daphnet (Dynamic Analysis of Physiological Networks)

People

Marc Bächlin

This project is supervised by Dr. Daniel Roggen and Prof. Gerhard Tröster

Objectives

Physiological signals as output of the human complex system are typically nonlinear and nonstationary, and much information is hidden in the dynamics of their fluctuations. By applying conventional analysis techniques based on averaged quantities and other features of histogram and classical power spectrum analysis, some important characteristic properties of the signal dynamics are neglected.

Our investigations strongly indicate that in particular the scaling behaviour of the fluctuations plays an important role for distinguishing between healthy and pathological cases. By adapting and extending recent methods developed in modern statistical physics and nonlinear mathematics, it has been shown that the fluctuations of heartbeat and other neurally-controlled signals exhibit unanticipated hidden information (order) in the form of self-similarity, scaling structure, multifractality and long-term memory.

Within the daphnet project we suggest to extend previous research on the properties of each particular signal. The physiological functions to be studied are the cardio vascular capacities, brain activity (EEG), motor control, gait, posture, sleep and sympathetic and parasympathetic effects. Algorithms to assess the long-term effects and interrelations between signals representing these functions are at the core of this project. The simultaneous collection of several long-term signals will enable the construction of physiological networks using dynamical synchronization and cross-correlations patterns, whose momentary state together with the properties of each signal can give a picture of the health status of an individual.

Main work packages

• Test the hypothesis - based upon preliminary findings - that essential medical information is hidden in the non-equilibrium dynamics of physiologic rhythms when recorded over long time periods, as well as in the synchronization properties of the various physiological-signals and their interactions.
• Collect and analyze long-term data from targeted groups of individuals with specific medical conditions. Initiate the concept of physiological network, which, in combination with suitable algorithms, provides novel, quantitative status indices for specific debilitating pathologies.
• Adapt an existing wearable personal monitoring system for the needs of simultaneous long-term recording of data from multiple physiological-sensors and its collection and transmission for offline analysis.
• Create a repository of signals and algorithms to serve the research community. The database will be addressable not only according to data records, but according to synchronization phenomena and network properties.

Key Issues

• Algorithm development and implementation.
• Clinical Trials:
  - Long-term physiological signal recording of elderly subjects prone to falls.
  - Study the phenomenon of freezing of gait (FOG) of patients with Parkinson’s disease (PD).
  - Clinical conditions related to sleep.
  - Clinical cardiac aspects.
• Development of a wearable platform.
• Development of data facilities.

Main contribution of the Wearable Computing Lab

The Wearable Computing Lab is the leading partner in the area of the wearable platform and on-body electronics.
Furthermore, the Wearable Computing Lab supports the project in the field of context recognition. By extending the analysis of physiological networks together with contextual information we envision acquiring deeper insight into physiological function. The contextual information (user activity, social context, environment, …) will provide new nodes in the network and therefore extended network analysis will be possible.

Wearable assistant for Parkinson’s disease patients

Case study of context-triggered acoustic cueing to assist walking of Parkinson’s disease patients

Publications

2010

• A Wearable System to Assist Walking of Parkinson's Disease Patients
  Marc Bächlin, Meir Plotnik, Daniel Roggen, Nir Giladi, Jeffrey M Hausdorff and Gerhard Tröster
  (2010), in: Methods of Information in Medicine, 49:1(88-95)
  [ BiBTeX RIS DOI URL ]
• Wearable assistant for load monitoring: recognition of on-body load placement from gait alterations
  Marco Benocci, Marc Bächlin, Elisabetta Farella, Daniel Roggen, Luca Benini and Gerhard Tröster
  in: Proceedings of the 4th International Conference on Pervasive Computing Technologies for Healthcare, 2010
  [ BiBTeX RIS ]
• Wearable assistant for Parkinson's disease patients with the freezing of gait symptom
  Marc Bächlin, Meir Plotnik, Daniel Roggen, Inbal Maidan, Jeffrey M Hausdorff, Nir Giladi and Gerhard Tröster
  (2010), in: IEEE Transactions on Information Technology in Biomedicine, 14:2(436 - 446)
  [ BiBTeX RIS DOI URL ]

2009

• A wearable system towards pervasive healthcare: Case study on Parkinson’s disease patients
  Marc Bächlin
  Talk at the International Workshop on Physiological Networks: Theory, Implementation and Application, 2009
  [ BiBTeX RIS ]
• Automated treatment of freezing of gait in Parkinson's disease using a wearable device that automatically detects freezing
  Meir Plotnik, Marc Bächlin, Daniel Roggen, Noit Inbar, Inbal Maidan, Talia Herman, Marina Brozgol, Eliya Shaviv, Gerhard Tröster and Jeffrey M Hausdorff
  in: Annual meeting of the Israeli Neurological Society, Israel, pages 63, 2009
  [ BiBTeX RIS ]
• Online Detection of Freezing of Gait in Parkinson's Disease Patients: A Performance Characterization
  Marc Bächlin, Daniel Roggen, Meir Plotnik, Jeffrey M Hausdorff, Nir Giladi and Gerhard Tröster
  in: Proceedings of the 4th International Conference on Body Area Networks, 2009
  [ BiBTeX RIS ]
• Parkinson patients' perspective on context aware wearable technology for auditive assistance
  Marc Bächlin, Meir Plotnik, Daniel Roggen, Noit Inbar, Nir Giladi, Jeffrey M Hausdorff and Gerhard Tröster
  in: Proceedings of the 3rd International Conference on Pervasive Computing Technologies for Healthcare, 2009
  [ BiBTeX RIS URL ]
• Potentials of enhanced context awareness in wearable assistants for Parkinson’s disease patients with freezing of gait syndrome
  Marc Bächlin, Daniel Roggen, Meir Plotnik, Noit Inbar, Inbal Maidan, Talia Herman, Marina Brozgol, Eliya Shaviv, Nir Giladi, Jeffrey M Hausdorff and Gerhard Tröster
  in: Proceedings of the 13th International Symposium on Wearable Computers (ISWC), pages 123-130, 2009
  [ BiBTeX RIS URL ]
• Quantifying Gait Similarity: User Authentication and Real-World Challenge
  Marc Bächlin, Johannes Schumm, Daniel Roggen and Gerhard Tröster
  in: Advances in Biometrics, Third International Conference, ICB 2009, Alghero, Italy, June 2009. Proceedings, pages 1040-1049, Springer Berlin / Heidelberg, 2009
  [ BiBTeX RIS DOI URL ]

2008

• Effect of movements on the electrodermal response after a startle event
  Johannes Schumm, Marc Bächlin, Cornelia Kappeler-Setz, Bert Arnrich, Daniel Roggen and Gerhard Tröster
  (2008), in: Methods of Information in Medicine, 47:3(186-191)
  [ BiBTeX RIS PDF DOI URL ]
• Effect of movements on the electrodermal response after a startle event
  Johannes Schumm, Marc Bächlin, Cornelia Kappeler-Setz, Bert Arnrich, Daniel Roggen and Gerhard Tröster
  in: Proceedings of 2nd International Conference on Pervasive Computing Technologies for Healthcare (Pervasive Health), pages 315-318, 2008
  [ BiBTeX RIS PDF DOI URL ]

2007

• Context-aware platform for long-term life style management and medical signal analysis
  Marc Bächlin, Daniel Roggen and Gerhard Tröster
  in: Proceedings of the 2nd SENSATION International Conference, Chania, Greece, 2007
  [ BiBTeX RIS ]

Other contributors

Marco Benocci

Project Links

• Official project website: www.daphnet.eu