The Efficacy of Internet of Medical Things (IoMT) and Cloud-Fog Computing in Monitoring Neuro-Oncology Patients: A Systematic Literature Review

In the emerging field of cardio-brain oncology, the continuous monitoring of physiological “cross-talk” between the neurological and cardiovascular systems is vital. Traditional monitoring frameworks often suffer from high latency and data silos, which can be detrimental for brain cancer patients at risk of sudden seizures or treatment-induced cardiotoxicity. The integration of the Internet of Medical Things (IoMT) with distributed computing architectures—specifically Cloud, Fog, and Edge computing—offers a transformative solution for real-time patient oversight. This systematic review aims to synthesize the current state of literature (2018–2025) regarding the architectural efficacy of IoMT systems in neuro-oncology. The study evaluates how different computing layers address the high-bandwidth and low-latency requirements of multi-modal data, such as EEG and ECG signals. Following the PRISMA 2020 guidelines, a systematic search was conducted across PubMed, Scopus, IEEE Xplore, and ACM Digital Library. Studies were screened based on their integration of IoMT architectures with oncological monitoring. Data extraction focused on latency metrics, diagnostic accuracy of integrated AI models, and energy efficiency. The review identifies a significant shift toward “Fog-driven” architectures, which reduce alert latency by over 60% compared to traditional Cloud-only systems. Analysis of the literature reveals that hybrid Deep Learning models (CNN-LSTM) deployed at the Fog layer achieve an average diagnostic accuracy of 95–98% for detecting acute physiological anomalies. Furthermore, emerging trends in 2025 highlight the use of “TinyML” for on-device processing to enhance battery longevity in wearable biosensors. While IoMT-enabled Cloud-Fog frameworks provide the necessary infrastructure for real-time cardio-brain monitoring, gaps remain in data security and interoperability. This chapter provides a roadmap for future research, emphasizing the need for secure, explainable AI (XAI) to foster clinical adoption in precision oncology.