Structural health prediction system is intended to display, evaluate, and envisage the condition of structures like bridges, buildings, and dams to ensure safety, extend the life of the structure, and optimise maintenance. Structural health prediction system typically involves the gathering of data from various sensors and observing devices installed on the structure. These sensors measure parameters like strain, vibration, displacement, and load. The collected data is analysed to assess the current health of the structure. This involves using arithmetical approaches, machine learning algorithms, or other analytical procedures to detect variances or deviations from expected behaviour. Predictive models are developed based on historical data and current measurements. These models simulate the future behaviour of the structure under various conditions, helping to forecast potential issues before they occur. The system evaluates the structural integrity and performance by comparing real-time data against the predicted models. It identifies areas that may require maintenance or repair. The system provides recommendations and alerts to engineers and maintenance teams. This helps in prioritising repairs and maintenance tasks, thereby optimising resource allocation and ensuring timely interventions. Structural health prediction system often includes tools for visualising data and generating reports. This helps stakeholders understand the current state and trends in structural health, facilitating informed decision-making. The Structural Health Prediction System (SHPS) is an innovative design tool to enhance the assessment and maintenance of concrete structures. Building upon Structural Health Monitoring (SHM) principles, this study develops the Structural Health Prediction System (SHPS), an advanced tool derived from the principles of Structural Health Monitoring (SHM). The SHPS integrates artificial intelligence model (AI) and Building Information Modelling (BIM) to predict the health and performance of concrete members. By leveraging experimentally acquired data, including crack types, load types, and images, the system trains AI models to understand the behaviour of concrete members under varying loads over time. This predictive capability will enable the SHPS to provide comprehensive health statistics and performance evaluations, supporting proactive maintenance and decision-making in structural engineering.