Attention-Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental condition affecting both children and adults alike, characterized primarily by problematic inattention and hyperactivity/impulsivity that causes functional impairment in daily life. The current ADHD diagnosis relies on the physician-administered approach and requires significant manual intervention, which in turn could be more prone to human error and may also suffer from recall bias. The ubiquitous nature of smartphones and their rich set of embedded sensors make them an ideal solution for behavior tracking and diagnosis. In this study, we introduce SmartADHDMonitor, a novel approach for predicting weekly ADHD symptom levels and diagnostic status. This approach utilizes passively collected smartphone app usage data from 12 college-age students on the Android platform. We calculated a comprehensive set of features using the smartphone app usage behavioral data and constructed a family of machine-learning models for predicting weekly levels of ADHD symptoms and ADHD diagnostic status. Our results demonstrate that the app usage data could be used for predicting ADHD diagnostic status fairly accurately with F1scores as high as 0.88. Our preliminary findings offer a promising research direction into machine learning applications for ADHD diagnosis and monitoring through smartphone sensing data. As one of the first studies in this domain, SmartADHDMonitor offers a novel, technology-driven perspective on addressing the growing need for accessible mental health care solutions, further advancing the smart connected health in the field of ADHD monitoring.