Reducing fall incidence in community elders by telecare using predictive systems

Abstract

Sensors have been developed to measure the relevant parameters that are associated with falls of the elderly living in the community; these include mobility, transfer rate, weight and impact history. The sensor outputs are fed into a computer system together with other bio-medical factors such as age, sex, eye-sight and medication. A predictive algorithm is described which determines the likelihood of a fall; this predictive system may form the basis of a practical telecare method to enable early intervention and reduce the number of falls.

A Review of Approaches to Mobility Telemonitoring of the Elderly in Their Living Environment

“…3(a)) 50 under the carpets and a vibration detector on the bed. These passive sensors raised an alert unless the 26,50 An unobtrusive pad placed under a mat to detect movement Smart tiles 37 Footstep detection tiles, which can identify a subject and the direction in which they are walking Passive infrared sensors 3,4,34,42,[54][55][56] Detects movement by responding at any heat variations. Can be used in broad mode to detect presence in a room or in narrow mode to detect presence in an area.…”

Phone Based Fall Risk Prediction

“…The calculus of a likelihood of a fall implies the use of logistic regression methods to estimate the regression coefficients of each predictor of falling, as suggested by different articles (c.f. [61,62]). Ganz et al (2007) used likelihood ratios to calculate the probability of fall for a particular patient [25].…”

“…building a risk profile through a multidimensional risk screening) and then combining them through the attribution of different weights to each risk factor. As a result, a likelihood of falling should be calculated [61,62,25]. The calculus of a likelihood of a fall implies the use of logistic regression methods to estimate the regression coefficients of each predictor of falling, as suggested by different articles (c.f.…”

“…Some articles suggest the quantification of the patient's global risk of falling, so that an intervention is done when the risk exceeds a certain value (refer to [61], [25] and [62]). Global risk's quantification can be achieved by accessing different risk factors (i.e.…”

Algorithms for Smart Spaces

“…Many of the efforts offer supporting technologies in specialized areas, such as using computer vision techniques to track inhabitants through the environment and specialized sensors to detect falls or other crises. Some special-purpose prediction algorithms have been implemented using factors such as measurement of stand-sit and sit-stand transitions and medical history [36][37][38]42,43], but are limited in terms of what they predict and how they apply the results. Remote monitoring systems have been designed with the common motivation that learning and predicting inhabitant activities is key for health monitoring, but very little work has combined the remote monitoring capabilities with prediction for the purpose of health monitoring.…”