Employing time-series forecasting to historical medical data: an application towards early prognosis within elderly health monitoring environments
Antonis S. Billis, Panagiotis D. Bamidis · International Conference on Artificial Intelligence · 2014
This work describes a first attempt to apply time-series forecasting analysis to health historical data in order to perform prediction of early pathological signs within telehealth applications, such as the Ambient Assisted Living environments for the elderly. A benchmark of state-of-the-art learning methods were applied to a set of artificial time-series data, simulating hypertensive patient profiles, based on blood pressure measurements. Results provided a fair proof of our initial hypothesis. Based on this first experimentation, our plans are to further investigate these findings in real -life or lab settings with seniors, thus proving the usefulness of time-series forecasting as a monitoring tool and an early prognosis mechanism in telehealth systems.