Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by a reduced attention span, hyperactivity, and impulsive behaviors, which typically manifest during childhood. This study employs functional magnetic resonance imaging (fMRI) to use spontaneous brain activity for classifying individuals with ADHD, focusing on a 3D convolutional neural network (CNN) architecture to facilitate the design of decision support systems. We developed a novel deep learning model based on 3D CNNs using the ADHD-200 database, which comprises datasets from NeuroImage (NI), New York University (NYU), and Peking University (PU). We used fractional amplitude of low-frequency fluctuations (fALFF) and regional homogeneity (ReHo) data in three dimensions and performed a fivefold cross-validation to address the dataset imbalance. We aimed to verify the efficacy of our proposed 3D CNN by contrasting it with a fully connected neural network (FCNN) architecture. The 3D CNN achieved accuracy rates of 76.19% (NI), 69.92% (NYU), and 70.77% (PU) for fALFF data. The FCNN model yielded lower accuracy rates across all datasets. For generalizability, we trained on NI and NYU datasets and tested on PU. The 3D CNN achieved 69.48% accuracy on fALFF outperforming the FCNN. Our results demonstrate that using 3D CNNs for classifying fALFF data is an effective approach for diagnosing ADHD. Also, FCNN confirmed the efficiency of the designed model.