con-PDmode: Control-oriented PD state modelling and estimation for precision medicine

Parkinson's disease (PD) is a progressive neurodegenerative disorder and constitutes a serious public health concern. Although there are various methods on the market for evaluating disease symptoms using wearable sensors, these technologies are difficult to use, expensive and often require specific hardware. The EU-funded con-PDmode project aims to address these limitations by developing software capable of accounting for inaccuracies and uncertainty in the data collected from low-cost wearable sensors. Using advanced techniques, scientists will generate a modelling approach for evaluating PD symptoms and disease state, information on which will be communicated back to the patient. Optimisation of the algorithms and user interface as well as rigorous testing will ensure the development of an accurate PD assessment tool.

Motivation

Despite the fact that there has been some progress in developing methods for estimating Parkinson’s disease (PD) symptoms using wearable sensors, these technologies have not sufficiently penetrated the market due to the usability of the system and its cost; existing technologies are constrained by specific hardware requirements or user activities, therefore aversively affecting the cost and usability of the technologies, respectively. Thus, Con-PDmode delivers a software prototype for control-oriented modelling and estimation of PD symptoms that are transparent and platform agnostic. The excellence in innovation potential for successfully bringing the PD assessment tool to the market is the capability to account for inaccuracies and uncertainty in the data collected from low-cost wearable sensors. To this purpose, we will adapt and implement advanced stochastic techniques for improved robustness in state estimation, the confidence level of the model estimation will be transparently communicated to its users. We will perform iterative tests in various environmental and sensor configurations to refine our algorithms as well as the user interface.

Team members

Currently available student thesis / research internship

Kinematic simulation of Parkinson's Disease for machine learning (Satoshi Endo, Neha Das) [PDF]

Quantifying Information Loss Resulting from Degradation of IMU Sensor Resolution in PD Symptom Classification (Satoshi Endo, Neha Das) [PDF]

Quantifying Information Loss from Excluding Activity Label When Predicting PD Symptom Severity from IMU data (Satoshi Endo, Neha Das) [PDF]

Selected publications

  • Pfister, Franz M. J.; Um, Terry Taewoong; Pichler, Daniel C.; Goschenhofer, Jann; Abedinpour, Kian; Lang, Muriel; Endo, Satoshi; Ceballos-Baumann, Andres O.; Hirche, Sandra; Bischl, Bernd; Kulić, Dana; Fietzek, Urban M.: High-Resolution Motor State Detection in Parkinson's Disease Using Convolutional Neural Networks. Scientific Reports 10 (1), 2020, 5860 more… BibTeX
  • M. Lang; F.J. Pfister; J. Fröhner; K. Abedinpour; D. Pichler; U. Fietzek; T.T. Um; D. Kulić; S. Endo; S. Hirche: A Multi-layer Gaussian Process for Motor Symptom Estimation in People with Parkinson’s Disease. IEEE Transactions on Biomedical Engineering 66 (11), 2019, 3038-3049 more… BibTeX
  • S. Endo; F.J. Pfister; J. Fröhner; U. Fietzek; D. Pichler; K. Abedinpour; T.T. Um; D. Kulić; M. Lang; S. Hirche: Dynamics-based estimation of Parkinson's disease severity using Gaussian Processes. Second IFAC Conference on Cyber-Physical & Human Systems, 2018 more… BibTeX
  • D. Pichler, M. Lang, D. Kulić, F. Pfister, G. König, T. Um, A. Ahmadi, S. Endo, F. Achilles, K. Abedinpour, K. Bötzel, A. Ceballos-Baumann, S. Hirche, U. Fietzek: Acquisition, Validation and Preprocessing of Wrist-Worn Sensor Data in Patients with Parkinson’s Disease and Healthy Controls. International Parkinson and Movement Disorder Society 201721st International Congress, Vancouver, BC more… BibTeX
  • F. Pfister; D. Kulić; T. Um; D. Pichler; A. Ahmadi; M. Lang; G. König; F. Achilles; S. Endo; K. Abedinpour; K. Ziegler; K. Bötzel; S. Hirche; A. Ceballos-Baumann; U. Fietzek: Deep Learning in Objective Classification of Spontaneous Movement of Patients with Parkinson’s Disease Using Large-Scale Free-Living Sensor Data. International Parkinson and Movement Disorder Society 201721st International Congress, Vancouver, BC more… BibTeX
  • T. Um; F. Pfister; D. Pichler; S. Endo; M. Lang; S. Hirche; U. Fietzek ; D. Kulić: Data augmentation of wearable sensor data for parkinson's disease monitoring using convolutional neural networks. Proceedings of the 19th ACM International Conference on Multimodal Interaction - ICMI 2017, 2017 more… BibTeX

This research is supported by the European Union’s ERC Proof of Concept Grant under grant agreement no 899260.

For further information, see https://cordis.europa.eu/project/id/899260