Affordable, automatic quantitative fall risk assessment based on clinical balance scales and Kinect data

P. Colagiorgio, F. Romano, F. Sardi, M. Moraschini, A. Sozzi, M. Bejor, G. Ricevuti, A. Buizza, S. Ramat

Research output: Contribution to journalArticle

Abstract

The problem of a correct fall risk assessment is becoming more and more critical with the ageing of the population. In spite of the available approaches allowing a quantitative analysis of the human movement control system's performance, the clinical assessment and diagnostic approach to fall risk assessment still relies mostly on non-quantitative exams, such as clinical scales. This work documents our current effort to develop a novel method to assess balance control abilities through a system implementing an automatic evaluation of exercises drawn from balance assessment scales. Our aim is to overcome the classical limits characterizing these scales i.e. limited granularity and inter-/intra-examiner reliability, to obtain objective scores and more detailed information allowing to predict fall risk. We used Microsoft Kinect to record subjects' movements while performing challenging exercises drawn from clinical balance scales. We then computed a set of parameters quantifying the execution of the exercises and fed them to a supervised classifier to perform a classification based on the clinical score. We obtained a good accuracy (~82%) and especially a high sensitivity (~83%).

Fingerprint

Risk assessment
Classifiers
Aging of materials
Control systems
Chemical analysis
Population

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Affordable, automatic quantitative fall risk assessment based on clinical balance scales and Kinect data. / Colagiorgio, P.; Romano, F.; Sardi, F.; Moraschini, M.; Sozzi, A.; Bejor, M.; Ricevuti, G.; Buizza, A.; Ramat, S.

In: Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, Vol. 2014, 2014, p. 3500-3503.

Research output: Contribution to journalArticle

@article{173c1b687342437faab76b6f7b594ee3,
title = "Affordable, automatic quantitative fall risk assessment based on clinical balance scales and Kinect data",
abstract = "The problem of a correct fall risk assessment is becoming more and more critical with the ageing of the population. In spite of the available approaches allowing a quantitative analysis of the human movement control system's performance, the clinical assessment and diagnostic approach to fall risk assessment still relies mostly on non-quantitative exams, such as clinical scales. This work documents our current effort to develop a novel method to assess balance control abilities through a system implementing an automatic evaluation of exercises drawn from balance assessment scales. Our aim is to overcome the classical limits characterizing these scales i.e. limited granularity and inter-/intra-examiner reliability, to obtain objective scores and more detailed information allowing to predict fall risk. We used Microsoft Kinect to record subjects' movements while performing challenging exercises drawn from clinical balance scales. We then computed a set of parameters quantifying the execution of the exercises and fed them to a supervised classifier to perform a classification based on the clinical score. We obtained a good accuracy (~82{\%}) and especially a high sensitivity (~83{\%}).",
author = "P. Colagiorgio and F. Romano and F. Sardi and M. Moraschini and A. Sozzi and M. Bejor and G. Ricevuti and A. Buizza and S. Ramat",
year = "2014",
doi = "10.1109/EMBC.2014.6944377",
language = "English",
volume = "2014",
pages = "3500--3503",
journal = "Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference",
issn = "1557-170X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Affordable, automatic quantitative fall risk assessment based on clinical balance scales and Kinect data

AU - Colagiorgio, P.

AU - Romano, F.

AU - Sardi, F.

AU - Moraschini, M.

AU - Sozzi, A.

AU - Bejor, M.

AU - Ricevuti, G.

AU - Buizza, A.

AU - Ramat, S.

PY - 2014

Y1 - 2014

N2 - The problem of a correct fall risk assessment is becoming more and more critical with the ageing of the population. In spite of the available approaches allowing a quantitative analysis of the human movement control system's performance, the clinical assessment and diagnostic approach to fall risk assessment still relies mostly on non-quantitative exams, such as clinical scales. This work documents our current effort to develop a novel method to assess balance control abilities through a system implementing an automatic evaluation of exercises drawn from balance assessment scales. Our aim is to overcome the classical limits characterizing these scales i.e. limited granularity and inter-/intra-examiner reliability, to obtain objective scores and more detailed information allowing to predict fall risk. We used Microsoft Kinect to record subjects' movements while performing challenging exercises drawn from clinical balance scales. We then computed a set of parameters quantifying the execution of the exercises and fed them to a supervised classifier to perform a classification based on the clinical score. We obtained a good accuracy (~82%) and especially a high sensitivity (~83%).

AB - The problem of a correct fall risk assessment is becoming more and more critical with the ageing of the population. In spite of the available approaches allowing a quantitative analysis of the human movement control system's performance, the clinical assessment and diagnostic approach to fall risk assessment still relies mostly on non-quantitative exams, such as clinical scales. This work documents our current effort to develop a novel method to assess balance control abilities through a system implementing an automatic evaluation of exercises drawn from balance assessment scales. Our aim is to overcome the classical limits characterizing these scales i.e. limited granularity and inter-/intra-examiner reliability, to obtain objective scores and more detailed information allowing to predict fall risk. We used Microsoft Kinect to record subjects' movements while performing challenging exercises drawn from clinical balance scales. We then computed a set of parameters quantifying the execution of the exercises and fed them to a supervised classifier to perform a classification based on the clinical score. We obtained a good accuracy (~82%) and especially a high sensitivity (~83%).

UR - http://www.scopus.com/inward/record.url?scp=84945306065&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945306065&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2014.6944377

DO - 10.1109/EMBC.2014.6944377

M3 - Article

VL - 2014

SP - 3500

EP - 3503

JO - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

JF - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

SN - 1557-170X

ER -