Početna » Sinteza 2026 - International Scientific Conference on Information Technology, Computer Science, and Data Science » Data Science and Applications
A Review of AI Methods Used in Digital Twins for Mental Health Monitoring
Abstract:
Digital twins represent a novel approach to the continuous monitoring of mental health. This paper provides a review and critical analysis of four representative papers that apply various AI methods within digital twins for mental health monitoring: TwinMind (passive smartphone sensing with XGBoost and SHAP), Quamer et al. (multimodal fusion of facial, vocal, and physiological signals using a Swin Transformer-TGNN architecture), Wang et al. (EEG signals with a genetic algorithm for accelerating explainable AI methods), and Abilkaiyrkyzy et al. (a BERT based chatbot for conversational depression screening). For each work we described: the data, the AI/ML model, the explainability mechanism and the achieved results. The works are analysed from multiple perspectives: accuracy, explainability and practical applicability. The results show that passive sensing offers the best trade off between practicality and accuracy, whereas multimodal fusion achieves the highest accuracy at the cost of expensive equipment. Genetic algorithms significantly accelerate XAI (from ~30s to <10s), which is of great importance for real time operation. The chatbot exhibits high usability but low accuracy. The conclusion is that there is no universally optimal solution. Instead, the choice depends on the context. Future directions include federated learning for privacy preservation and hybrid architectures that combine sensors and conversational agents.
CITATION:
IEEE format
N. Radešić, N. Jeličić, “A Review of AI Methods Used in Digital Twins for Mental Health Monitoring,” in Sinteza 2026 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2026, pp. 275-282. doi:10.15308/Sinteza-2026-275-282
APA format
Radešić, N., Jeličić, N. (2026). A Review of AI Methods Used in Digital Twins for Mental Health Monitoring. Paper presented at Sinteza 2026 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2026-275-282
BibTeX format
Download
RefWorks Tagged format
Download
