Quantification of Daily Arm Use from IMU Data in Children with Hemiparesis
Masterthesis / Biomedical Engineering / AI in Medicine
Status: Open
Time frame: Unspecified
Quantification of Daily Arm Use from IMU Data in Children with Hemiparesis
Project background
Children with hemiparesis show sensory and motor deficits, which negatively affect activities of daily living and thus, their quality of live. Having to overcome these barriers on a daily basis makes it difficult for affected children to actively participate in activities with their peers. This may further have a negative impact on social and psychological aspects. A study of the Bern University Children’s Hospital (Inselspital) investigates the effects and mechanisms of sensory afferent electrostimulation with the goal to improve upper limb function in children with spastic hemiparesis. To evaluate the daily arm use at different stages during the study, two inertial measurement units (IMUs, see Figure 1) are worn by the participants at home for periods of 24 hours. There are a total of four recordings per participant: 1) Baseline recording, 2) Training evaluation recording, 3) Treatment evaluation recording, 4) Follow-up recording.
Aim
Development of a robust algorithm to quantify daily arm use from IMU data captured at different timepoints in a clinical trial with a follow-up examination.
Materials and Methods
This thesis consist of two parts.
The first part focuses on developing a robust algorithm to preprocess the underlying data and to extract and classify movement activities. This requires the student to 1) research and get familiar with the neurological condition of the participant group as well as commonly used algorithms for quantifying activities from arm swing using IMUs, 2) evaluate the applicability of existing algorithms and add your own ideas to suit the given task, and 3) implement and test the evaluated methods.
The second part of this project aims to investigate differences of arm use between the impaired and the healthy arm as well as the performance changes between the different study stages. The developed algorithm and corresponding findings are expected to be documented in form of a written thesis document.
Figure 1 | Axivity Ax6 logging accelerometer from Axivity Ltd (Newcastle, UK)
Source: https://axivity.com/product/ax6
Nature of the Thesis
Development of algorithms: 60%
Data analysis: 40%
Requirements
Good programming skills in python
Good knowledge in time series analysis
Good knowledge in statistics
Supervisors
Kim Svenja Lory & Kevin Möri
Prof. Dr. Tobias Nef
Institutes
Division of Neuropediatrics, Development and Rehabilitation, University Children's Hospital Bern
ARTORG Center for Biomedical Engineering Research, University of Bern, Gerontechnology and Rehabilitation Group
Language: English
Contact: Kevin Möri, Freiburgstrasse 3, CH-3010 Bern
Application: kevin.moeri@unibe.ch