Stress is a pervasive issue impacting physical and mental health in modern society, contributing to conditions such as anxiety, depression, and cardiovascular diseases. The integration of wearable technology with artificial intelligence (AI) and machine learning (ML) offers a promising approach for real-time stress detection and management. This paper explores the use of wearable devices, such as smartwatches, fitness bands, EEG headsets, and smart rings, to collect physiological data, including heart rate variability (HRV), electrodermal activity (EDA), and skin temperature. The data are analysed using advanced AI and ML algorithms, such as Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Deep Learning (DL) models, to identify stress patterns with high accuracy. The study discusses various wearable technologies, their applications, and ML methodologies employed for stress detection. It also highlights ongoing research, challenges, and future directions, including the need for improved sensor accuracy, hybrid ML models, and integration with healthcare systems. By leveraging AI-driven wearables, this research aims to enhance mental health monitoring, facilitate early interventions, and provide personalised stress management solutions, ultimately improving the quality of life.