Handwriting plays a key role in the daily life of school-going children. Many standardized assessments are based on written work, particularly in time-limited written examinations. Impaired handwriting can interfere with learning to spell words in writing and speed of writing text and the overall well-being of a student. Dysgraphia is a neurological disorder characterized by writing difficulties. Specifically, the disorder causes a person's writing to be distorted or incorrect. In children, the difficulty generally emerges when they are first introduced to writing. It interferes with spelling, word spacing, and the general ability to put thoughts on paper. It makes the process of writing laboriously slow, with a product that is often impossible to read. As writing demands in school increase with age, it is important to diagnose dysgraphia as early as possible. People usually take the help of educational psychologists for identifying whether the child is having handwriting difficulties. The automated systems for screening dysgraphia were also developed using machine learning approaches. Even though automated system models were developed for screening dysgraphia, publicly available datasets are very limited, especially in Indian scenario. The proposed model focused on dysgraphia detection among 7- to 12-year-old school children by collecting handwritten text samples from rural schools. Totally, 152 handwriting samples were collected from children, out of which, 102 were non dysgraphic and 50 were identified as dysgraphic. Data preprocessing standardized the samples, and the dataset was divided into training and testing sets. The primary approach employed a convolutional neural network (CNN), achieving an impressive accuracy of 90.83%. Additionally, a comparison was made with support vector machine (SVM) and K-nearest neighbors (KNN), both of which demonstrated reasonable accuracies of 81.88% and 81.25%, respectively. The user-friendly interface enables the user to screen whether the child possesses symptoms of dysgraphia or not, by uploading a handwriting image of the child. These results showcase the potential of deep learning, particularly CNN, for dysgraphia screening, that enables timely interventions to support affected children.