Betel leaf (Piper betel L.) is highly susceptible to severe fungal and bacterial diseases such as leaf rot, collar rot, anthracnose (leaf spot), and bacterial leaf spot, which cause significant yield losses through rotting, spotting, and wilting. Its rich phytochemistry underpins various medicinal properties, while its production supports rural economies in Asia. However, diseases and perishability pose serious challenges to yield and profitability, necessitating improved agronomic practices, disease management, and post-harvest handling to sustain and enhance its global economic contribution. Effective disease management therefore requires early integration of cultural practices along with fungicidal and bactericidal treatments. In the present study, laser-induced breakdown spectroscopy (LIBS) coupled with k-nearest neighbors (KNN) modeling was employed to discriminate between healthy and diseased betel leaves. The discriminative potential of nineteen LIBS emission peaks was evaluated using an interclass distance approach. Among these, the Mg II (279 nm) and Na I (588 nm) emission peaks were identified as the most effective variables for classification. One-dimensional KNN models developed using the spectral intensities of Mg II and Na I achieved classification accuracies of 92% and 96%, respectively. This approach demonstrates a cost-effective and time-efficient alternative to conventional elemental analysis techniques, enabling rapid, field-deployable analysis with minimal sample preparation.