This study aimed to investigate the relationship between lipoprotein(a) [Lp(a)] levels and non-alcoholic fatty liver disease (NAFLD), and to analyze its linear association and subgroup differences. This cross-sectional analysis was based on data from 2308 participants in the National Health and Nutrition Examination Survey (NHANES) III. Multivariate logistic regression models were used to assess the association between Lp(a) and NAFLD, adjusting for demographic factors, lifestyle behaviors, comorbidities, and biomarkers. Subgroup analyses were conducted based on age, sex, body mass index (BMI), diabetes, and hypertension. Restricted cubic spline (RCS) regression model was used to explore the nonlinear relationship between Lp(a) and NAFLD. Higher Lp(a) levels were significantly associated with a lower risk of NAFLD. In the fully adjusted model, compared to the lowest quartile group (Q1), the third and fourth quartiles (Q3 and Q4) had significantly reduced risks of NAFLD [Q3: OR = 0.701, 95% CI 0.511, 0.961
P = 0.027
Q4: OR = 0.605, 95% CI 0.438, 0.835
P = 0.002]. Subgroup analysis showed that the association between higher Lp(a) levels and reduced NAFLD risk was significant in individuals aged 50 years and older, those with BMI ≥ 30 kg/m