Accurate classification of adenocarcinoma (AC) and squamous cell carcinoma (SCC) in lung cancer is critical to physicians' clinical decision-making. exhaled breath analysis provides a tremendous potential approach in non-invasive diagnosis of lung cancer but was rarely reported for lung cancer subtypes classification. In this paper, we firstly proposed a combined method, integrating K-nearest neighbor classifier (KNN), borderline2-synthetic minority over-sampling technique (borderlin2-SMOTE), and feature reduction methods, to investigate the ability of exhaled breath to distinguish Ac from Scc patients. The classification performance of the proposed method was compared with the results of four classification algorithms under different combinations of borderline2-SMOTE and feature reduction methods. The result indicated that the KNN classifier combining borderline2-SMOTE and feature reduction methods was the most promising method to discriminate Ac from Scc patients and obtained the highest mean area under the receiver operating characteristic curve (0.63) and mean geometric mean (58.50) when compared to others classifiers. The result revealed that the combined algorithm could improve the classification performance of lung cancer subtypes in breathomics and suggested that combining non-invasive exhaled breath analysis with multivariate analysis is a promising screening method for informing treatment options and facilitating individualized treatment of lung cancer subtypes patients. Lung cancer is one of the most malignant tumors threatening people's health and life, which is divided into small cell lung cancer (SCLC, ~15%) and non-small cell lung cancer (NSCLC, ~85%), NSCLC mainly includes adenocarcinoma (AC, ~38%) and squamous cell carcinoma (SCC, ~20%) 1,2. Numerous clinical trials have proved that the more exact the type of tumor histology we know, the more effective treatment would be 1,3. Therefore, how to quickly distinguish the exact subtypes of lung cancer, especially AC and SCC, has become a mandatory diagnostic requirement in the past decades years 4-6. In clinical practice, the histopathological analysis is a gold standard for diagnosing the lung cancer subtypes, but it can cause invasive injury and is complicated in operation. Another common method is imaging diagnosis (e. g., low-dose computed tomography (LD-CT)), which has certain limitations of radiation exposure and high false-positive rate. Thus, the non-invasive and safe alternative diagnosis methods based on omics analysis (e. g., proteomics and radiomics) are pursued by experts to distinguish lung cancer subtypes 6-12. Similar to other omics, breathomics as a non-invasive diagnostic method had shown its potential for early diagnosis of diseases, prognosis evaluation, and classification of disease subtypes 13,14. Relative studies also revealed the possibility of machine learning algorithms coupled with high-throughput platforms to the classification