Seborrheic dermatitis is a chronic inflammatory skin disorder affecting the scalp, face, and upper trunk. Evidence suggests a link between seborrheic dermatitis and systemic metabolic abnormalities, especially among individuals with metabolic syndrome, a condition involving central obesity, dyslipidemia, hypertension, and impaired glucose metabolism. However, specific clinical and biochemical predictors of seborrheic dermatitis in this population remain unclear.To identify clinical and biochemical predictors of seborrheic dermatitis and to estimate individual risk among people with metabolic syndrome using a machine learning approach applied to real-world clinical data.We conducted a retrospective observational study using electronic medical records from a tertiary hospital. Adults who visited the hospital between January 2018 and December 2024 and met the National Cholesterol Education Program Adult Treatment Panel III (NCEP-ATP III) criteria for metabolic syndrome were included. Seborrheic dermatitis was identified using International Classification of Diseases, 10th Revision (ICD-10) codes and verified through clinical notes; patients with non-specific skin symptoms were excluded unless seborrheic dermatitis was clearly documented. Features included age, sex, body mass index (BMI), waist circumference, triglyceride-to-high-density lipoprotein (HDL) ratio, fasting glucose, glycated hemoglobin (HbA1c), smoking, alcohol use, and comorbidities. A gradient boosting model (extreme gradient boosting, XGBoost) was trained to predict seborrheic dermatitis, and performance was evaluated using five-fold cross-validation.Among 446 patients with metabolic syndrome, 53 (11.9%) had seborrheic dermatitis. The machine learning model achieved an area under the receiver operating characteristic curve (AUC) of 0.78, accuracy of 74.4%, precision of 61.7%, recall of 66.0%, and F1-score of 63.8%. Shapley Additive Explanations (SHAP) indicated that triglyceride-to-HDL ratio, HbA1c, BMI, and smoking status were the most influential predictors of seborrheic dermatitis risk.This electronic medical record–based machine learning study highlights the role of metabolic imbalance and lifestyle factors in seborrheic dermatitis among patients with metabolic syndrome.Predictive tools based on routinely collected clinical data may support early identification and risk stratification of seborrheic dermatitis in primary care, but prospective validation in diverse settings is needed.