Structure-aware fatigue modeling in foot deformities: A digital health framework for tissue-specific running injury risk prediction using multi-modal data
PLOS digital health · 2026
Hallux valgus alters ankle/MTP loading in runners, but 'injury risk' here is simulated, not observed — don't act on it yet.
The paper
Case-control study, n=52 runners (26 with hallux valgus, 26 healthy controls), using 3D gait analysis, subject-specific musculoskeletal modelling, and deep learning to estimate tissue loading during running.
What they found
Hallux valgus (HV) runners showed higher peak ankle (p=0.004) and metatarsophalangeal (p=0.003) joint moments and reduced ROM, with modelled increases in cumulative load, cumulative damage, and probability of fatigue failure at the Achilles tendon and plantar fascia (tibial loading was similar between groups). Deep learning models predicted these modelled loading indices from IMU data with R²=0.89-0.93, improving to R²=0.94-0.97 when foot-structure data were added.
The appraisal
This is a small (26 vs 26), cross-sectional, unpowered comparison with no reported effect sizes or confidence intervals for the joint moment differences, so clinical magnitude can't be judged from the abstract. Critically, 'fatigue-failure probability' is a simulated output of the musculoskeletal model, not an observed injury outcome — no runners were actually followed for injuries. The deep learning R² values describe how well IMU data predict the model's own simulated loading indices, which risks circularity rather than validating real-world injury risk.
The gap
There is no prospective injury outcome data linking these modelled loading differences to actual Achilles or plantar fascia injuries in HV runners — the entire risk narrative rests on simulation, not observed events.
Landmark context
This extends established musculoskeletal-model fatigue-failure approaches (originally developed for tibial stress fracture risk) to a broader set of tissues and pairs them with deep learning for wearable-based prediction, but unlike foundational stress-fracture modelling work, it has not yet been validated against real injury incidence.
What to do Monday
Not actionable yet — clinicians shouldn't change screening or load management for HV runners based on this alone; at most, it flags hallux valgus as a structural variable worth considering when assessing Achilles/plantar fascia load, pending outcome validation.
The five papers that matter — every week, free.
We read the whole sports-medicine, rehab & performance literature and appraise the papers worth your time.
Get the free weekly issueRelated appraisals
Read in your language: English · Français · Deutsch · Español · Italiano · Nederlands · Dansk · Svenska