Foot Deformity Fatigue Modeling with Wearable Sensor Data

A digital health framework dataset for predicting tissue-specific fatigue risk in hallux valgus feet. It integrates multi-modal data including foot morphology, joint mechanics, and cumulative tissue loading to generate personalized fatigue profiles. The dataset supports a hierarchical machine-learning model trained on wearable sensor data.

Use Cases

• Predict cumulative tissue loading fatigue trajectories from wearable sensor data using a hierarchical machine-learning model.
• Analyze correlations between foot morphology features and joint mechanics to identify structural risk factors for tissue overload.
• Build personalized fatigue profiles by combining foot morphology, joint mechanics, and cumulative tissue loading data.
• Validate structure-aware fatigue modeling outputs against wearable sensor data for non-invasive monitoring applications.

Strengths

• Data supports a digital health framework for personalized, real-time fatigue assessment.
• Integrates multi-modal data types: foot morphology, joint mechanics, and cumulative tissue loading.
• Framework enables non-invasive, continuous monitoring outside laboratory settings.

Limitations

• Dataset size is small at 14.7 MB, limiting the scale of machine learning model training.
• Specific row count, column count, and sample data are unavailable, hindering reproducibility and direct analysis.
• Focus is on hallux valgus foot deformities, which may limit generalizability to other conditions.

Provenance

Source

figshare

Collection Method

Developed via a digital health framework using wearable sensor data and structure-aware fatigue modeling.

Time Range

null

Freshness

Last updated March 2026.

Geography

null