Interpretable gait analysis uncovers disease patterns with diagonal segment extraction
DiaSeg: Diagonal Segment Extraction from DTW Paths for Interpretable Gait Analysis
Computer Vision and Pattern Recognition
Summary
Measuring how people walk helps doctors diagnose diseases, but usual methods ignore detailed timing information. The authors propose DiaSeg, a way to capture detailed walking patterns by breaking down timing similarities into meaningful segments. Their method finds consistent patterns that separate healthy and disease-affected walking, and highlights exactly where in the walking cycle problems occur. This approach can improve understanding and diagnosis of neurodegenerative diseases like Parkinson's and ALS.
What this means in practice
- •For clinical gait analysts: Extract phase-specific temporal features from walking data to aid disease diagnosis and track motor impairments in neurodegenerative conditions.
- •For biomedical device developers: Incorporate interpretable gait pattern extraction into wearable sensor software to enhance monitoring of patient mobility and rehabilitation progress.$Commercial implications: Enables new diagnostic or monitoring products for neurological diseases by providing detailed and interpretable gait feature extraction from sensor data.
Authors
Tresor Y. Koffi, Amel Hidouri, Corentin Legrand, Aurélie Bertaux
Abstract
Dynamic Time Warping (DTW) is the dominant approach for measuring similarity between time series, yet standard practice discards the optimal warping path after computing a single distance value, losing local alignment information most relevant to clinical diagnosis. We introduce DiaSeg, a framework that extracts diagonal segments from DTW paths with controlled breaks, characterizing each segment by five geometric features (effective length, interruption count, cost variation, temporal position, and path context), and enabling unsupervised pattern discovery without domain-specific feature engineering. Validated on 91 subjects across six clinical conditions (healthy aging, Parkinson's, Huntington's, ALS, brain tumor, and stroke), three findings emerge. First, diagonal segments form consistent unsupervised patterns (silhouette 0.33) aligned with biomechanical phase annotations, with label-based validation confirming near-perfect separation of healthy and pathological gait (ARI up to 0.986). Second, segments discriminate pathology at 69% (supervised) and 75% (patient-level clustering), with pathology manifesting through distributional shifts in segment length; combining segment and cycle-level features further improves classification to 91.7%. Third, while cycle-based methods achieve higher accuracy (91%), diagonal segments provide phase-specific interpretability unavailable in global representations, localizing where coordination breaks down within the gait cycle. DiaSeg thus transforms DTW from a black-box distance into a source of interpretable temporal features for neurodegenerative disease assessment.