BACKGROUND: Despite the construction of the metagenome of the asthmatic lung, limitations persist in sampling the bronchial airway. This study analyzed extracellular vesicles (EVs) obtained from exhaled breath condensate (EBC) to compare the distinct characteristics of the microbiome in asthmatics with those in healthy controls and proposed a diagnostic artificial intelligence-based model of asthma. METHODS: We obtained the EBC from 58 healthy controls and 251 patients with asthma. EVs were isolated from the EBC and analyzed. The extracted 16s rDNA was subjected to next generation sequencing. Taxonomic profiling was conducted for all samples at the genus level. A combination of artificial neural network (ANN) and gradient boosting (GBM) was applied to selective EBC biomarkers. RESULTS: The asthma group exhibited significantly higher alpha diversity based on the results of the Chao1, Shannon, and Simpson indices. The bacterial composition of patients with asthma different from that of the controls. At the genus level, Sphingomonas, Akkermansia, Methylophaga, Acidocella, and Marinobacter were significantly more abundant in patients with asthma. The diagnostic model using GBM and ANN demonstrated good performance with respective areas under the curve of 0.832 and 0.769. Firmicutes and Proteobacteria at the phylum level were common important features between the GBM and ANN asthma models. CONCLUSION: We demonstrated a distinct pattern in the microbiome of patients with asthma, indicating the potential role of microbiome-based diagnosis of asthma. To the best of our knowledge, this was the first study to identify the microbiome in asthma using EBC-derived EVs.