A Survey on the Role of Artificial Intelligence in the Prediction and Diagnosis of Schizophrenia

TL;DR

This survey reviews recent AI and machine learning approaches, especially deep learning, for predicting and diagnosing schizophrenia using neuroimaging data, highlighting high prediction accuracies and recent progress.

Contribution

It systematically summarizes and compares recent studies on deep learning methods for schizophrenia detection using EEG, fMRI, and dMRI from 2019 to 2022.

Findings

All reviewed studies achieved over 80% prediction accuracy.

Deep learning techniques are increasingly effective in schizophrenia diagnosis.

The field is rapidly advancing with growing AI tool availability.

Abstract

Machine learning is employed in healthcare to draw approximate conclusions regarding human diseases and mental health problems. Compared to older traditional methods, it can help to analyze data more efficiently and produce better and more dependable results. Millions of people are affected by schizophrenia, which is a chronic mental disorder that can significantly impact their lives. Many machine learning algorithms have been developed to predict and prevent this disease, and they can potentially be implemented in the diagnosis of individuals who have it. This survey aims to review papers that have focused on the use of deep learning to detect and predict schizophrenia using EEG signals, functional magnetic resonance imaging (fMRI), and diffusion magnetic resonance imaging (dMRI). With our chosen search strategy, we assessed ten publications from 2019 to 2022. All studies achieved successful predictions of more than 80%. This review provides summaries of the studies and compares their notable aspects. In the field of artificial intelligence (AI) and machine learning (ML) for schizophrenia, significant advances have been made due to the availability of ML tools, and we are optimistic that this field will continue to grow.