A Review: Early Scrutiny of Mental Health Disorders through Machine Learning and Deep Learning Methodologies

Review discusses the application of machine learning and deep learning in the field of mental wellness, with an emphasis on early assessments, therapy result prediction, and extending supervision to improve diagnosis and individualized treatment. It explores various techniques, challenges and possible remedies that might enhance mental health care. It is common to hear about psychological disorders, which are occasionally triggered by a traumatic experience or any number of other situations. However, an individual is more prone to suffer from mental health issues. There are various forms of mental health issues. Naming Post Traumatic Stress Disorder (PTSD), Schizophrenia, Social anxiety, dementia, Alzheimer disease, cognitive impairment, obsessive compulsive disorder (OCD), stress, attentiondeficit/ hyperactivity disorder (ADHD) along with further disorders. Here is an overview of all psychological issues and their respective diagnoses using EEG signals, brains MRI, healthcare information with existing medical records, facial expressions, audio and retinal movement are all applicable to perform this. Considering all of these kinds of input data, the medical diagnosis is processed. The usage of machine learning and deep learning algorithms as well as models plays a substantial part. Classification techniques such as Regression, deep forest, VGG16, Support Vector Machine (SVM), AdaBoost, Artificial Neural Network (ANN) XGBoost, Convolutional Neural Network (CNN) were utilized. Available primary datasets are used, and some articles incorporate real-time data.