Elderly Risk Assessment of Falls with BSN R.C. King1, L. Atallah1, C. Wong1, F. Miskelly2 and G-Z. Yang1 Department of Computing1, Charing Cross Hospital2 Imperial College London London rachel.king@imperial.ac.uk Abstract- Due to the natural aging process, the risks associated with falling can increase significantly. For the elderly, this usually marks a rapid deterioration of their health. While there are identified strategies that can be adopted to reduce the number of falls, it is still not possible to prevent all falls. Clinically, the Tinetti Gait and Balance Assessment has been widely used to assess the risk of falls in elderly by examining balance and gait. This paper presents our initial results of using an ear-worn BSN sensor to detect aspects of the Tinetti Gait and Balance Assessment to predict the risk of falls compared to a healthy control cohort. For this study, data was collected from a control cohort of 12 healthy volunteers and a cohort of 16 elderly fallers of varying degrees of risk. The results derived have shown that it is possible to directly detect some aspects of the Tinetti Gait and Balance Assessment and the Timed Up and Go test, demonstrating the potential value of using the platform for continuous assessment in a home environment. Keywords-Body Sensor Networks elderly faller balance assessment I. INTRODUCTION Falls are a serious problem in the aging population. They can indicate deterioration in health and are related to a decrease in musculoskeletal and motor-control function, with identified rates of mortality and morbidity in the elderly [1]. After the age of 60, there is a general rise in the number and severity of the falls, with an increased tendency linked to further complications. After this age, these rates increase substantially [2]. Falls affect elderly living not only in the community, but also in nursing homes and hospitals. For elderly living in the community, however, help or medical assistance can be difficult to summon and victims could remain without assistance for many hours. While falling is not in itself a normal aspect of aging, it can be indicative of an underlying medical problem or some environmental hazard. These are defined as risk factors and can be classified as either intrinsic, or, extrinsic. Intrinsic risk factors generally include changes in the faller due to the aging process such as changes in cognitive, visual, or neurological functioning and musculoskeletal, sensory or cardiovascular impairment. Extrinsic factors are generally related to the environment including trip hazards, poor lighting, lack of hand rails, and some types of medication [3]. There are often complex interactions between the intrinsic and extrinsic risk factors that can increase the likelihood of a fall. For example, a faller with poor vision may not see a telephone cable in a poorly lit room and trip over it. In terms of the prevention of falls, several strategies can be adopted [1]. It has been found that exercise can help improve balance and reduce the number of falls. Education can draw the attention of the elderly to their surrounding environment such that they become aware of possible trip hazards such as rugs, electrical cables and poor lighting. Occupational therapists can also visit homes to assess the home and recommend improvements, help prevent and reduce the incidence of falls [1]. Medical evaluation can identify possible intrinsic causes of falls and review the medication required for fall prevention. There are also several balance and mobility tests available that can be carried out by trained personnel to assess the risks. These include the Functional Reach test, Romberg test, the Hendrich Fall Risk Model, the timed and un-timed Get-Up- and-Go, and the Tinetti Gait and Balance Assessment [4, 5]. The majority of these observe the patient performing a number of activities, such as standing, sitting, walking, turning, and in the case of the functional reach test, the degree of flexibility, to determine the risk a person has of falling. Commercially, there are also products available to help reduce the risk of injury caused by a fall and to summon assistance should a fall occur. Hip protectors can be worn discreetly beneath normal clothes to reduce the impact of a fall. The use of airbags has also been proposed [6]. Pendent alarms can also worn around the neck to provide a method of attracting attention should a fall occur [7], however, this is only effective if the wearer is conscious and is able to operate the alarm. There are two main complementary areas of research that need to be addressed the prevention and reduction in risk of falls, and the detection of falls. With recent advances of mircoelectromechanical (MEMs) devices, such as accelerometers and gyroscopes, there has been a great focus on developing automated fall detection systems [8]. To attempt to prevent falls, clinical assessments as described above are commonly used. However, as with any observation based assessment, it can be subjective and can only offer a snap-shot of the patient���s health. Liu et al. [9] developed a pair of e-textile trousers, fitted with accelerometers on the ankles and knees, and piezo-sensors to 2010 International Conference on Body Sensor Networks 978-0-7695-4065-8/10 $26.00 �� 2010 IEEE DOI 10.1109/BSN.2010.42 30