Lung cancer is the leading cause of cancer-related death worldwide. MicroRNAs (miRNAs) in circulating small extracellular vesicles (sEVs) have been suggested to be potential biomarkers for cancer diagnosis. The present study was designed to explore whether plasma-derived sEV miRNAs could be utilized as diagnostic biomarkers for differentiating between early-stage small cell lung cancer (SCLC) and early-stage non-small cell lung cancer (NSCLC). We compared the miRNA profiles of plasma-derived sEVs from healthy individuals, patients with early-stage SCLC and patients with early-stage NSCLC. Next-generation sequencing was used to screen for differentially expressed miRNAs (DEMs). Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses were used to predict the potential functions of these DEMs. Weighted gene coexpression network analysis (WGCNA) was used to identify the different pathology-related miRNA modules. We found that 22 DEMs were significantly different among healthy individuals, patients with early-stage SCLC, and patients with early-stage NSCLC. We selected six representative DEMs for validation by qRT-PCR, which confirmed that miRNA-483-3p derived from plasma sEVs could be used as a potential biomarker for the diagnosis of early-stage SCLC, miRNA-152-3p and miRNA-1277-5p could be used for the diagnosis of early-stage NSCLC respectively.