Lung cancer (Lca) is one of the malignant tumors with the fastest morbidity and mortality increase and the greatest threat to human health and life. The incidence of non-small cell lung cancer (NSCLC) in the nonsmoking female has increased recently. However, its pathogenesis is still unclear, and there is an urgent need for clinical diagnostic biomarkers, especially for early diagnosis. A nontargeted lipidomic approach based on ultra-high-performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry (UHPLC-Q-TOF/MS), as well as two machine learning approaches (genetic algorithm and binary logistic regression) was used to screen candidate discriminating lipids and define a combinational lipid biomarker in serum samples to distinguish female patients with NSCLC from healthy controls. Moreover, the candidate biomarkers were verified by using an external validation sample set. Our result revealed that fatty acid (FA) (20:4), FA (22:0) and LPE (20:4) can serve as a combinational biomarker for distinguishing female patients with NSCLC from healthy control with good sensitivity and specificity. Furthermore, this combinational biomarker also showed good performance in distinguishing early-stage NSCLC female patients from a healthy control. We observed that levels of unsaturated fatty acids clearly decreased, while saturated fatty acids and lysophosphatidylethanolamines pronouncedly increased in Lca patients, compared with the healthy controls, which revealed significant disturbance of lipid metabolism in NSCLC females. Our results not only provide hints to the pathological mechanism of NSCLC in nonsmoking female but also supply a combinational lipid biomarker to aid the diagnosis of NSCLC at early-stage.