Artificial Intelligence in Schizophrenia Spectrum Disorders: Current Use and Future Perspectives. A Systematic...

Area of Science:

• Psychiatry
• Computational Neuroscience
• Medical Informatics

Background:

• Artificial intelligence (AI) applications in psychiatric research are growing but remain inconsistent for schizophrenia spectrum disorders (SSDs).
• This review systematically maps AI use in SSDs, categorizing approaches into natural language processing (NLP), machine learning (ML), and deep learning (DL).
• Key study characteristics, AI algorithms, populations, outcomes, and instrumental techniques were analyzed, alongside journal impact factor trends.

Purpose of the Study:

• To systematically examine and categorize current AI applications within schizophrenia spectrum disorders research.
• To identify trends in AI methodologies, clinical outcomes, and instrumental techniques used in SSD studies.
• To provide insights for planning and implementing AI-based research and clinical strategies for SSDs.

Main Methods:

• A systematic mapping literature review approach was utilized.
• 853 relevant studies investigating AI in SSDs were identified and analyzed.
• Studies were evaluated based on predefined criteria, including AI type, population, outcomes, and instrumental techniques.

Main Results:

• Machine learning (ML) was the most prevalent AI approach in SSD research.
• AI methods were primarily applied to diagnostic and differential diagnostic tasks for SSDs.
• Magnetic resonance imaging (MRI) and electroencephalography (EEG) were the most common instrumental techniques.

Conclusions:

• This is the first systematic mapping review of AI in schizophrenia spectrum disorders.
• Findings can guide clinicians and researchers in AI methodology application for SSDs.
• Further research is essential to validate the clinical utility and translational applicability of AI algorithms in SSDs.