Metabolic syndrome (MetS) is a complex condition characterized by a group of interconnected metabolic abnormalities. Due to its increasing prevalence, better predictive markers are needed. Therefore, this study aims to develop predictive models for MetS by integrating adipokines, metabolic and cardiovascular risk factors, and anthropometric indices. Data were collected from 381 subjects aged 20 to 59 years (242 women and 139 men) from Guadalajara, Jalisco, Mexico, who were classified as having MetS or non-MetS based on the ATP-III criteria. Four supervised machine learning models were developed—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost)—and their performance was evaluated using the Area under the Curve (AUC), calibration curves, Decision Curve Analysis (DCA), and local interpretability analysis. The RF and XGBoost models achieved the highest AUCs (0.940 and 0.954). The RF and LR models were the best calibrated and showed the highest net benefit in DCA. Key variables included age, anthropometric indices (BRI and DAI), insulin resistance measures (HOMA-IR), lipid profiles (sdLDL-C and LDL-C), and high-molecular-weight adiponectin, used to classify the presence of MetS. The results highlight the usefulness of specific models and the importance of anthropometric variables, cardiovascular risk factors, metabolic profiles, and adiponectin as indicators of MetS.

Extracellular vesicles (EVs), particularly exosomes, are key mediators of intercellular communication, transporting biomolecules such as nucleic acids, lipids, and proteins that influence immune and metabolic pathways. In adipose tissue (AT), adipocyte-derived EVs (AdEVs) play a crucial role in maintaining metabolic homeostasis and have been implicated in obesity-related dysfunction. Among their bioactive cargo, microRNAs regulate post-transcriptional gene expression and participate in immunometabolic regulation. This study aimed to determine whether miR-34a expression in serum and circulating EVs varies according to body fat percentage, to explore its potential utility as a non-invasive biomarker of AT dysfunction. A total of 142 adults (mean age 36 ± 11 years) were classified by body fat percentage (≥25% in men, ≥35% in women). Exosomes were isolated (Invitrogen^®) and characterized by cryo-TEM, and miR-34a expression was quantified by qRT-PCR. miR-34a expression correlated negatively with Total Cholesterol, Triglycerides, LDLc/HDLc, TG/HDLc, BMI, C3, CRP, fasting insulin, HOMA-IR, HOMA-B, Body adiposity, Chemerin, CCL2, AdipoQT, and AdipoQ-H, but positively with HDLc and QUICKI. Notably, LDLc, sdLDLc, sdLDLc/LDLc, TC/HDLc, and fasting glucose showed opposite correlation patterns between serum and exosomes. Overall, serum miR-34a levels were higher than in exosomes, suggesting its potential as a biomarker of metabolic dysfunction and insulin resistance.