This study explores the integration of large language models (LLMs), like ChatGPT, to improve attention deficit hyperactivity disorder (ADHD) treatments. Utilizing the Delphi method for its systematic forecasting capabilities, we gathered a panel of child ADHD therapy experts. These experts interacted with our custom ChatGPT through a specialized interface, thus engaging in simulated therapy scenarios with behavioral prompts and commands. Using empirical tests and expert feedback, we aimed to rigorously evaluate ChatGPT’s effectiveness in therapy settings to integrate AI into healthcare responsibly. We sought to ensure that AI contributes positively and ethically to therapy and patient care, thus filling a gap in ADHD treatment methods. Findings show ChatGPT’s empathy, adaptability, and communication strengths, thereby highlighting its potential to significantly improve ADHD care. The study points to ChatGPT’s capacity to transform therapy practices through personalized and responsive patient care. However, it also notes the need for enhancements in privacy, cultural sensitivity, and interpreting nonverbal cues for ChatGPT’s effective healthcare integration. Our research advocates for merging technological innovation with a comprehensive understanding of patient needs and ethical considerations, thereby aiming to pioneer a new era of AI-assisted therapy. We emphasize the ongoing refinement of AI tools like ChatGPT to meet ADHD therapy and patient care requirements more effectively.

Traditional attention-deficit/hyperactivity disorder (ADHD) interventions often struggle with scalability, requiring significant human resources to ensure individualized attention and real-time adaptability, as many existing tools rely on fixed content that cannot adjust to fluctuating user behaviors. Additionally, most current methods lack multi-modal interaction, limiting their ability to engage children effectively across speech, text, and visual feedback. This study explores the integration of ChatGPT-4o with robotic assistants to enhance personalization, engagement, and adaptability in ADHD therapy. Unlike pre-scripted or static therapy tools, ChatGPT-4o enables dynamic, real-time interactions tailored to individual needs, providing a more engaging and adaptable therapeutic experience. The results validate its potential to deliver personalized, scalable, and responsive therapeutic support through AI-driven robotic assistants. Technical validation demonstrated inclusivity across diverse user profiles, achieving a 93% success rate in tailored interactions and maintaining stability in 91% of extreme input scenarios. Cross-platform tests confirmed high accuracy, while scalability assessments validated effective handling of multi-user interactions. Clinical evaluations over eight weeks indicated potential improvements in attention span (+ 28%) and reductions in hyperactivity (− 22%), with high satisfaction ratings from therapists, caregivers, and teachers. These results establish ChatGPT as a promising tool for ADHD therapy, enhancing engagement, personalization, and scalability. Future directions include optimizing for younger users, deploying to real-world environments, and further interdisciplinary advancements to refine AI-driven therapeutic solutions.