Summary: Background: Falls are a predominant problem in our aging society, often leading to severe somatic and psychological consequences, and having an incidence of about 30% in the group of persons aged 65 years or above. In order to identify persons at risk, many assessment tools and tests have been developed, but most of these have to be conducted in a supervised setting and are dependent on an expert rater.Objectives: The overall aim of our research work is to develop an objective and unobtrusive method to determine individual fall risk based on the use of motion sensor data. The aims of our work for this paper are to derive a fall risk model based on sensor data that may potentially be measured during typical activities of daily life (aim #1), and to evaluate the resulting model with data from a one-year follow-up study (aim #2).Methods: A sample of n = 119 geriatric inpatients wore an accelerometer on the waist during a Timed ‘Up & Go’ test and a 20 m walk. Fifty patients were included in a one-year follow-up study, assessing fall events and scoring average physical activity at home in telephone interviews. The sensor data were processed to extract gait and dynamic balance parameters, from which four fall risk models – two classification trees and two logistic regression models – were computed: models CT#1 and SL#1 using accelerometer data only, models CT#2 and SL#2 including the physical activity score. The risk models were evaluated in a ten-times tenfold cross-validation procedure, calculating sensitivity (SENS), speci ficity (SPEC), positive and negative predictive values (PPV, NPV), classification accuracy, area under the curve (AUC) and the Brier score.Results: Both classification trees show a fair to good performance (models CT#1/ CT#2): SENS 74% / 58%, SPEC 96% / 82%, PPV 92% / 74%, NPV 77%/82%, accuracy 80% / 78%, AUC 0.83 / 0.87 and Brier scores 0.14 / 0.14. The logistic regression models (SL#1/ SL#2) perform worse: SENS 42% / 58%, SPEC 82% / 78%, PPV 62% / 65%, NPV 67% / 72%, accuracy 65% /70%, AUC 0.65 / 0.72 and Brier scores 0.23 / 0.21.Conclusions: Our results suggest that accelerometer data may be used to predict falls in an unsupervised setting. Furthermore, the parameters used for prediction are measurable with an unobtrusive sensor device during normal activities of daily living. These promising results have to be validated in a larger, long-term prospective trial.

Fall 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.

Falls have various causes and are often associated with mobility impairments. Preventive steps to avoid falls may be initiated, if an increasing fall risk could be detected in time. The objective of this article is to identify an automated sensor-based method to determine fall risk of patients based on objectively measured gait parameters. One hundred fifty-one healthy subjects and 90 subjects at risk of falling were measured during a Timed ‘Up & Go’ test with a single triaxial acceleration sensor worn on a waist belt. The fall risk was assessed using the STRATIFY score. A decision tree induction algorithm was used to distinguish between subjects with high and low risk using the determined gait parameters. The results of the risk classification produce an overall accuracy of 90.4% in relation to STRATIFY score. The sensitivity amount to 89.4%, the specificity to 91.0% and the reliability parameter κ equals 0.79. The method presented is able to distinguish between subjects with high and low fall risk. It is unobtrusive and therefore may be applied over extended time periods. A subsequent study is needed to confirm the model's suitability for data recorded in patients' everyday lives.

Marschollek M, et al. Healthc Inform Res. 2012 Jun;18(2):97-104. http://dx.doi.org/10.4258/hir.2012.18.2.97

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.