Related Experiment Video
Updated: Jan 9, 2026
The Adventures of Fundi Intervention Based on the Cognitive and Emotional Processing in Attention Deficit Hyperactive Disorder Patients
Published on: June 12, 2020
Exploring AI-assisted design of executive function rehabilitation programs for individuals with ADHD: a mixed-methods
Margherita Dahò1,2, Barbara Caci3,4
1Department of Psychology, Educational Science and Human Movement, University of Palermo, Viale delle Scienze, Ed.15, Palermo, 90146, Italy. Margherita.daho@unipa.it.
Background:
As Artificial Intelligence (AI) tools like ChatGPT gain traction in clinical contexts, their role in neurorehabilitation, particularly in addressing executive function impairments associated with ADHD, remains underexplored. This study examines whether generative AI can meaningfully support clinicians in designing individualized cognitive rehabilitation plans, not as a replacement but as a complementary aid.
Methods:
The research consisted of three separate studies, each addressing distinct stages of the investigation. First, expert-driven prompts were developed based on literature and clinical insights to guide ChatGPT in generating rehabilitation plans for three hypothetical profiles of individuals with ADHD (adolescents, adults, and older adults). In Study 2, the outputs were analyzed using a semi-systematic qualitative framework (ISAAC), assessing structure, coherence, and adaptability across developmental stages. Study 3 involved an external panel of 27 neuropsychologists and cognitive rehabilitation specialists (M = 6; F = 21; mean age = 46.5, SD = 15) who rated each plan's theoretical validity, clinical relevance, and feasibility.
Results:
Experts in Study 3 generally responded positively to the theoretical consistency of the plans, especially those for adolescents and adults, recognizing alignment with established models of executive function rehabilitation. Many professionals expressed openness to using AI as a support tool in practice. However, feasibility emerged as a key limitation, with concerns over a lack of personalization, unrealistic resource assumptions, and unvalidated techniques, particularly in adult and older adult profiles. These findings align with earlier studies in occupational therapy and clinical decision-making, which also identified challenges in real-world applicability.
Conclusion:
While clinical experts express cautious optimism about AI-assisted rehabilitation planning, further development is necessary to enhance accuracy, personalization, and feasibility for the safe integration of AI into clinical practice.
