The extent of mental health is much more than what the general public knows. Many studies have found that women, the elderly, those who had recently survived a disaster, those who worked in the industrial sector, children, adolescents, and persons with long-term medical illnesses were at a higher risk of mental difficulties. Early recognition helps patients treat them more effectively and enhance their lives. Better living conditions, healthcare, and women's empowerment are all necessary. Mental health treatment is required for every age group, from children to seniors. This research will illuminate the need for mental health treatment across different age groups. This prediction is evaluated on the publicly available dataset. The dataset consists of 1259 entries and 27 attributes. Various accuracy metrics were used to evaluate the performance of machine learning techniques in identifying mental health concerns in this study. A comparison of these methods has been done and put into practice and also found that the Logistic Regression method, based on a forecast accuracy of 83.07%, was the most accurate. The machine learning algorithms used in this study include K-NN Classifier, Logistic Regression, Decision Tree Classifier, AdaBoost and Random Forest, which are discussed with their algorithm procedure.