No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Enhancing FoG detection by means of postural context using a waist accelerometer
Abstract
Objectives
Current FoG detection algorithms depend on movement frequencies and, thus, false positives could appear during daily life of patients. The aim of this study is to analyse the contextualization of FoG detection based on a waist inertial sensor by including a posture detection algorithm previously validated.
Methods
20 PD patients (mean age: 69.3, std: 7.05 and Hoehn and Yahr mean: 2.74, std: 0.41), 10 freezers and 10 non-freezers, performed a set of predefined activities at their home during approximately 20 minutes, both in ON and OFF motor states. Video recordings were obtained as gold-standard, synchronized with the inertial signals and labelled by experienced therapists. Signals used belong to REMPARK database (www.rempark.eu).
FoG algorithm originally developed by Moore and extended by Bächlin has been applied. Sensitivity has been determined from freezer patients and specificity from non-freezers. Optimal FoG detection parameters (FI, PB) were found by maximizing the geometric mean among sensitivity and specificity. The enhancing effect of posture contextualization is measured on optimal FoG detection by rejecting those episodes arisen when patients are sitting.
Results
FoG detection with optimal parameters provides a sensitivity and specificity of 71.5% and 74.7%, respectively. Posture contextualization slightly decreased sensitivity to 70.1% and increased specificity to 79%, on average. In a non-freezing patient the algorithm is capable of increasing the specificity up to 11.95% more.
Conclusions
FoG detection based on a waist-worn accelerometer can be enhanced in terms of specificity by posture contextualization. Daily life monitoring and actuation can benefit from these algorithms.
... For this paper, signals from 20 PD patients were used, among which 8 patients presented FOG episodes and 12 did not present the symptom. The recordings are identical to those employed by Rodríguez-Martín et al. [27,28]. ...
Freezing of gait (FOG) is a common motor symptom of Parkinson's disease (PD), which presents itself as an inability to initiate or continue gait. This paper presents a method to monitor FOG episodes based only on acceleration measurements obtained from a waist-worn device. Three approximations of this method are tested. Initially, FOG is directly detected by a support vector machine (SVM). Then, classifier's outputs are aggregated over time to determine a confidence value, which is used for the final classification of freezing (i.e., second and third approach). All variations are trained with signals of 15 patients and evaluated with signals from another 5 patients. Using a linear SVM kernel, the third approach provides 98.7 % accuracy and a geometric mean of 96.1 %. Moreover, it is investigated whether frequency features are enough to reliably detect FOG. Results show that these features allow the method to detect FOG with accuracies above 90 % and that frequency features enable a reliable monitoring of FOG by using simply a waist sensor.
The following dissertation presents the contributions of the author in the field of human movement analysis and, specifically, in Parkinson's disease.
Recent technologies have allowed developing reduced inertial sensors capable of monitoring human movement. This, along with the reduced prices of these inertial sensors, the so-called inertial measurement units, which consists in small devices capable to measure movement by means of inertial sensors, have widely spread. Inertial measurement units have been employed among others, in fields such as medicine, sports, automotive and gaming.
In the first part of the present thesis, a wearable long-term monitoring inertial measurement unit is presented as the first main contribution in human movement analysis. The unit is capable of acquiring data and provides the possibility of implementing artificial intelligence-based classifiers in real time. A specific hardware and firmware has been developed in order to implement both operations. This tool has been validated in different European projects and studies carried out in the Technical Research Centre for Dependency Care and Autonomous Living of the Universitat Politècnica de Catalunya (CETpD-UPC).
The second part of the thesis addresses the analysis of human posture based on accelerometry measurements. To this end, data acquired from the inertial system described at the first part of the thesis have been used. Two methodologies are presented that have been validated on healthy people and patients with Parkinson's disease. The algorithms developed are focused on the detection of positions with a single inertial system located at the waist thereby achieving an enhanced comfort and acceptance by the users. A key contribution is the methodology provided to detect postural transitions, which consist in the movement performed to achieve a position from another one. The algorithm is based on support vector machines applied to the inertial data coming from a single measurement unit. Basic activity recognition is performed recognizing static postures such as sitting, standing, or lying with a hierarchical classification system. Moreover, dynamic postures such as walking and different postural transitions are also recognized.
Finally, the posture detection methodologies are employed to enhance the identification of one of the most annoying symptoms of Parkinson's disease, the so-called Freezing of Gait. This contribution relies on the posture algorithm which has been validated in Parkinson’s disease patients. Furthermore, it is shown how the introduction of the posture detection improves the evaluation values of the FOG algorithms
ResearchGate has not been able to resolve any references for this publication.