The increasing demand for high-quality medical services and the rising costs of healthcare are gradually reshaping the traditional healthcare system. The new advancements in the Internet of Things (IoT) have demanded the improvement of the medical sector, giving rise to the incorporating of IoT with medical devices, commonly known as IoMT. The most important factor for the successful integration of IoT technology into the healthcare system is security. Since the IoMT network is vulnerable to several types of assaults, it is very important to safeguard patient data. Machine Learning (ML) and Deep Learning (DL) can play a key role in the ongoing data analysis and production of useful information. This paper introduces the BiLSTM (Bidirectional Long Short-Term Memory) model to discover various IoMT threats and attacks. The proposed method distinguishes between normal and attack traffic in the network and demonstrates its efficiency through ToN-IoT datasets.The recommended model performance has been compared to the results obtained from traditional techniques.The findings reveal that the BiLSTM model achieves 99.96% accuracy in detecting attacks and malicious traffic in the IoMT framework.