Evaluation of Orthostatic Reactions in Real-World Environments Using Wearable Sensors.

As global life expectancy is constantly rising, the early detection of age-related, neurodegenerative diseases, such as Parkinson's disease, is becoming increasingly important. Patients suffering from Parkinson's disease often show autonomic nervous system dysfunction which is why its examination is an important diagnostic tool. Measuring the response of the heart rate (variability) to postural transitions and thereby assessing the orthostatic reaction is a common indicator of autonomic nervous system functioning. However, since these measurements are commonly performed in a clinical environment, results can be impaired by the white coat effect. To reduce this influence as well as inter- and intra-day variations, our work aims to investigate the assessment of orthostatic reactions in free-living environments. We collected IMU and ECG data of seven healthy participants over four days and evaluated differences in orthostatic reactions between standardized tests at lab, at home, as well as unsupervised recordings during real-world conditions. Except for the first lab recording, we detected significant changes in heart rate due to postural transitions in all recording settings, with the strongest response occurring during standardized tests at home. Our findings show that real-world assessment of orthostatic reactions is possible and provides comparable results to supervised assessments in lab settings. Additionally, our results indicate high inter- and intra-day variability which motivates the continuous orthostatic reaction measurement over the span of multiple days. We are convinced that our presented approach provides a first step towards unobtrusive assessment of orthostatic reactions in real-world environments, which might enable a more reliable early detection of disorders of the autonomic nervous system.

Detection of Unsupervised Standardized Gait Tests From Real-World Inertial Sensor Data in Parkinson's Disease.

Gait tests as part of home monitoring study protocols for patients with movement disorders may provide valuable standardized anchor-points for real-world gait analysis using inertial measurement units (IMUs). However, analyzing unsupervised gait tests relies on reliable test annotations by the patients requiring a potentially error-prone interaction with the recording system. To overcome this limitation, this work presents a novel algorithmic pipeline for the automated detection of unsupervised standardized gait tests from continuous real-world IMU data. In a study with twelve Parkinson's disease patients, we recorded real-world gait data over two weeks using foot-worn IMUs. During continuous daily recordings, the participants performed series of three consecutive 4×10 -Meters-Walking-Tests ( 4×10 MWTs) at different walking speeds, besides their usual daily-living activities. The algorithm first detected these gait test series using a gait sequence detection algorithm, a peak enhancement pipeline, and subsequence Dynamic Time Warping and then decomposed them into single 4×10 MWTs based on the walking speed. In the evaluation with 419 available gait test series, the detection reached an F1-score of 88.9% and the decomposition an F1-score of 94.0%. A concurrent validity evaluation revealed very good agreement between spatio-temporal gait parameters derived from manually labelled and automatically detected 4×10 MWTs. Our algorithm allows to remove the burden of system interaction from the patients and reduces the time for manual data annotation for researchers. The study contributes to an improved automated processing of real-world IMU gait data and enables a simple integration of standardized tests into continuous long-term recordings. This will help to bridge the gap between supervised and unsupervised gait assessment.