This is joined with a contextual investigation involving information from general practices in the Netherlands to recognize youngsters in danger of experiencing mental problems. To foster a precise model, include designing strategies, for example, one hot encoding and recurrence change are proposed, and the example determination is custom fitted to this kind of clinical information. Six AI models are prepared on five age gatherings, with XGBoost accomplishing the most noteworthy AUC values (0.75-0.79) with responsiveness and particularity above 0.7 and 0.6 individually [1]. Among youngsters, paces of misery and uneasiness have expanded by 70% in the beyond 25 years and the quantity of college understudies unveiling a psychological instability has developed fivefold in the previous ten years. Such problems adversely affect day to day existence and could prompt repercussions in prosperity and working, particularly whenever experienced in adolescence [2]. A significant number of youthful patients are perceived in a late state. As an outcome, emotional well-being remains deficiently treated, with an enormous extent of kids in need not getting ideal assistance [3 ]. This is a review with medical care information from youngsters enrolled with general practice habitats in the space of Leiden, the Netherlands. It processes Electronic Medical Records (EMR) from general experts (GP-s) [4]. The dataset comprises of coded records (patients, manifestations, interviews, lab results, medicine, and references) and free text mined from the specialists' notes.