Abstract Aging is a complex and systematic biological process that involves multiple genes and biological pathways across different tissues. While existing studies focus on tissue-specific aging factors, the inter-tissue interplay between molecular pathways during aging remains insufficiently explored. To bridge this gap, we propose a novel computational framework to identify the effect of aging on the coordinated patterns of gene-expression across multiple tissues. Our framework includes (1) an adjusted multi-tissue weighted gene co-expression network analysis, (2) differential network connectivity analysis between age groups and (3) machine learning models, XGBoost and Random Forest (RF) fed by gene expression levels and lower-dimensional pathway score space, to identify unique key inter-tissue genes and biological pathways for classifying aging. We applied our approach to three representative tissues: Adipose-Subcutaneous, Muscle-Skeletal and Brain-Cortex. The RF model demonstrated the best performance in predicting age group (AUC