Deep Feedforward Neural Networks for Prediction of Mental Health

Mental health disorders or psychiatric issues such as Alzheimer’s disease (AD), cognitive impairments, and depression have an impact on physical health. The early detection of patients who are at risk of a mental health crisis is of paramount importance to reduce burdens and costs that can result from. However, the high prevalence of mental health issues makes it impractical to manually review complicated patient health records to make proactive psychiatric health care decisions. Artificial intelligence (AI) techniques have recently been developed to aid mental health professionals, such as psychiatrists and psychologists, in making clinical decisions. Recently, deep learning approaches find great attention among biomedical researchers due to their unmatchable ability to use very large size datasets to predict medical results. One such tremendous application is the use of deep learning for the prediction of psychiatric disorders. However, typical deep learning (DL) approaches suffer from limitations due to their significant presumptions, which make this not suitable for medical imaging. This book chapter reviews the literature on DL algorithm applications in predictive research on psychiatric health. In particular, it gives a succinct overview of contemporary DL techniques in psychiatric health research. This chapter proposed a novel deep learning method using deep feedforward neural networks coupled with psychiatric tools, which could hasten a new way for integration into prognostic research in digital psychiatry and eventually lead to its use in clinical results. In our final section, it examined the major difficulties in applying DL algorithms and psychiatric tools to enhance the prognosis and prediction of mental health disorders and leveraging several interesting applications for DL algorithms along with physician’s intelligence for enhancing mental health treatment.