Time-series data plays a crucial role in Structural Health Monitoring (SHM), especially in evaluating the condition and performance of infrastructure like bridges. It consists of measurements taken at consistent intervals, allowing the analysis of system changes over time. Utilizing time-series data enables the application of advanced techniques such as Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (RNN) that excels at learning long-term dependencies. LSTM models have been successfully applied across various fields to derive insights from temporal data, making them ideal for analyzing the behavior of bridge structures. This paper emphasizes the application of LSTM for bridge damage detection using time-series data. The comprehensive dataset allows LSTM models to detect subtle variations that indicate structural damage or deterioration over time. Our findings demonstrate that this approach not only enhances accuracy but also improves the reliability of damage detection in SHM, offering a proactive solution for bridge maintenance and safety management.