Gait2Hip-60: A Unified Deep Learning Benchmark for Predicting Hip Muscle Forces and Joint Moments from Multi-Cadence Gait Kinematics

• URL: http://arxiv.org/abs/2605.30374v1
• Date: Sun, 24 May 2026 14:00:42 GMT
• Title: Gait2Hip-60: A Unified Deep Learning Benchmark for Predicting Hip Muscle Forces and Joint Moments from Multi-Cadence Gait Kinematics
• Abstract summary: Estimating hip muscle forces and joint moments during gait typically relies on musculoskeletal simulation.<n>This study developed a deep learning framework to predict these hip dynamics parameters directly from lower-limb gait kinematics.
• Score: 14.156448292622136
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Estimating hip muscle forces and joint moments during gait typically relies on musculoskeletal simulation, which is informative but time-consuming and difficult to apply in clinical settings. This study developed a deep learning framework to predict these hip dynamics parameters directly from lower-limb gait kinematics and compared three representative sequence models under a unified protocol. Gait data were collected from 60 healthy adults under three metronome-guided cadence conditions. Ten bilateral lower-limb joint angles were used as inputs, and OpenSim-derived hip muscle forces and hip joint moments were used as reference outputs. Three deep learning models of LSTM, Transformer, and Mamba were trained and evaluated using the same subject-level split, preprocessing pipeline, and metrics. The best model was then directly tested on an external cohort of 9 patients with osteonecrosis of the femoral head (ONFH) without retraining. In the healthy-subject benchmark, Transformer achieved the best subject-level mean performance for both hip muscle force prediction (RMSE = 1.33 N/kg, MAE = 0.57 N/kg, R2 = 0.819) and hip joint moment prediction (RMSE = 0.11 Nm/kg, MAE = 0.07 Nm/kg, R2 = 0.862), with similar advantages across walking cadences. In zero-shot external validation, Transformer retained moderate predictive ability in ONFH for hip muscle force prediction (RMSE = 1.51 N/kg, MAE = 0.70 N/kg, R2 = 0.537) and hip joint moment prediction (RMSE = 0.17 Nm/kg, MAE = 0.12 Nm/kg, R2 = 0.569). These findings support the feasibility of estimating hip dynamics from gait kinematics, identify Transformer as a strong baseline, and highlight the need for broader pathological validation and improved generalization before clinical application.

