration in Autism Spectrum Disorder Using Intelligent Collaborative Virtual Environments. Zhang, L., Weitlauf, AS., Amat, AZ., et al.[2021]

A prototype conversation simulation was developed to help adolescents and adults with Autism Spectrum Disorder (ASD) improve their conversational skills, showing promise in engaging users through realistic feedback during virtual interactions.

In a 2-week trial with 16 participants, most reported that the simulation was helpful and endorsed its quality, indicating strong acceptability; however, further controlled studies are needed to assess its effectiveness in enhancing real-world communication skills.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Virtual conversation partner for adults with autism. Trepagnier, CY., Olsen, DE., Boteler, L., et al.[2021]

A new therapeutic platform using a humanoid robot named FACE has been developed to help individuals with Autism Spectrum Disorders (ASD) practice social skills in simulated scenarios, guided by a psychologist.

Preliminary results indicate that this robot-assisted therapy is well accepted by individuals with ASD, suggesting it could be an effective tool for improving their interpersonal relationships and social interactions.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Development and evaluation of a social robot platform for therapy in autism. Mazzei, D., Lazzeri, N., Billeci, L., et al.[2020]

The article emphasizes the importance of assessing social communication (SC) in individuals with autism spectrum disorder (ASD), defining SC as the appropriate use of verbal and nonverbal behaviors during interactions, which is crucial for treatment-sensitive measures in research.

Clinicians currently lack standardized methods to evaluate SC in routine psychiatric assessments, highlighting the need for a clear definition and a conceptual model to differentiate SC from social interaction and language, which are often confused in existing literature.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The Need for a Clinically Useful Schema of Social Communication. Blank, MS., Turner, JB., Fisher, PW., et al.[2021]

An automated speaker diarization algorithm can effectively analyze natural conversations between autistic individuals and their partners, providing a more objective measure of communication skills compared to traditional methods.

The study found a significant correlation (r = 0.51) between the duration of speech during conversations and the Vineland Adaptive Behavior Scales expressive communication score, suggesting that this automated measure can reliably reflect communication challenges in autism spectrum disorder.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Automatic speaker diarization for natural conversation analysis in autism clinical trials. O'Sullivan, J., Bogaarts, G., Schoenenberger, P., et al.[2023]

The study involved three adolescents with autism spectrum disorder (ASD) and three with other cognitive impairments, who played a memory card game using a humanoid robot, a Smart Board, and traditional playing cards over three days.

Participants with ASD exhibited reduced repetitive behaviors when interacting with the robot and Smart Board compared to playing cards, indicating that robotic technology can be a feasible tool for enhancing social skills in adolescents with ASD.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Feasibility of using a humanoid robot for enhancing attention and social skills in adolescents with autism spectrum disorder. Jordan, K., King, M., Hellersteth, S., et al.[2015]

A study involving 238 children (120 with autism spectrum disorder and 118 with other non-ASD conditions) identified a three-factor model of social-communication impairments, distinguishing between 'Basic Social-Communication' behaviors and 'Interaction Quality.'

This separation of social-communication dimensions can improve understanding of autism and related disorders, aiding in diagnosis and treatment by highlighting different types of impairments that may respond differently to interventions.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Subdimensions of social-communication impairment in autism spectrum disorder. Bishop, SL., Havdahl, KA., Huerta, M., et al.[2020]

A 4-week training program using a conversational agent significantly improved social skills in participants, particularly in generalized self-efficacy and reduced state anxiety, with a notable effect size (r=0.53 for self-efficacy).

Participants who received training showed enhanced speech clarity as rated by third-party trainers, indicating that automated social skills training can effectively support communication skills development.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The Validation of Automated Social Skills Training in Members of the General Population Over 4 Weeks: Comparative Study. Tanaka, H., Saga, T., Iwauchi, K., et al.[2023]

References

1. United States pubmed.ncbi.nlm.nih.gov

Embodied conversational agents for multimodal automated social skills training in people with autism spectrum disorders. [2018]

2. United States pubmed.ncbi.nlm.nih.gov

Assessing Social Communication and Collaboration in Autism Spectrum Disorder Using Intelligent Collaborative Virtual Environments. [2021]

3. United States pubmed.ncbi.nlm.nih.gov

Virtual conversation partner for adults with autism. [2021]

4. United States pubmed.ncbi.nlm.nih.gov

Development and evaluation of a social robot platform for therapy in autism. [2020]

5. United States pubmed.ncbi.nlm.nih.gov

The Need for a Clinically Useful Schema of Social Communication. [2021]

6. England pubmed.ncbi.nlm.nih.gov

Automatic speaker diarization for natural conversation analysis in autism clinical trials. [2023]

7. England pubmed.ncbi.nlm.nih.gov

Feasibility of using a humanoid robot for enhancing attention and social skills in adolescents with autism spectrum disorder. [2015]

8. England pubmed.ncbi.nlm.nih.gov

Subdimensions of social-communication impairment in autism spectrum disorder. [2020]

9. Canada pubmed.ncbi.nlm.nih.gov

The Validation of Automated Social Skills Training in Members of the General Population Over 4 Weeks: Comparative Study. [2023]