A Comprehensive Survey on Schizophrenia Detection Using Machine Learning and EEG Analysis

Abstract

Schizophrenia is a devastating mental illness that affects many millions of people worldwide and is defined by a breakdown of the thought process and perception. Clinical interviews and behavioural assessments used as traditional diagnostic methods are subjective and time-consuming. Recent progress in machine learning (ML) and electroencephalography (EEG) facilitates the development of automated, stable, and generalizable diagnostic procedures. This survey offers an extensive review of state-of-the-art studies which utilized ML to detect schizophrenia, specifically in the context of EEG data. The comparison assesses the strengths and weaknesses of the methodologies, datasets, and algorithms. To go beyond existing challenges, we then explore future directions, such as explainable AI, multimodal integration, and personalization of diagnostic tools.