Depression also known as depressive disorder is a serious and common medical condition that has an adverse impact on how you feel, think, and behave. But it can also be treated. Depression causes feelings of sadness or a loss of interest in activities once you enjoyed. It can impair your ability to perform at work and at home and cause a number of mental and physical issues. Therefore, it is important to provide some solutions to overcome the depression problem. These days’ information and communications technology (ICT) is used in various domains to sort out their problems. In this paper, we propose an embedded long short-term memory (LSTM) based scheme for depression detection and analysis. It is a brain health mapping based system for the detection of depression. It is a first of its kind interdisciplinary brain cognition tool (software), which acts as a personalized support intelligence mechanism. It incorporates psychological traits for determining a user's mental health state. The proposed scheme utilizes natural language processing techniques to provide a novel framework to predict the sentimental and emotional state of the user based on the user's behavior in their interaction with the designed model. In order to actively track the user's mental state, proposed scheme analyses their text and identify specific keywords through the text that they input in different applications that the user utilizes in their machine. The practical implementation of the proposed scheme is provided and important results (i.e., accuracy and F1 score) are estimated. During the performance comparison, it has been observed that proposed scheme achieved better accuracy than the other existing schemes.