Georg Wieland

Advisors
Nils Roth (M.Sc.), Robert Richer (M.Sc.), Prof. Dr. Björn Eskofier

Duration
01/2019 – 08/2019

Abstract
Neurodegenerative diseases such as Parkinson’s disease (PD) have evidently an impairing impact on the movement of patients, especially gait [1]. Due to frequent motor fluctuations during disease progression a continuous, objective and quantitative, assessment of gait parameters within a natural, home environment is a promising approach for better diagnosis and patient treatment instead of the common visual examinations in clinical or laboratory environments where patients perform specific gait tests [1]–[6]. Moreover, various studies show that the physical environment of patients with PD is influencing gait and symptoms such as freezing of gait [7], [8]. The development of wearable technologies, particularly inertial sensor units (IMUs) and wireless technologies, introduce a possibility to asses quantitative and accurate gait parameters during daily life in a more natural environment and in an unobtrusive manner [6]. Therefore, systems for home and long-term monitoring should work in an unsupervised environment and should preferably require as little user interaction as possible in order to achieve high user compliance and reduce error risk [6].

Recently, a prototype of a smart insole, which combines IMU and pressure sensors was developed at the Machine Learning and Data Analytics Lab of the Friedrich-Alexander-Universität Erlangen-Nürnberg for assessing gait parameters. In order to automatically collect recorded data in long-term-monitoring scenarios, the smart insoles need to be extended by a context-aware data concentrator.

Therefore, the goal of this master’s thesis is to develop such a fully automated data concentrator for collecting recorded data of wearable insole systems in home-monitoring scenarios. The system should be easy to use and should require as little user interaction as possible. If necessary, the firmware of the wearable insole systems should be adapted accordingly to optimize the workflow.

To address the question how the physical environment can influence gait parameters, the feasibility of an “at home/out of home” context detection mechanism should be evaluated and implemented for the developed data concentrator to deliver additional context information. This context information will then be used to evaluate how gait parameters will change in different situations like “at home” vs “out of home”.

Therefore, a small study needs to be conducted to automatically collect long-term sensor data and evaluate gait parameters clustered to “at home” vs “out of home” situations, using an existing analysis pipeline.  Furthermore, the system needs to be evaluated in terms of usability and data quality as well as data integrity during data collection.

References:

1. J. G. Barth, Development and Validation of a Mobile Gait Analysis System Providing Clinically Relevant Target Parameters in Parkinson’s Disease. 2017.
2. M. A. Hobert, W. Maetzler, K. Aminian, and L. Chiari, “Technical and clinical view on ambulatory assessment in Parkinson’s disease,” Acta Neurol. Scand., vol. 130, no. 3, pp. 139–147, 2014.
3.  J. M. Fisher, N. Y. Hammerla, T. Ploetz, P. Andras, L. Rochester, and R. W. Walker, “Unsupervised home monitoring of Parkinson’s disease motor symptoms using body-worn accelerometers,” Park. Relat. Disord., vol. 33, pp. 44–50, 2016.
4. S. V. Perumal and R. Sankar, “Gait and tremor assessment for patients with Parkinson’s disease using wearable sensors,” ICT Express, vol. 2, no. 4, pp. 168–174, 2016.
5. C. Martindale, N. Roth, J. Hannink, S. Sprager, and B. M. Eskofier, “Smart Annotation Tool for Multi-sensor Gait-based Daily Activity Data,” Proc. 2018 IEEE Int. Conf. Pervasive Comput. Commun. Work., pp. 668–673, 2018.
6. E. Rovini, C. Maremmani, and F. Cavallo, “How wearable sensors can support parkinson’s disease diagnosis and treatment: A systematic review,” Front. Neurosci., vol. 11, no. OCT, 2017.
7. S. Del Din, A. Godfrey, B. Galna, S. Lord, and L. Rochester, “Free-living gait characteristics in ageing and Parkinson’s disease: Impact of environment and ambulatory bout length,” J. Neuroeng. Rehabil., vol. 13, no. 1, pp. 1–12, 2016.
8. J. Ottosson, L. Lavesson, S. Pinzke, and P. Grahn, “The significance of experiences of nature for people with parkinson’s disease, with special focus on freezing of gait—the necessity for a biophilic environment. a multi-method single subject study,” Int. J. Environ. Res. Public Health, vol. 12, no. 7, pp. 7274–7299, 2015.