Mobile gait analysis via eSHOEs instrumented shoe insoles: a pilot study for validation against the gold standard GAITRite ®

J Med Eng Technol. 2017 Jul;41(5):375-386. doi: 10.1080/03091902.2017.1320434. Epub 2017 Jun 2.


Clinical gait analysis contributes massively to rehabilitation support and improvement of in-patient care. The research project eSHOE aspires to be a useful addition to the rich variety of gait analysis systems. It was designed to fill the gap of affordable, reasonably accurate and highly mobile measurement devices. With the overall goal of enabling individual home-based monitoring and training for people suffering from chronic diseases, affecting the locomotor system. Motion and pressure sensors gather movement data directly on the (users) feet, store them locally and/or transmit them wirelessly to a PC. A combination of pattern recognition and feature extraction algorithms translates the motion data into standard gait parameters. Accuracy of eSHOE were evaluated against the reference system GAITRite in a clinical pilot study. Eleven hip fracture patients (78.4 ± 7.7 years) and twelve healthy subjects (40.8 ± 9.1 years) were included in these trials. All subjects performed three measurements at a comfortable walking speed over 8 m, including the 6-m long GAITRite mat. Six standard gait parameters were extracted from a total of 347 gait cycles. Agreement was analysed via scatterplots, histograms and Bland-Altman plots. In the patient group, the average differences between eSHOE and GAITRite range from -0.046 to 0.045 s and in the healthy group from -0.029 to 0.029 s. Therefore, it can be concluded that eSHOE delivers adequately accurate results. Especially with the prospect as an at home supplement or follow-up to clinical gait analysis and compared to other state of the art wearable motion analysis systems.

Keywords: Gait analysis; hip fracture; inertial sensors; pressure sensors; wearable technologies.

Publication types

  • Clinical Trial
  • Validation Study

MeSH terms

  • Adult
  • Aged
  • Aged, 80 and over
  • Algorithms
  • Biosensing Techniques / instrumentation*
  • Female
  • Gait*
  • Humans
  • Male
  • Middle Aged
  • Shoes*
  • Signal Processing, Computer-Assisted
  • Walking / physiology