Authors:
Joana Silva
1
;
João Madureira
1
;
Cláudia Tonelo
2
;
Daniela Baltazar
3
;
Catarina Silva
3
;
Anabela Martins
3
;
Carlos Alcobia
2
and
Inês Sousa
1
Affiliations:
1
Fraunhofer Portugal AICOS, Portugal
;
2
Sensing Future Technologies, Portugal
;
3
ESTeSC Coimbra Health School, Portugal
Keyword(s):
Fall Risk Assessment, Inertial Sensors, Pressure Platform, Timed-up and Go Test, Sit-to-Stand, 4-Stage Test, Machine Learning, Classification, Regression.
Abstract:
Traditional fall risk assessment tests are based on timing certain physical tasks, such as the timed up and go
test, counting the number of repetitions in a certain time-frame, as the 30-second sit-to-stand or observation
such as the 4-stage balance test. A systematic comparison of multifactorial assessment tools and their
instrumentation for fall risk classification based on machine learning approaches were studied for a
population of 296 community-dwelling older persons aged above 50 years old. Using features from inertial
sensors and a pressure platform by opposition to using solely the tests scores and personal metrics increased
the F-Score of Naïve Bayes classifier from 72.85% to 92.61%. Functional abilities revealed higher
association with fall level than personal conditions such as gender, age and health conditions.