A Microservices e-Health System for Ecological Frailty Assessment Using Wearables

Abstract

The population in developed countries is aging and this fact results in high elderly health costs, as well as a decrease in the number of active working members to support these costs. This could lead to a collapse of the current systems. One of the first insights of the decline in elderly people is frailty, which could be decelerated if it is detected at an early stage. Nowadays, health professionals measure frailty manually through questionnaires and tests of strength or gait focused on the physical dimension. Sensors are increasingly used to measure and monitor different e-health indicators while the user is performing Basic Activities of Daily Life (BADL). In this paper, we present a system based on microservices architecture, which collects sensory data while the older adults perform Instrumental ADLs (IADLs) in combination with BADLs. IADLs involve physical dimension, but also cognitive and social dimensions. With the sensory data we built a machine learning model to assess frailty status which outperforms the previous works that only used BADLs. Our model is accurate, ecological, non-intrusive, flexible and can help health professionals to automatically detect frailty.

Unobtrusive Sensors for the Assessment of Older Adult’s Frailty: A Scoping Review

“…These phenomena have been measured transparently in many studies (16%, 9%, and 22%, respectively), and so have been mobility patterns (4%), stair climbing (3%), heart rate (1%), and arm movements (1%). All the studies relying on activity patterns (15 studies), mobility patterns (three studies), stair climbing (two studies), heart rate (one study), and arm movements (one study) involved transparent activities and did not involve any non-transparent activities [ 64 , 106 , 107 , 108 , 109 , 110 , 111 ]. Together, they represent 29% of all the studies.…”

“…The sensors in both studies on stair climbing were tested in controlled conditions without an algorithm for the automatic detection of stairs [ 64 , 109 ]. Finally, arm movements were monitored during the execution of a predefined procedure while buying a 1 kg package of salt in a supermarket [ 111 ].…”

“…The study on heart rate measured heart rate variability quantified with the triangular index [ 110 ]. Finally, the study on arm movements measured mean, standard deviation, skewness, kurtosis, maximum, minimum, amplitude, and energy of 3D acceleration, 3D gyroscope, and heart rate [ 111 ].…”

Reducing Response Time in Motor Imagery Using A Headband and Deep Learning

“…In this line, another of our objectives is the recognition of activities, mental state, and emotions of the users while they are performing daily life activities and the relationship with their health status. The headband will be part of our previous e-health system based on microservices and the cloud [ 42 , 47 ], which includes other wearable sensors and applications to monitor and intervene in the healthcare of the elderly. Thus, the integration of the proposal presented in this paper with our previously designed e-health system will be able to contribute to a practical solution for healthcare systems.…”

“…For example, if we have a window size of 2 s and sampling rate is 256 Hz, the number of windows (timesteps) will be 512. We tested with several windows sizes (0.01, 0.025, 0.05, 0.1, 0.25, 0.5, 1, 1.5, 2, 2.5, and 5), in order to get the best performance for every session and window (as in previous works [ 42 , 43 ]): …”