Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 20, 2026IEEE Transactions on Neural Systems and Rehabilitation EngineeringOpen Access

A Minimalist, Foot-Mounted IMU Approach to Parkinson’s Disease Detection in Semi-Controlled Settings

View Full Paper
Ask AI
Bookmark
Share

Authors

AGAlberto Hijazo GascónÁMÁlvaro MarcoPHPablo Herrero

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved Parkinson’s disease detection accuracy in semi-controlled settings, suggesting practical advancements for real-time identification.

Key Points

  • To evaluate a minimalist approach for Parkinson's disease detection using a foot-mounted IMU and a compact CNN.
  • Tested a minimalist six-axis IMU per shoe during a six-minute walk test in 89 participants (44 PD, 45 healthy controls).
  • Signals standardized and ingested as raw time series using 0.5-s non-overlapping windows and a 1D-CNN with 2,818 parameters.
  • Evaluation employed participant-level, stratified 5-fold cross-validation across seeds.
  • Achieved 80.58% overall accuracy with 74.76% sensitivity and 85.55% specificity at the foot level.
  • Utilizing a clinically motivated one-foot-positive criterion (OFPC) improved patient-level performance to 82.1% accuracy with 84.78% sensitivity and 80.29% specificity.
  • Indoor testing yielded 81.48% accuracy, whereas outdoor testing resulted in 82.17% accuracy, reflecting differences in sensitivity and specificity.

Cite This Study

Gascón et al. (2026) studied this question.

synapsesocial.com/papers/6a362de1db0793dc1a535dcbhttps://doi.org/10.1109/tnsre.2026.3704797
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Early Detection of Parkinson’s Disease Using a Single-Arm Wearable Sensor and Convolutional Neural Networks2025
  2. 2Deep Learning-Based Estimation of Ground Reaction Forces in Parkinsonian Gait Using an Optimized Set of IMU Data2026
  3. 3Detection of early-stage Parkinson’s disease using wearable sensors at multiple body locations and convolutional neural networks2026
  4. 4Automatic Parkinson’s Disease Diagnosis with Wearable Sensor Technology for Medical Robot2024 · 1 citations
  5. 5Multimodal machine learning mobility assessment in Parkinson’s disease within supervised and unsupervised settings2026