One of the most common assessments for the mobility of older people is the Timed Up and Go test (TUG). Due to its sensitivity regarding the indication of Parkinson’s disease (PD) or increased fall risk in elderly people, this assessment test becomes increasingly relevant, should be automated and should become applicable for unsupervised self-assessments to enable regular examinations of the functional status. With Inertial Measurement Units (IMU) being well suited for automated analyses, we evaluate an IMU-based analysis-system, which automatically detects the TUG execution via machine learning and calculates the test duration. as well as the duration of its single components. The complete TUG was classified with an accuracy of 96% via a rule-based model in a study with 157 participants aged over 70 years. A comparison between the TUG durations determined by IMU and criterion standard measurements (stopwatch and automated/ambient TUG (aTUG) system) showed significant correlations of 0.97 and 0.99, respectively. The classification of the instrumented TUG (iTUG)-components achieved accuracies over 96%, as well. Additionally, the system’s suitability for self-assessments was investigated within a semi-unsupervised situation where a similar movement sequence to the TUG was executed. This preliminary analysis confirmed that the self-selected speed correlates moderately with the speed in the test situation, but differed significantly from each other.

An early detection of functional decline with age is important to start interventions at an early state and to prolong the functional fitness. In order to assure such an early detection, functional assessments must be conducted on a frequent and regular basis. Since the five time chair rise test (5CRT) is a well-established test in the geriatric field, this test should be supported by technology. We introduce an approach that automatically detects the execution of the chair rise test via an inertial sensor integrated into a belt. The system’s suitability was evaluated via 20 subjects aged 72–89 years (78.2 ± 4.6 years) and was measured by a stopwatch, the inertial measurement unit (IMU), a Kinect^® camera and a force plate. A Multilayer Perceptrons-based classifier detects transitions in the IMU data with an F1-Score of around 94.8%. Valid executions of the 5CRT are detected based on the correct occurrence of sequential movements via a rule-based model. The results of the automatically calculated test durations are in good agreement with the stopwatch measurements (correlation coefficient r = 0.93 (p < 0.001)). The analysis of the duration of single test cycles indicates a beginning fatigue at the end of the test. The comparison of the movement pattern within one person shows similar movement patterns, which differ only slightly in form and duration, whereby different subjects indicate variations regarding their performance strategies.

Introduction: Falls are one of the most common causes of emergency hospital visits in older people. Early recognition of an increased fall risk, which can be indicated by the occurrence of near-falls, is important to initiate interventions.Methods: In a study with 87 subjects we simulated near-fall events on a perturbation treadmill and recorded them with inertial measurement units (IMU) at seven different positions. We investigated different machine learning models for the near-fall detection including support vector machines, AdaBoost, convolutional neural networks, and bidirectional long short-term memory networks. Additionally, we analyzed the influence of the sensor position on the classification results.Results: The best results showed a DeepConvLSTM with an F1 score of 0.954 (precision 0.969, recall 0.942) at the sensor position “left wrist.”Discussion: Since these results were obtained in the laboratory, the next step is to evaluate the suitability of the classifiers in the field.

Comprehensive and repetitive assessments are needed to detect physical changes in an older population to prevent functional decline at the earliest possible stage and to initiate preventive interventions. Established instruments like the Timed “Up & Go” (TUG) Test and the Sit-to-Stand Test (SST) require a trained person (e.g., physiotherapist) to assess physical performance. More often, these tests are only applied to a selected group of persons already functionally impaired and not to those who are at potential risk of functional decline. The article introduces the Unsupervised Screening System (USS) for unsupervised self-assessments by older adults and evaluates its validity for the TUG and SST. The USS included ambient and wearable movement sensors to measure the user’s test performance. Sensor datasets of the USS’s light barriers and Inertial Measurement Units (IMU) were analyzed for 91 users aged 73 to 89 years compared to conventional stopwatch measurement. A significant correlation coefficient of 0.89 for the TUG test and of 0.73 for the SST were confirmed among USS’s light barriers. Correspondingly, for the inertial data-based measures, a high and significant correlation of 0.78 for the TUG test and of 0.87 for SST were also found. The USS was a validated and reliable tool to assess TUG and SST.

The Azure Kinect DK is an RGB-D-camera popular in research and studies with humans. For good scientific practice, it is relevant that Azure Kinect yields consistent and reproducible results. We noticed the yielded results were inconsistent. Therefore, we examined 100 body tracking runs per processing mode provided by the Azure Kinect Body Tracking SDK on two different computers using a prerecorded video. We compared those runs with respect to spatiotemporal progression (spatial distribution of joint positions per processing mode and run), derived parameters (bone length), and differences between the computers. We found a previously undocumented converging behavior of joint positions at the start of the body tracking. Euclidean distances of joint positions varied clinically relevantly with up to 87 mm between runs for CUDA and TensorRT; CPU and DirectML had no differences on the same computer. Additionally, we found noticeable differences between two computers. Therefore, we recommend choosing the processing mode carefully, reporting the processing mode, and performing all analyses on the same computer to ensure reproducible results when using Azure Kinect and its body tracking in research. Consequently, results from previous studies with Azure Kinect should be reevaluated, and until then, their findings should be interpreted with caution.