An investigation of innovative computational approaches utilizing auditory, visual, and multimedia data to enhance quality of clinical practices in mental health: a systematic literature review utilizing the PRISMA framework
Neural Computing and Applications, cilt.38, sa.20, 2026 (Scopus)
- Yayın Türü: Makale / Derleme
- Cilt numarası: 38 Sayı: 20
- Basım Tarihi: 2026
- Doi Numarası: 10.1007/s00521-026-12410-7
- Dergi Adı: Neural Computing and Applications
- Derginin Tarandığı İndeksler: Scopus, Aerospace Database, Applied Science & Technology Source, Compendex, Index Islamicus, INSPEC, zbMATH, Academic Search Ultimate (EBSCO), Engineering Source (EBSCO), Technology Collection (ProQuest)
- Anahtar Kelimeler: Anxiety, Deep learning, Depression, Diagnosis, Machine learning, Monitoring, Multi-modal data, Neural networks, Psychosis, Treatment
- Recep Tayyip Erdoğan Üniversitesi Adresli: Evet
Özet
Psychiatric disorders are often difficult to diagnose and monitor due to their subjective symptomatology and the limitations of traditional clinical methods. Recent computational advances that utilize auditory, visual, and multimodal data offer promising alternatives for enhancing objectivity in early detection, treatment, and monitoring processes. This systematic review investigates current research employing such methods, focusing on their clinical relevance and methodological robustness. A comprehensive literature search was conducted in September and October 2024 across major databases, including ACM Library, APA PsycInfo, PsycArticles, ISI-Web of Science, IEEE Xplore, PubMed, Livivo, ScienceDirect-Elsevier, and Scopus, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework. Eligible studies were analyzed concerning the computational techniques used, the data types employed, the psychiatric conditions addressed, and their integration into clinical settings. The findings reveal a significant increase in machine learning and multimodal approaches after the COVID-19 pandemic, especially in depression detection. However, a key gap in the literature is the lack of diverse, cross-cultural datasets that capture clear and representative facial and audio data. We conclude that future research should prioritize the development of such datasets and the application of these methods to a broader spectrum of psychiatric disorders.