Falls in the elderly are a major problem for society. A serious consequence of falling is the "long-lie". A fall detection system and algorithm, incorporated into a custom designed garment has been developed which will automatically detect falls and potentially reduce the incidence of the "long-lie". The developed fall detection system consists of a tri-axial accelerometer, microcontroller, battery and Bluetooth module. This sensor is attached to a custom designed vest, designed to be worn by the elderly person under clothing. The fall detection algorithm was developed and incorporates both impact and posture detection capability. The vest was developed using feedback from elderly subjects donning, wearing and doffing a prototype vests and subsequently filling in a questionnaire. The re-designed vest and fall algorithm was tested in two clinical trials. Trial 1: young healthy subjects performing normal activities of daily living (ADL) and falls onto crash mats, while wearing the vest and sensor. Trial 2: The system was subsequently tested using 10 elderly subjects wearing the system over the course of 4 weeks, for 8 hours a day. Two teams of 5 elderly subjects wore the sensor system in turn for 2 week each. Results from trial 1, show that falls can be distinguished from normal activities with a sensitivity >90% and a specificity of >99%, from a total data set of 264 falls and 165 normal ADL. In trial 2, over 833 hours of monitoring was performed over the course of the four weeks from the elderly subjects, during normal daily activity. In this time no actual falls were recorded, however the system registered a total of the 42 fall-alerts. Further development of the system will include a more accurate fall-detection algorithm, more comfortable sensor attachment method, lighter and smaller sensor as well as, mobility monitoring and energy expenditure measurement. A fall detection system incorporated into a custom designed garment has been developed which will help reduce the incidence of the long-lie, when falls occur in the elderly population.
[1]
N. Noury.
A smart sensor for the remote follow up of activity and fall detection of the elderly
,
2002,
2nd Annual International IEEE-EMBS Special Topic Conference on Microtechnologies in Medicine and Biology. Proceedings (Cat. No.02EX578).
[2]
A McIntosh,et al.
The design of a practical and reliable fall detector for community and institutional telecare
,
2000,
Journal of telemedicine and telecare.
[3]
B. Isaacs,et al.
How dangerous are falls in old people at home?
,
1981,
British medical journal.
[4]
G M Lyons,et al.
Long-term mobility monitoring of older adults using accelerometers in a clinical environment
,
2004,
Clinical rehabilitation.
[5]
H. Menz,et al.
Falls in Older People: Risk Factors and Strategies for Prevention
,
2000
.
[6]
A K Bourke,et al.
Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm.
,
2007,
Gait & posture.
[7]
Maarit Kangas,et al.
Comparison of low-complexity fall detection algorithms for body attached accelerometers.
,
2008,
Gait & posture.
[8]
Nigel H. Lovell,et al.
Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring
,
2006,
IEEE Transactions on Information Technology in Biomedicine.