Frontiers in Neurology (Oct 2023)

Ecological validity of a deep learning algorithm to detect gait events from real-life walking bouts in mobility-limiting diseases

  • Robbin Romijnders,
  • Robbin Romijnders,
  • Francesca Salis,
  • Clint Hansen,
  • Arne Küderle,
  • Anisoara Paraschiv-Ionescu,
  • Andrea Cereatti,
  • Lisa Alcock,
  • Kamiar Aminian,
  • Clemens Becker,
  • Stefano Bertuletti,
  • Tecla Bonci,
  • Tecla Bonci,
  • Philip Brown,
  • Ellen Buckley,
  • Ellen Buckley,
  • Alma Cantu,
  • Anne-Elie Carsin,
  • Anne-Elie Carsin,
  • Anne-Elie Carsin,
  • Marco Caruso,
  • Brian Caulfield,
  • Brian Caulfield,
  • Lorenzo Chiari,
  • Lorenzo Chiari,
  • Ilaria D'Ascanio,
  • Silvia Del Din,
  • Silvia Del Din,
  • Björn Eskofier,
  • Sara Johansson Fernstad,
  • Marceli Stanislaw Fröhlich,
  • Judith Garcia Aymerich,
  • Judith Garcia Aymerich,
  • Judith Garcia Aymerich,
  • Eran Gazit,
  • Jeffrey M. Hausdorff,
  • Jeffrey M. Hausdorff,
  • Hugo Hiden,
  • Emily Hume,
  • Alison Keogh,
  • Alison Keogh,
  • Cameron Kirk,
  • Felix Kluge,
  • Felix Kluge,
  • Sarah Koch,
  • Sarah Koch,
  • Sarah Koch,
  • Claudia Mazzà,
  • Claudia Mazzà,
  • Dimitrios Megaritis,
  • Encarna Micó-Amigo,
  • Arne Müller,
  • Luca Palmerini,
  • Luca Palmerini,
  • Lynn Rochester,
  • Lynn Rochester,
  • Lars Schwickert,
  • Kirsty Scott,
  • Kirsty Scott,
  • Basil Sharrack,
  • David Singleton,
  • David Singleton,
  • Abolfazl Soltani,
  • Abolfazl Soltani,
  • Martin Ullrich,
  • Beatrix Vereijken,
  • Ioannis Vogiatzis,
  • Alison Yarnall,
  • Alison Yarnall,
  • Gerhard Schmidt,
  • Walter Maetzler

DOI
https://doi.org/10.3389/fneur.2023.1247532
Journal volume & issue
Vol. 14

Abstract

Read online

IntroductionThe clinical assessment of mobility, and walking specifically, is still mainly based on functional tests that lack ecological validity. Thanks to inertial measurement units (IMUs), gait analysis is shifting to unsupervised monitoring in naturalistic and unconstrained settings. However, the extraction of clinically relevant gait parameters from IMU data often depends on heuristics-based algorithms that rely on empirically determined thresholds. These were mainly validated on small cohorts in supervised settings.MethodsHere, a deep learning (DL) algorithm was developed and validated for gait event detection in a heterogeneous population of different mobility-limiting disease cohorts and a cohort of healthy adults. Participants wore pressure insoles and IMUs on both feet for 2.5 h in their habitual environment. The raw accelerometer and gyroscope data from both feet were used as input to a deep convolutional neural network, while reference timings for gait events were based on the combined IMU and pressure insoles data.Results and discussionThe results showed a high-detection performance for initial contacts (ICs) (recall: 98%, precision: 96%) and final contacts (FCs) (recall: 99%, precision: 94%) and a maximum median time error of −0.02 s for ICs and 0.03 s for FCs. Subsequently derived temporal gait parameters were in good agreement with a pressure insoles-based reference with a maximum mean difference of 0.07, −0.07, and <0.01 s for stance, swing, and stride time, respectively. Thus, the DL algorithm is considered successful in detecting gait events in ecologically valid environments across different mobility-limiting diseases.

Keywords