A review on integrating immersive technology, machine learning, and blockchain technologies in crime scene investigations

While machine learning, blockchain, and immersive technologies have demonstrated significant benefits across many forensic science domains, their application within crime scene investigations (CSIs) remains fragmented. This study presents a systematic literature review (SLR) of 161 publications (2015–2025) examining the application of machine learning (ML), blockchain, and immersive technologies in crime scene investigations (CSIs). Following PRISMA 2020 guidelines, the review synthesizes fragmented research to evaluate technological contributions, adoption trends, and integration challenges across forensic workflows. The results show that immersive technologies enhance spatial reconstruction, scene re-visitation, and courtroom communication. ML supports automated forensic analysis through classification, detection, and predictive modeling in both physical and digital forensic domains. Blockchain technologies provide evidence integrity through secure, tamper-resistant, and decentralized evidence management and chain-of-custody verification. However, key limitations persist, including blockchain scalability and energy constraints, ML data dependency and interpretability issues, and hardware and deployment barriers in immersive systems. A key finding of the review is the absence of fully integrated frameworks combining all three technologies within a unified CSI pipeline. To address this gap, the study proposes the Perception–Cognition–Trust (PCT) framework, which positions immersive technologies, ML, and blockchain as complementary layers supporting perception, analysis, and evidentiary integrity. The study provides a foundation for future work, highlighting the need for empirical validation, legal harmonization, and human-centric design in next-generation forensic systems.