Jadwal Sholat

Memuat jadwal sholatโ€ฆ

Ilmu Komputer & AI editorial

Open AccessOA2023

A Review of Machine Learning and Deep Learning Approaches on Mental Health Diagnosis

This PRISMA-based review analyzes 33 articles on machine learning and deep learning for diagnosing mental health disorders, categorizing methodologies by disorder and discussing challenges and public datasets.
Ngumimi Karen Iyortsuun; Soo-Hyung Kim; M. Jhon; Hyung-Jeong Yang; Sudarshan Pantยท Healthcareยท 2023ยท DOI 10.3390/healthcare11030285

The core problem

Mental illnesses such as depression and anxiety have become a global concern, necessitating effective diagnostic and treatment outcome prediction methods. Machine learning (ML) and deep learning (DL) approaches are increasingly integrated into healthcare systems for these purposes. With growing interest in these methods, a systematic analysis of existing work is needed to guide future research. This review aims to synthesize studies on the diagnosis of schizophrenia, depression, anxiety, bipolar disorder, post-traumatic stress disorder (PTSD), anorexia nervosa, and attention deficit hyperactivity disorder (ADHD) using ML/DL techniques.

Innovation

The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. A search across various databases yielded 33 articles that employed ML and DL technologies for mental health diagnosis. Each publication was individually assessed, and the recommended methodologies were categorized by disorder. The review also discusses difficulties encountered by researchers and provides a list of public datasets.
Introduction
Mental illnesses such as depression and anxiety have become a global concern, necessitating effective diagnostic and treatment outcome prediction methods. Machine learning (ML) and deep learning (DL) approaches are increasingly integrated into healthcare systems for these purposes. With growing interest in these methods, a systematic analysis of existing work is needed to guide future research. This review aims to synthesize studies on the diagnosis of schizophrenia, depression, anxiety, bipolar disorder, post-traumatic stress disorder (PTSD), anorexia nervosa, and attention deficit hyperactivity disorder (ADHD) using ML/DL techniques.

Why it matters

The review discusses the challenges faced by researchers in applying ML/DL to mental health diagnosis, such as data availability, variability in diagnostic criteria, and model interpretability. The categorization of methodologies by disorder provides a structured overview of the field. The list of public datasets serves as a resource for future studies. The authors emphasize the need for further research to address these challenges and improve the effectiveness of ML/DL in mental health care.

Who should read this

Pembaca Research Digest dan praktisi rumpun ini.

Opening member contentโ€ฆ