We concluded that it is possible to classify gait episodes of fallers and non-fallers in people with dementia during everyday life using accelerometry.

BackgroundFall events contribute significantly to mortality, morbidity and costs in our ageing population. In order to identify persons at risk and to target preventive measures, many scores and assessment tools have been developed. These often require expertise and are costly to implement. Recent research investigates the use of wearable inertial sensors to provide objective data on motion features which can be used to assess individual fall risk automatically. So far it is unknown how well this new method performs in comparison with conventional fall risk assessment tools. The aim of our research is to compare the predictive performance of our new sensor-based method with conventional and established methods, based on prospective data.MethodsIn a first study phase, 119 inpatients of a geriatric clinic took part in motion measurements using a wireless triaxial accelerometer during a Timed Up&Go (TUG) test and a 20 m walk. Furthermore, the St. Thomas Risk Assessment Tool in Falling Elderly Inpatients (STRATIFY) was performed, and the multidisciplinary geriatric care team estimated the patients' fall risk. In a second follow-up phase of the study, 46 of the participants were interviewed after one year, including a fall and activity assessment. The predictive performances of the TUG, the STRATIFY and team scores are compared. Furthermore, two automatically induced logistic regression models based on conventional clinical and assessment data (CONV) as well as sensor data (SENSOR) are matched.ResultsAmong the risk assessment scores, the geriatric team score (sensitivity 56%, specificity 80%) outperforms STRATIFY and TUG. The induced logistic regression models CONV and SENSOR achieve similar performance values (sensitivity 68%/58%, specificity 74%/78%, AUC 0.74/0.72, +LR 2.64/2.61). Both models are able to identify more persons at risk than the simple scores.ConclusionsSensor-based objective measurements of motion parameters in geriatric patients can be used to assess individual fall risk, and our prediction model's performance matches that of a model based on conventional clinical and assessment data. Sensor-based measurements using a small wearable device may contribute significant information to conventional methods and are feasible in an unsupervised setting. More prospective research is needed to assess the cost-benefit relation of our approach.

Wearable sensor systems which allow for remote or self-monitoring of health-related parameters are regarded as one means to alleviate the consequences of demographic change. This paper aims to summarize current research in wearable sensors as well as in sensor-enhanced health information systems. Wearable sensor technologies are already advanced in terms of their technical capabilities and are frequently used for cardio-vascular monitoring. Epidemiologic predictions suggest that neuropsychiatric diseases will have a growing impact on our health systems and thus should be addressed more intensively. Two current project examples demonstrate the benefit of wearable sensor technologies: long-term, objective measurement under daily-life, unsupervised conditions. Finally, up-to-date approaches for the implementation of sensor-enhanced health information systems are outlined. Wearable sensors are an integral part of future pervasive, ubiquitous and person-centered health care delivery. Future challenges include their integration into sensor-enhanced health information systems and sound evaluation studies involving measures of workload reduction and costs.

Accelerometers are frequently used for activity assessment and as reference devices for counting steps. Their performance on healthy subjects' data is good, but there are doubts as to their applicability on elderly and mobility-impaired subjects. Furthermore, only few step detection algorithms have been published so far, and their performance has not been evaluated on a large, non-laboratory sample. The aim of this paper is to compare the performance of four freely accessible accelerometry-based step detection algorithms in a non-laboratory setting. Two samples of healthy persons (n=140) and mobility-impaired, geriatric in-patients (n=10) wore a single triaxial accelerometer on a waist-belt during unconstrained walking. The relative error rate of the four algorithms on the two samples was compared with reference video recordings. All four algorithms show a fairly poor performance on healthy subjects' (8.4-30.8% relative error rate) and especially geriatric patients' data (28.1-62.1%). Among the tested ones, a simple autocorrelation algorithm works best on both data sets together. More complex algorithms might work better, and more research is needed to evaluate the accuracy of step detection methods on mobility-impaired subjects.