Related papers

• Learning Biomechanically Plausible Human Motion from Sparse Radar Point Clouds [39.56983715336933]
  We integrate a full-body skeletal model into a differentiable, end-to-end trainable radar-based pose estimation framework.<n>Subject-specific body segment proportions are predicted from radar point cloud features to scale a biomechanical skeleton.<n>A motion prediction network maps temporal radar sequences to generalized coordinates, and differentiable forward kinematics converts predicted joint angles into 3D positions.
  arXiv  Detail & Related papers  (2026-08-04T13:20:05Z)
• A Latent ODE Approach to Spatiotemporal Modeling of Cine Cardiac MRI [35.84205082882139]
  We present a latent dynamical model that encodes bi-ventricular anatomy and full-cycle cine motion as a continuous trajectory.<n>We studied 72,386 UK Biobank participants without baseline cardiovascular disease, including 367 incident heart failure events.
  arXiv  Detail & Related papers  (2026-06-25T07:53:45Z)
• Physiologically Constrained Musculoskeletal Neural Network for Multi-DoF Joint Kinematics Estimation from Partially Observed sEMG [3.2286367508489495]
  A novel musculoskeletal neural network (MSK-NN) is proposed to estimate multi-DoF joint angles.<n>MSK-NN consists of a CNN-based muscle activation estimator and an embedded MSK forward dynamics module.<n>Compared with CNN, Bi-LSTM, CNN-LSTM, and PET baselines, MSK-NN achieves lower normalized root mean square error (NRMSE) and higher coefficient of determination (R2)
  arXiv  Detail & Related papers  (2026-06-05T17:30:16Z)
• From Pixels to Newtons: Predicting In Vivo Joint Contact Forces from Monocular Video [0.6768558752130311]
  I present a physics-free pipeline to predict instantaneous 3D hip and knee contact forces from an uncalibrated monocular video.<n>Parametric body meshes are recovered per frame, encoded as kinematic features, and decoded into forces by a transformer.<n>This pipeline establishes uncalibrated monocular video as a viable modality for estimating joint loading.
  arXiv  Detail & Related papers  (2026-06-04T18:31:00Z)
• Differentiable latent structure discovery for interpretable forecasting in clinical time series [38.473526928012724]
  We introduce StructGP, a continuous-time multi-task Gaussian process that couples differentiable structure learning to uncover a sparse, ordered directed acyclic graph (DAG) of inter-variable dependencies while preserving principled uncertainty.<n>We propose LP-StructGP, which augments StructGP with latent pathways-shared, temporally shifted trajectories inferred via subject-specific coupling filters and a softmax gating mechanism-to capture cross-patient progression patterns.
  arXiv  Detail & Related papers  (2026-04-30T14:59:50Z)
• Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale [38.15316304510102]
  MuscleMimic is an open-source framework for motion imitation learning with physiologically realistic, muscle-driven models.<n>By lowering the computational and data barriers to musculoskeletal simulation, MuscleMimic enables systematic model validation across diverse dynamic movements.
  arXiv  Detail & Related papers  (2026-03-26T15:18:37Z)
• Muscle Synergy Priors Enhance Biomechanical Fidelity in Predictive Musculoskeletal Locomotion Simulation [0.0]
  Human locomotion emerges from high-dimensional neuromuscular control, making predictive musculoskeletal simulation challenging.<n>We present a physiology-informed reinforcement-learning framework that constrains control using muscle synergies.<n>These results show that embedding neurophysiological structure into reinforcement learning can improve biomechanical fidelity and generalization in predictive human locomotion simulation with limited experimental data.
  arXiv  Detail & Related papers  (2026-03-11T06:48:15Z)
• A Feature Extraction Pipeline for Enhancing Lightweight Neural Networks in sEMG-based Joint Torque Estimation [1.9573380763700712]
  We propose a feature extraction pipeline to predict elbow and shoulder joint torques.<n>This pipeline enables a simple to achieve performance comparable to that of a network designed explicitly for temporal dependencies.
  arXiv  Detail & Related papers  (2026-01-23T12:59:39Z)
• Practical Geometric and Quantum Kernel Methods for Predicting Skeletal Muscle Outcomes in chronic obstructive pulmonary disease [12.752575381856934]
  Skeletal muscle dysfunction is a clinically relevant extra-pulmonary manifestation of chronic obstructive pulmonary disease (COPD)<n>This motivates predictive modelling of muscle outcomes from minimally invasive biomarkers that can be acquired longitudinally.<n>We benchmark tuned classical baselines, geometry-aware symmetric positive definite (SPD) descriptors with Stein divergence, and quantum kernel models designed for low-dimensional data.
  arXiv  Detail & Related papers  (2026-01-01T13:25:45Z)
• Diff-MSM: Differentiable MusculoSkeletal Model for Simultaneous Identification of Human Muscle and Bone Parameters [5.071602765737453]
  We propose using Differentiable MusculoSkeletal Model (Diff-MSM) to simultaneously identify its muscle and bone parameters.<n>The new parameter identification technique with the Diff-MSM has great potential to enable new applications in muscle health monitoring, rehabilitation, and sports science.
  arXiv  Detail & Related papers  (2025-08-18T18:43:43Z)
• Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV [49.1574468325115]
  This study explores multiple ML approaches for predicting LOS in ICU specifically for the patients with neurological diseases based on the MIMIC-IV dataset.<n>The evaluated models include classic ML algorithms (K-Nearest Neighbors, Random Forest, XGBoost and CatBoost) and Neural Networks (LSTM, BERT and Temporal Fusion Transformer)
  arXiv  Detail & Related papers  (2025-05-23T14:06:42Z)
• Time-Varying Coronary Artery Deformation: A Dynamic Skinning Framework for Surgical Training [33.92599418560439]
  This study proposes a novel dynamic modeling framework for coronary arteries using skeletal skinning weights.<n>It aims to achieve precise control over vessel deformation while maintaining real-time performance for surgical simulation applications.
  arXiv  Detail & Related papers  (2025-03-04T02:51:37Z)
• sEMG-Driven Physics-Informed Gated Recurrent Networks for Modeling Upper Limb Multi-Joint Movement Dynamics [5.524068837259551]
  Exoskeletons and rehabilitation systems have the potential to improve human strength and recovery by using adaptive human-machine interfaces.<n>We introduce the Physics-informed Gated Recurrent Network (PiGRN), a novel model designed to predict multi-joint movement dynamics from sEMG data.<n>PiGRN uses a Gated Recurrent Unit (GRU) to process time-series sEMG inputs, estimate multi-joint kinematics and external loads, and predict joint torque while incorporating physics-based constraints during training.
  arXiv  Detail & Related papers  (2024-08-29T15:09:04Z)
• A Progressive Risk Formulation for Enhanced Deep Learning based Total Knee Replacement Prediction in Knee Osteoarthritis [36.12790384412525]
  We developed deep learning models for predicting Total Knee Replacement (TKR) need within various time horizons in knee osteoarthritis patients.<n>The models can perform TKR prediction using a single scan, and furthermore when a previous scan is available, they leverage a progressive risk formulation to improve their predictions.<n>Knee radiographs and MRIs from the Osteoarthritis Initiative (OAI) and Multicenter Osteoarthritis Study (MOST) were used in this work.
  arXiv  Detail & Related papers  (2024-06-14T15:24:49Z)
• Pulmonary Embolism Mortality Prediction Using Multimodal Learning Based on Computed Tomography Angiography and Clinical Data [31.830488752817804]
  The objective of this study is to implement deep learning models using Computed Tomography Angiography (CTPA), clinical data, and Pulmonary Severity Index (PESI) scores to predict PE mortality.
  arXiv  Detail & Related papers  (2024-06-03T13:10:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.