Assistive Technologies and Medical Engineering

Critical Systems Engineering Living Lab - Medical Process Modeling (CSE LL-MPM)

Researchers in the Living Lab - Medical Process Modeling develop research infrastructures for medical-specific questions. The Living Lab allows the acquisition and modeling of standardized time-critical processes, e.g. prehospital resuscitation (the Mega Code Training). The aim is the analysis of the quality of individual performance and the prediction of human behavior in a defined socio-technical system to optimize processes through human-machine interaction. The Living Lab CMP makes a significant contribution to the quantification, optimization, and standardization of medical processes.

Approach

In a first step, the necessary infrastructure is developed to model medical workflow (such as prehospital resuscitation) in typical safety-critical situations with a focus on functional properties such as timing, workloads, and attention.

For this purpose, relevant motion sequences of the participants must be monitored very precisely via both environmental sensors and inertial sensors (motion capture). The combination of these two different motion capture approaches avoids the weaknesses of the individual systems: Optical motion capture methods are, e.g. very sensitive to sunlight and inertial sensors become imprecise at the end of the kinematic tree (e.g. towards the hands). Furthermore, the cognitive workload and the viewing angles of the participants are measured and modeled.

Also, all activities that can be related to patients are recorded using an A(C)LS simulator and ECG and merged into an evaluation platform. Further, it will be investigated which sensor system is suitable for future decision support systems that can be utilized for field use. Based on the context information, processes are modeled about timing, workloads, and attention. In a second step, simulations will be designed to optimize the Mega Codes Training.

Grants and cooperations

The interdisciplinary research center for the design of safety-critical socio-technical systems investigates the role of humans in the control of complex transport systems on land and water. Cooperation partners are OFFIS e.V. in Oldenburg, DLR Institute for Traffic Systems Engineering in Braunschweig and the network SafeTRANS. Currently, the project is funded in the second phase by the state of Lower Saxony with EUR 2 million. The project runtime was extended by additional 18 months (2017-2018).

Publications

  • [incollection] bibtex | Go to document Go to document
    C. Lins, S. M. Müller, and A. Hein, "Model-Based Approach for Posture and Movement Classification in Working Environments," in Ambient Assisted Living: 8. AAL-Kongress 2015,Frankfurt/M, April 29-30. April, 2015, Wichert, R. and Klausing, H., Eds., Frankfurt/M: Springer International Publishing, 2016, pp. 25-33.
    @incollection{Lins.2016b, abstract = {In this paper, we present an approach for model-based movement and posture classification in working environments. The approach presented here is designed for long-term in-situ observations of and by workers in their workplaces. The proposed model is adaptable to different input data, e.g., skeleton data from either an Inertial Measurement Unit (IMU) or a skeleton derived from an optical sensor such as Kinect. We present a preliminary design of the model and suggest algorithms suitable for real-time usage of the model in an IMU-based motion capture suite. In an experiment we measured the weight on the knee while performing different kneeing postures to show the dependence of posture angles on the knee load.},
      address = {Frankfurt/M},
      author = {Lins, Christian and M{\"{u}}ller, Sebastian Matthias and Hein, Andreas},
      booktitle = {Ambient Assisted Living: 8. AAL-Kongress 2015,Frankfurt/M, April 29-30. April, 2015},
      doi = {10.1007/978-3-319-26345-8_3},
      editor = {Wichert, Reiner and Klausing, Helmut},
      isbn = {978-3-8007-3901-1},
      keywords = {Working environment Model Posture Classification K},
      pages = {25--33},
      publisher = {Springer International Publishing},
      series = {Advanced Technologies and Societal Change},
      title = {{Model-Based Approach for Posture and Movement Classification in Working Environments}},
      url = {http://link.springer.com/10.1007/978-3-319-26345-8_3},
      year = {2016} }
  • [inproceedings] bibtex
    S. Hellmers, S. Fudickar, E. Lange, C. Lins, and A. Hein, "Validation of a Motion Capture Suit for Clinical Gait Analysis," in Proc. Proceedings of the 11th EAI Conference on Pervasive Computing Technologies for Healthcare, Barcelona, 2017.
    @inproceedings{Hellmers2017b, abstract = {Gait analysis is often supported by technology. Due to limitations in optical systems, such as limited measurement volumes and the requirement of a laboratory environment, low-cost inertial measurement unit (IMU) based motion capture system might be better suited for gait analysis since they involve no spatial limitations and are flexible applicable. In this paper we investigate, if a low-cost IMU-based motion capture suits are an adequate alternative for clinical gait analysis in terms of accuracy of the determination of joint flexions and gait parameters. For this reason, we developed a gait analysis system and a gait analysis algorithm, which detects joint positions based on the Joint Coordinate System and determines knee, hip, and ankle flexions, as well as spatiotemporal parameters such as the number of steps, cadence, step duration and step length, and the specific gait phases. We evaluated and validated the IMU-based system in comparison to camera-based measurements (as gold standard) with three different healthy adult subjects. The evaluation indicates that the full-body motion capture system achieves a high degree of precision (0.86) and recall (0.98) in the recognition of gait cycles. The harmonic mean F(0.15) of the two factors precision and recall is on average 0.96 and the mentioned temporal gait parameters can be determined with an error below 10 ms. The mean derivation in the determination of joint angles amounts 1.35+-2°. Consequently, the article at hand indicates that low-cost IMU-based motion capture suits are an accurate alternative for gait analysis. },
      address = {Barcelona},
      author = {Hellmers, Sandra and Fudickar, Sebastian and Lange, Eugen and Lins, Christian and Hein, Andreas},
      booktitle = {Proceedings of the 11th EAI Conference on Pervasive Computing Technologies for Healthcare},
      title = {{Validation of a Motion Capture Suit for Clinical Gait Analysis}},
      year = {2017} }
  • [inproceedings] bibtex | Go to document Go to document
    C. Lins, M. Eichelberg, L. Rölker-Denker, and A. Hein, "SIRKA: Sensoranzug zur individuellen Rückmeldung körperlicher Aktivität," in Proc. Dokumentationsband zur 55. DGAUM--Jahrestagung, München, 2015, pp. 301-303.
    @inproceedings{Lins.2015, abstract = {Im SIRKA-Projekt wird ein neuartiger Messanzug entwickelt, der – in die Arbeitskleidung integriert – Bewegungsabl{\"{a}}ufe und damit verbundene k{\"{o}}rperliche Belastungen pr{\"{a}}zise {\"{u}}ber lange Zeitr{\"{a}}ume erfassen kann.},
      address = {M{\"{u}}nchen},
      author = {Lins, Christian and Eichelberg, Marco and R{\"{o}}lker-Denker, Lars and Hein, Andreas},
      booktitle = {Dokumentationsband zur 55. DGAUM--Jahrestagung},
      isbn = {978-3-9817007-1-8},
      keywords = {Informationenfehlen DOI},
      mendeley-tags = {Informationenfehlen DOI},
      pages = {301--303},
      publisher = {Deutsche Gesellschaft f{\{}{\"{u}}{\}}r Arbeitsmedizin und Umweltmedizin e. V},
      title = {{SIRKA: Sensoranzug zur individuellen R{\"{u}}ckmeldung k{\"{o}}rperlicher Aktivit{\"{a}}t}},
      url = {www.dgaum.de/fileadmin/PDF/Tagungsbaende/Dokumentationsband_DGAUM_2015_END.pdf},
      year = {2015} }