Evolving dynamic self-adaptation policies of mHealth systems for long-term monitoring

Abstract

Tele-rehabilitation can complement traditional rehabilitation therapies by providing valuable information that can help in the evaluation, monitoring, and treatment of patients. Many patient tele-monitoring systems that integrate wearable technology are emerging as an effective tool for the long-term surveillance of rehabilitation progression, enabling continuous sampling of patient real-time movement in a non-invasive way, without affecting the normal daily activity of the outpatient, who, therefore, will not need to make frequent clinic visits. One of the main challenges of tele-rehabilitation systems is to pay special attention to the diversity of dysfunctions in patients by offering devices with customized behaviours adaptable to the physical conditions of each patient at the different stages of the rehabilitation therapy. Long-term monitoring systems need an adaptation policy to autonomously reconfigure their behaviour according to vital signs read during the physical activity of the patient, the remaining battery level, or the required accuracy of collected data. However, it would alsobe desirable to adjust such adaptation policies over time, according to the patient's evolution. This work presents a wearable patient-monitoring system for tele-rehabilitation that is able to dynamically self-configure its internal behaviour to the current context of the outpatient according to a set of adaptation policies that optimize battery consumption, taking into account other QoS parameters at the same time. Our system is also able to self-adapt its internal adaptation policies as a patient's condition improves, while maintaining the system's efficiency. We illustrate our proposal with a real mHealth case study. The results of the experiments show that the system updates the adaptation policies, taking into account specific indicators of the disease. The validation results show that the evolution of the self-adaptation policies correlates with the progression of different patients.

Keywords: Activity recognition; Adaptive systems; Assistive technology; Context awareness; Fuzzy systems; Internet of Things; Mobile applications; Reconfigurable architectures; Software product lines; Ubiquitous computing; Wearable computers.