Concerns regarding chronic injuries (e.g., fibrosis and carcinogenesis) induced by nanoparticles raised public health concerns and needs to be rapidly assessed in hazard identification. Although in silico analysis is commonly used for risk assessment of chemicals, predicting chronic in vivo nanotoxicity remains challenging due to the complex interactions at multiple nano-bio interfaces. Herein, we developed a multimodal feature fusion analysis framework to predict the fibrogenic potential of metal oxide nanoparticles (MeONPs). Eighty-seven features derived from multiple MeONP-lung interfaces were used to develop a machine learning-based predictive framework. We identified viability damage and cytokine (IL-1β and TGF-β1) production in macrophages and epithelial cells as key events that are closely associated with particle size, surface charge, and interactions with lysosomes. Experimental validations showed that the developed in silico model had 85% accuracy in predicting MeONP-induced lung fibrosis. The heterogeneity distribution of data points indicated good applicability of the predictive model. Our findings demonstrate the potential usefulness of this predictive model for risk assessment of nanomaterials and in assisting regulatory decision making.