Four Decades of ADHD: A Systematic AI-assisted Analysis of Conceptual Shifts Across Six DSM Editions

Background Considering the central role of the Diagnostic and Statistical Manual of Mental Disorders (DSM) in psychiatric classification, multiple studies have examined how it describes Attention-Deficit/Hyperactivity Disorder (ADHD)—one of the most common psychiatric diagnoses. However, despite analyzing the same DSM texts, these studies yielded conflicting conclusions, likely influenced by the subjectivity of qualitative research and the challenge of systematically tracking subtle changes in large textual corpora. This study addresses these limitations by providing the first systematic, Artificial Intelligence (AI)-assisted analysis of all ADHD-related texts across six DSM editions ( DSM-III to DSM-5-TR ). Methods The analysis employed two AI models ( GPT-4o and Claude 3.5 Sonnet ) and followed five steps: (A) preliminary human review, (B) AI-assisted comparison, (C) refinement through self-prompting to detect subtle linguistic changes, (D) thematic synthesis by each model, and (E) cross-model validation. Strict adherence to DSM texts ensured that all findings were grounded in verifiable evidence. To reduce interpretive bias, human interpretations were intentionally minimized. Results The complete analysis is available in the Supplementary Materials. Overall, the findings revealed six overarching shifts toward: (1) a neurodevelopmental framework, (2) a lifespan condition across genders, (3) a broader concept of impairment, (4) greater diagnostic flexibility, (5) expanded comorbidities and differential diagnoses, and (6) cultural and contextual influences. Conclusions These trends, together with the full study materials, systematically map how ADHD has been described and classified in the DSM over four decades, offering a structured and transparent foundation for future discussions.