The increasing frequency and impact of strong earthquakes on urban areas have prompted researchers to develop rapid seismic health monitoring techniques. Urban apartment-type multistorey buildings often feature shear walls for earthquake resistance. Health monitoring is crucial in these structures, as they house many people and differ from structures without shear walls. This research introduces an artificial intelligence (AI)-based method for identifying seismic damage in RC buildings. When developing an AI model, it is critical to incorporate key parameters of real earthquake ground motions (EQGM) such as peak ground displacement (PGD), peak ground velocity (PGV), peak ground acceleration (PGA), and time duration. Additionally, building parameters like maximum displacement, story drift, and base shear are also taken into account. The finite element software ETABS is utilized to generate simulation data for AI model development. MATLAB software is employed to develop the AI model, which is trained using the Levenberg–Marquardt (LM) algorithm. This proposed method can be effectively applied to monitor the post-earthquake condition of reinforced concrete (RC) structures.