Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Autism Spectrum Disorder

Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by persistent deficits in social communication and interaction alongside restrictive and repetitive behaviors or interests. ASD is sometimes accompanied by intellectual impairment.
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.

Automatic Processing and Automatic Social Behavior

Automatic Processing and Automatic Social Behavior

Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...

Modeling in Therapy

Modeling in Therapy

Modeling, a key technique in therapy, uses observational learning to help clients acquire and practice new skills by watching therapists demonstrate desired behaviors. This approach, rooted in Albert Bandura's concept of vicarious learning, plays a significant role in therapeutic interventions for various psychological conditions, including social anxiety, ADHD, and depression.
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in situations...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Thiols as Key HAT Catalysts in Photoredox Catalysis: Diversifying the Hydrofunctionalization Landscape of Unactivated Alkenes.

Chemistry (Weinheim an der Bergstrasse, Germany)·2026

Same author

Prediction of Depression in Women With Metabolic Dysfunction-Associated Fatty Liver Disease Using Routine Blood Tests: A Five-Year Longitudinal Analysis From the UK Biobank.

Alpha psychiatry·2026

Same author

Oral microbiome modulation mitigates hyperglycemia exacerbation in gestational diabetes mellitus.

Nature communications·2026

Same author

Application of Cerium-Tannic Acid-Formaldehyde Coordination Polymer Colloidal Nanomaterials to Alleviate Lipopolysaccharide-Induced Acute Lung Injury.

International journal of nanomedicine·2026

Same author

An orally deliverable Co<sub>3</sub>O<sub>4</sub>@MMT nanozyme platform for inflammatory bowel disease via ROS scavenging, barrier repair, and mucosal homeostasis regulation.

Materials today. Bio·2026

Same author

Methane inhalation during ex vivo lung perfusion protects donor lungs after cardiac death via modulation of MAPK-related inflammatory and oxidative pathways.

The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation·2026

Search research articles

Related Experiment Video

Updated: Jul 3, 2026

Practical Methodology of Cognitive Tasks Within a Navigational Assessment

Practical Methodology of Cognitive Tasks Within a Navigational Assessment

Published on: June 1, 2015

Starmate: A Lightweight AI Assistant for Autism Caregivers Developed and Evaluated Through a User-Centered

Zhifan Li¹, Xiaoxia Liu¹, Tianhao Chen¹

¹Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China.

Journal of Medical Systems

|July 1, 2026

Summary

A new AI assistant, Starmate, offers reliable, empathetic guidance for autism spectrum disorder (ASD) caregivers. Developed using a user-centered approach, it outperforms commercial models in providing practical, clear, and empathetic support for families navigating ASD challenges.

Keywords:

Autism spectrum disorder Caregiver support Large language models Retrieval-augmented generation User-centered design

Related Experiment Videos

Last Updated: Jul 3, 2026

Practical Methodology of Cognitive Tasks Within a Navigational Assessment

Practical Methodology of Cognitive Tasks Within a Navigational Assessment

Published on: June 1, 2015

Area of Science:

Artificial Intelligence
Human-Computer Interaction
Neurodevelopmental Disorders

Background:

Millions of families worldwide face challenges with autism spectrum disorder (ASD).
Online resources for ASD caregivers often lack reliability and empathy.
Limited access to timely and accurate guidance exacerbates caregiver stress.

Purpose of the Study:

To develop an AI assistant, Starmate, specifically for autism spectrum disorder (ASD) caregivers.
To address the critical gap in reliable, empathetic, and timely online guidance for ASD families.
To evaluate Starmate's performance against leading commercial large language models (LLMs).

Main Methods:

Developed Starmate, a 1.5B-parameter, domain-tuned AI assistant, using a user-centered mixed-methods framework.
Engineered a modular architecture integrating sentiment analysis, knowledge-graph-augmented retrieval (LightRAG), and a fine-tuned Qwen2.5 model.
Conducted blinded, side-by-side comparisons and automated benchmarking against commercial LLMs.

Main Results:

Starmate demonstrated superior performance in key metrics compared to leading commercial LLMs (86.76 vs 78.43-83.84).
Starmate showed significant advantages in Empathy, Hands-on guidance, and Logical clarity.
Automated benchmarking confirmed top scores for Professional accuracy (86.18), Empathy (86.79), and Hands-on guidance (82.58).

Conclusions:

A lightweight, privacy-conscious, domain-specific LLM can generate accurate, empathetic, and actionable responses for ASD caregivers.
Starmate represents a technically feasible solution to improve online support for families affected by ASD.
Findings lay the groundwork for future real-world usability and clinical testing of AI-driven ASD support tools.