Schizophrenia Detection and Classification: A Systematic Review of the Last Decade

Area of Science:

• Utilizes advanced algorithms for analyzing complex, large-scale datasets in healthcare.
• Mimics human cognitive processes for automated decision-making in medical analysis.

Background:

• Schizophrenia (SZ) is a chronic mental disorder impacting millions globally.
• Characterized by hallucinations, paranoia, and cognitive disruptions, impairing daily functioning.
• Highlights the critical need for advanced diagnostic tools in mental healthcare.

Purpose of the Study:

• To systematically review Artificial Intelligence (AI) applications in schizophrenia (SZ) detection and classification.
• To examine Machine Learning (ML) and Deep Learning (DL) methods across various neuroimaging modalities.
• To synthesize current advancements and identify challenges in AI-driven SZ diagnosis.

Main Methods:

• Systematic review adhering to PRISMA 2020 guidelines, covering studies from 2015-2024.
• Inclusion of peer-reviewed studies sourced from multiple databases.
• Evaluation of ML and DL techniques using Electroencephalography (EEG), sMRI, and fMRI data.

Main Results:

• Significant advancements in AI for SZ diagnosis, particularly ML and DL efficacy in feature extraction and classification.
• Demonstrated potential of AI in multi-modal data integration for improved diagnostic accuracy.
• Identified challenges: dataset limitations, preprocessing variability, and need for model interpretability.

Conclusions:

• Comprehensive evaluation of AI-based methods for SZ prognosis, detailing strengths and limitations.
• Identification of research gaps and future directions for AI in SZ detection and diagnosis.
• Emphasizes the evolving role of AI in enhancing mental health diagnostics.