The neurological developmental disorder ADHD induces patients to experience attention problems together with excessive activity as well as impulsive behaviors. Three methodologies have been established for diagnosis that combine clinical assessment along with behavioral evaluation through manual observer-based evaluation that yield delayed responses with imprecise outcomes between different evaluators. The research's main goal targets improved ADHD assessment by introducing automated machine learning and AI techniques. The diagnostic accuracy tests require ML models to utilize behavioral and cognitive datasets during their training process for precision assessments. The research results show artificial intelligence programs excel in detecting ADHD signs during their initial development period. The research project develops AI-based medical diagnostic tools for faster condition detection and incorrect results prevention for medical practitioners. The methodology serves as a foundation for creating upcoming AI tools that will handle mental health screening operations.