Hormone level fluctuation is connected with several health problems affecting human beings. To properly managing and diagnosing hormone levels, it is essential to understand hormonal imbalance and its detection. Commonly the levels of hormones were detected with the help of laboratory tests like chromatographic methods and immunoassays which gives accurate results but are very slow process and there is no real time detection proficiency. Hormone monitoring is crucial and wearable devices are progressing very effectively with the help of biosensors to monitor hormones to provide better understanding of health control. This review paper is focusing on the theory of hormones, hormonal imbalance indicators, and detection approaches which are available. Several tests for diagnosing hormone level imbalance were investigated including chromatographic techniques (HPLC, GC-MS), biosensors and immunoassays (ELISA, RIA) while also focusing on machine learning including deep learning algorithms, pattern recognition, regression, classification to provide customized treatment. Deep learning approaches like CNN (Convolutional Neural Networks) and Supervised learning approaches like SVM (Support Vector Machine) and Random Forests have demonstrated encouraging uses in real-time monitoring and the prediction of hormone related diseases. The review also highlights wearable devices available for hormonal levels monitoring, comparison of wearable sensors like electrochemical, optical and microfluidic systems. By empowering real-time surveillance of hormone level imbalances and promoting early detection, diagnosing and illness prevention, these advancements have improved conveniency. According to the research, combining Machine learning (ML) algorithms with wearable biosensors can transform monitoring of hormone levels may result in better results and can provide early medication.