JMIR Publications

ABSTRACT

The Internet of Things (IoT) is transforming various industries, including healthcare. IoT-based systems are increasingly prevalent in consumer health applications, while intelligent smart devices equipped with sophisticated sensors are gaining recognition for their potential to improve clinical care practice and decision-making. Cancer care is a particularly promising area for IoT applications, enabling real-time, personalized interventions; however, empirical intervention research on the effect of IoT in this field is limited, partly due to the complexities arising from the nature of cancer as a complex, dynamic disease. This complexity and the paucity of available IoT-generated data for research underscores an opportunity to apply mathematical modelling to understand IoT effects under various scenarios. These analytical and in silico mathematical approaches are especially useful with limited data. They allow analysis of treatment uncertainties and patient responses, effectively balancing tradeoffs between patient preferences, clinical outcomes, and health system factors. This survey paper, grounded in mathematical oncology, explores how these approaches could be applied at multiple levels of analysis to understand the impact of these IoT interventions, guide their implementation, and optimize their effectiveness in oncology services.