Phone Based Fall Risk Prediction

Abstract

Falls in older people can represent serious individual and socioeconomic problems. With the increasing number of older people in the population, management of falls is becoming a challenge.It is now recognized that several risk factors for falling can be identified, and specific interventions can be designed in order to reduce those risks. Several tools were then developed and are now available to screen for fall risk. However, these tools are applied with low frequency, usually requiring the use of expensive equipments that can only be manipulated by experts. This poses some constraints on the prevention of falls, since when these techniques are applied, it can be too late.In order to improve the earlier detection of risks and the application of fall prevention strategies, new community based solutions must be developed. In this project, the mobile phone was purposed as a potential instrument to perform fall risk screening. Several strategies were then evaluated to be adapted to the phone for fall risk screening purposes.Phone's inertial sensors were used to extract some parameters of gait that were related with an increased risk of falling. Foot contacts, gait phases, step length, step duration, walking velocity and variability parameters could then be determined from sensors data. Acceptable measures of step length and walking velocity could be obtained. Additionally, other risk factors were selected to be assessed by self-report, using some clinical scales/questionnaires.Results suggest that phone can be used as a major strategy to improve fall prevention, being a great value for older persons and society.i ii ResumoUma queda num idoso pode resultar em graves problemas individuais e socioeconómicos. Com o aumento do número de idosos na população, a gestão de quedas está a tornar-se um desafio.Actualmente, é possível identificar vários factores de risco para a ocorrência de quedas bem como reduzir esses riscos, através da aplicação da aplicação de intervenções especí-ficas. Nesse sentido, há já algumas ferramentas actualmente disponíveis para avaliar o risco de queda. Estas ferramentas no entanto usadas com baixa frequência, exigindo o uso de equipamentos caros que apenas podem ser manipulados por pessoas qualificadas. Muitas vezes, estas técnicas podem já ser aplicadas tarde demais.Para que a detecção dos riscos e a aplicação de estratégias de prevenção de quedas possa ser feita mais precocemente, é necessário o desenvolvimento de novas soluções dirigidas à população. Neste projecto, foi proposto o uso do telemóvel para a detecção do risco de queda nos idosos.Os sinais dos sensores do telemóvel foram utilizados para extrair parâmetros da marcha relacionados com um risco de queda aumentado. A partir deles, os contactos do pé com o chão, as fases da marcha, o tamanho e duração dos passos, a velocidade e parâmetros que quantificam a variabilidade da marcha puderam ser determinados. Medidas aceitáveis do tamanho dos passos e da velocidade foram obtidas. Adicionalmente, outros factores de risco foram sele...

A Review on Fall Prediction and Prevention System for Personal Devices: Evaluation and Experimental Results

“…People with increased fall risk tend to walk slowly. As such, the actual fall risk can be quantified according to gait speed [29]. Gait speed is estimated by measuring duration and length of user's steps.…”

“…The depression of the acceleration signal comes from the movement of the body, and the angular rotation is due to the forward and backward leans of the trunk during transition. technique eliminates some frequencies from the original signal to attenuate the background noise and to remove undesired frequencies [29,35]. Frequently used filters in FPPSs are high-pass filters, which eliminate frequencies lower than the cutoff frequency, and low-pass filters, which pass only frequencies lower than a certain threshold frequency.…”

“…As mentioned in Section 2.2, low gait speed increases the risk of a fall. The average speed of the gait can be measured to estimate the fall risk [29].…”

“…They are based on the variance of the signal V ( ( )): Peak is the absolute maximum value of the signal over the period of time, and peak-to-peak is the difference between the minimum and the maximum value of the signal over the period of time. The peak-to-peak acceleration amplitude and the peak-to-peak acceleration derivative are two features used in FPPSs [29].…”

Analysis of Android Device-Based Solutions for Fall Detection

“…Android Smartphones have also been considered [ 79 ] in systems devoted to safety zone monitoring and wandering detection for people suffering dementia. Likewise, Guimaraes et al utilize in [ 80 ] a SP-based Android platform to predict fall risks. By using the internal accelerometer in the SP, the developed program is in charge of measuring the step length, duration and velocity from acceleration signals during normal gait.…”