Machine Learning Approach for Detection of Mental Health

Abstract

Mental health issues are the most prevalent between the ages of 15 and 60. People are unaware of this health issue. The identification of mental health made use of numerous machine-learning approaches. Artificial intelligence (AI) called machine learning enables computers to automatically learn from their experiences and advance over time without explicit programming. In this work, ANN, regression, linear regression, random forest, and decision tree models were utilized to identify mental health problems precisely. This was because machine-learned technology was an effective method for evaluating whether a person had a mental health issue. For the detection of mental diseases, machine learning is crucial. There are ANN and Linear Regression used for better results. There were key indicators as to whether an episode was imminent. These crises could be predictable if we could detect a pattern of stress, isolation, or exposure to triggers. The model data used is a survey based on a company that gave information about how many people had gone through mental health problems. Our proposed ANN model gives an accuracy of around 64% as we increase epochs, the model performs better, and accuracy increases.