COMPUTE DEPRESSION AND ANXIETY AMONG STUDENTS IN PAKISTAN, USING MACHINE LEARNING

The worldwide mechanical advancement in medical services digitizes the copious information, empowering the guide of the different types of human science all the more precisely than conventional estimating strategies. AI (ML) has been certified as a productive approach for dissecting the enormous measure of information in the medical services area. ML strategies are being used in emotional well-being to anticipate the probabilities of mental problems and, subsequently, execute potential treatment results. In the speedy present-day world, mental medical problems like depression and anxiety have become exceptionally normal among the majority. In this paper, forecasts of depression and anxieties were made utilizing AI calculations. Depression and anxiety have become emergent hindrances in the lives of human beings. It not only disturbs their daily decorum but has also become a prominent cause for their downfall in health. All around the world people are getting affected by this mental disorder yet the majority of such cases lie between ages 18-25 making university-going students a prime target for such mental diseases. Though the mental health of university students is known globally as a momentous public health matter. Academicals, social depression, and anxieties are playing quite a negative role in university student’s life, especially in forms of mental illness like depression and anxiety. These mental health issues are becoming a major constraint on their studies and career. Hence, this research is being conducted to develop a technological solution for mentally distorted students. This paper analyzes depression and anxiety amongst university students by effectively utilizing the k-nn algorithm (a conspicuous technique for detecting and analyzing mental depression and anxiety) and providing a technical solution for this mental hindrance. The experimental results show up to 76.5% accuracy in results after using k-nn without PCA while the accuracy was increased up to 76.6% when the results were generated with PCA.