Bridging the Gap Between Research and Practice: A Systematic Literature Review of IoT and Machine Learning Applications in Mental Healthcare Systems

Objective: This study conducts a systematic review of Internet of Things (IoT) and Machine Learning (ML) applications to identify existing gaps and scope for improvisation. Design: Databases such as Scopus, Web of Science, PubMed, IEEE Xplore, and ScienceDirect were searched to find relevant studies focusing on IoT and ML in mental healthcare. Using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, 18 studies were selected for the final review. Cyber-Physical Systems (CPS) theory and thematic analysis were employed to answer research questions. Result/outcomes: Four dimensions were identified as: continuous behavioural monitoring, ML-driven predictive analytics, real-time adaptive mental healthcare interventions, and responsible clinical deployment. IoT and ML technologies were found to have significantly improved patients’ monitoring, predicting risks, and enhancing interventions using digital phenotyping, wearable data sensing, digital phenotyping and AI-driven analytics. However, some challenges in effective implementation of IoT and ML applications included explainability, ethical governance, interoperability, and clinical integration. Conclusion: An Operational Framework for Real-Time IoT-ML Mental Healthcare Systems is proposed to bring together sensing, analytics, and interventions. This framework recommends taking adequate actions to support either scalability or clinically sustainable mental healthcare delivery.