The study investigated the association between non-obese steatotic liver disease (SLD) and coronary artery disease (CAD) in patients with a normal body mass index. They analyzed 8,722 subjects and found that the risk of CAD was significantly higher in non-obese patients with SLD than in obese patients with SLD or individuals without SLD. They produced a nomogram to predict CAD with an area under the curve of 0.846 in the training set and 0.732 in the validation set. Using bioinformatics analysis of the GSE89632 and GSE113079 datasets, they identified 28 overlapping upregulated and 66 downregulated genes. The protein-protein interaction network contained 94 edges and 40 hub genes. Machine learning algorithms selected key genes HNF4A and LTBP4 that have high diagnostic value for both non-obese SLD and CAD. The study confirms the close correlation between non-obese SLD and CAD and proposes a new diagnostic model.