Software architecture optimization of mobile biomedical sensor-based tools providing analytical services for disease diagnostics and assistance

Abstract

The development of highly specialized mobile applications and systems has risen for several years, as we observe rapid deployment of innovative biomedical sensors and wearable technologies. The experiences gathered over 10 years of mobile medical software development, provide practical recommendations for architectural concepts utilized in analytical health-based services. Constructed systems and mobile applications in majority of cases utilize biomedical signals to identify health state of a patient, as well as to evaluate or estimate the intensity of disease symptoms. Based on these experiences, this paper proposes architectural concepts, for both mobile and web-based components aimed at acquisition and processing of biomedical data in large scale medical systems dedicated for monitoring of patients. The major assumptions for this research included utilization of wearable and mobile technologies, supporting maximum number of wearable diagnostic technologies including inertial and biomedical data streams. Although medical diagnostics and decision algorithms have not been the main aim of the research, this preliminary phase was crucial to test capabilities of existing off-the-shelf technologies and functional responsibilities of system’s logic components. Optimized architecture variants contain several schemes for data processing, moving the responsibility for signal feature extraction, data classification and pattern recognition from wearable to mobile application and further to server services. The analysis of delays during data transmission and processing, provided architecture variants’ pros and cons but most of captured recommendations for applicability of such mechanisms in the domains of medical, military and fitness. To evaluate and construct architecture, a set of alternative technology stacks and quantitative measures has been defined. The major architecture characteristics (high availability, scalability, reliability) have been defined imposing asynchronous processing of sensor data, efficient data representation, iterative reporting, event-driven processing, restricting pulling operations. Analytical processing of inertial or biomedical sensor data requires filtering, time-window processing, aggregation, application of specific algorithmic transformations etc. Combination of several data sources and correlation of biomedical parameters between each other and specific patient’s health state, extend predefined ordinarily used event triggering rules. This work provides construction details of wearable-based mobile systems with specialized aimed at health state identification and monitoring. Undertaken construction decisions have been confirmed and justified based on functional and stress tests of system components. The first deployment attempt of designed architecture and its implementation has been aimed at remote, mobile monitoring of elderly people, and preconfigured for crucial health event recognition – fainting, stroke, cardiac arrest, seizures, some classes of neurological disorders and derivatives of such conditions.