Real-Time Musculoskeletal Surrogates for Pediatric Cerebral Palsy: a Credibility Pilot

Mohammad Arif Ul Alam

cs.CVAug 28, 2026

Real-Time Musculoskeletal Surrogates for Pediatric Cerebral Palsy: a Credibility Pilot

Authors: Mohammad Arif Ul Alam

Organizations: College of Science and Technology, North Carolina A & T State University, Greensboro, NC, USA

Abstract

Real-time musculoskeletal (MSK) surrogates could support personalized rehabilitation for children with cerebral palsy (CP), but their credibility depends on subject-wise evaluation, low inference latency, and calibrated uncertainty. We develop a subject-conditioned causal neural surrogate using OpenSim-derived static parameters, temporal joint kinematics, true muscle capacities, and training-only perturbations. On a real pediatric CP gait dataset comprising nine children, we use leave-one-subject-out validation on six development subjects and evaluate a frozen configuration once on three locked test subjects. The surrogate accurately reproduces musculotendon lengths (R-square = 0.92 in development validation and approximately 0.95 on locked subjects; nRMSE < 8%) while requiring only sub-millisecond to few-millisecond neural inference, well below a 100 ms interactive-rehabilitation target. In contrast, direct muscle-force estimation remains unstable at this small, heterogeneous scale: pooled metrics can overstate within-subject, per-muscle accuracy. A Monte Carlo credibility pilot further shows that propagating only +/-5% anthropometry and muscle-capacity variation produces severely overconfident nominal 90% intervals (approximately 4% force coverage and below 1% MT-length coverage). These results establish a leakage-free evaluation and credibility framework for pediatric MSK surrogates, while identifying force modeling and epistemic uncertainty as the central next challenges for clinically credible digital twins.

Figures & tables

Subject	Severity	Frames	Split
MI01	Mild	674	Dev
MI02	Mild	893	Dev
MO02	Moderate	799	Dev
MO03	Moderate	749	Dev
SE01	Severe	838	Dev
SE02	Severe	889	Dev

Table 1: Cohort and subject-level evaluation partition. Frame counts denote aligned kinematic/CMC ground-truth frames. Dev: development LOSO; Test: locked held-out evaluation.

Figure 1: Overview of the subject-conditioned musculoskeletal surrogate and leakage-free evaluation protocol. Pediatric CP gait data are processed with subject-scaled OpenSim models and computed muscle control to generate force, activation, musculotendon-length, moment-arm, and inverse-dynamics labels. Windowed kinematics and static model parameters are provided to a causal TCN. Development subjects are used exclusively for leave-one-subject-out model selection and training-only augmentation. A firewall separates the locked held-out evaluation from development. The frozen model is subsequently used for a Monte Carlo credibility pilot with $\pm 5\%$ input variation and nominal 90% prediction-interval coverage assessment.

Set	Subject	Force	MT length	Joint moment
Dev.	MI01	0.380	0.974	-0.019
Dev.	MI02	-0.050	0.512	-0.024
Dev.	MO02	0.441	0.951	0.000
Dev.	MO03	0.486	0.987	-0.014
Dev.	SE01	-0.635	0.986	-0.013
Dev.	SE02	0.374	0.919	-0.007

Table 2: Subject-wise global

R^{2}

results. Each subject-level value is computed over that subject’s evaluation windows and output dimensions. Joint-moment labels were generated only for development LOSO evaluation.

Figure 2: Subject-wise global $R^{2}$ for muscle force and MT length. Development subjects are evaluated by leave-one-subject-out validation; locked subjects are evaluated once after model configuration freezing. MT-length prediction is consistently strong except for one development subject, whereas force prediction varies sharply across children. This variation demonstrates why pooled force $R^{2}$ must be interpreted alongside subject-wise metrics.

Figure 3: Monte Carlo credibility pilot on locked held-out subjects. The dashed line denotes nominal 90% coverage. Propagating only $\pm 5\%$ variation in muscle capacity and anthropometry-related static inputs yields severely overconfident intervals: pooled empirical coverage is 4.35% for force and 0.70% for MT length. Narrow interval widths show that input-parameter variation captures only a small component of total predictive uncertainty.

Musculoskeletal Modeling

See all 16 papers

Quantifying Rodda and Graham Gait Classification from 3D Markerless Kinematics derived from a Single-view Video in a Heterogeneous Pediatric Clinical Cohort
May 11, 2026Lauhitya Reddy, Seth Donahue, Jeremy Bauer +8Markerless Motion Capture Gait Analysis
Department of Biomedical Informatics, Emory University, Atlanta, GA, USA · Shriners Children’s, USA · The Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
Physiologically Constrained Musculoskeletal Neural Network for Multi-DoF Joint Kinematics Estimation from Partially Observed sEMG
Jun 5, 2026Wending Heng, Mingming Zhang, Glen Cooper +1Surface Electromyography Physics-Informed ML
University of Manchester · 2Southern University of Science and Technology
NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception
Jul 13, 2026Zhiyang Dou, John U. Onyemelukwe, Hangxing Zhang +9Neural Surrogate Modeling Robot Dynamics Identification
1MIT · 2Amazon Robotics

May 11, 2026J/K move · Enter open · S save

Quantifying Rodda and Graham Gait Classification from 3D Markerless Kinematics derived from a Single-view Video in a Heterogeneous Pediatric Clinical Cohort

Lauhitya Reddy, Seth Donahue, Jeremy Bauer, Susan Sienko+7

Department of Biomedical Informatics, Emory University, Atlanta, GA, USA · Shriners Children’s, USA · The Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA

Markerless Motion Capture Gait Analysis

Open paper AskPDF arXiv

Cerebral Palsy (CP) is a neurological disorder of movement and the most common cause of lifelong physical disability in childhood. Approximately 75% of children with CP are ambulatory, and accurate gait assessment is central to preserving walking function, which deteriorates by mid-adulthood in a quarter to half of adults with CP. The Rodda and Graham classification system quantifies sagittal-plane gait deviations using ankle and knee z-scores derived from 3D Instrumented Gait Analysis (3D-IGA), but 3D-IGA is expensive and limited to specialized centers, while observational assessment shows only moderate inter-rater agreement. We developed a markerless gait analysis pipeline that quantifies Rodda and Graham knee and ankle z-scores directly from single-view clinical gait videos. Across 1,058 bilateral limb samples from 529 trials of 152 children (88 male, 63 female; age 12.1

\pm

4.0 years; 60 distinct primary diagnoses, cerebral palsy the most common at

n=54

), the sagittal-view model achieved

R^2 = 0.80 \pm 0.02

and CCC

= 0.89 \pm 0.02

for knee z-scores and

R^2 = 0.57 \pm 0.02

and CCC

= 0.72 \pm 0.02

for ankle z-scores against 3D-IGA. Binary screening for excess knee flexion achieves AUROC

= 0.88

, correctly identifying 83% of affected children, and applying Rodda and Graham rules yields

43 \pm 1

% 7-class accuracy with macro-AUROC

= 0.78 \pm 0.01

, ankle prediction error remaining the primary bottleneck. Beyond cross-sectional screening, continuous z-scores support longitudinal trajectory tracking across visits, providing a quantitative substrate for monitoring disease progression and treatment response unavailable from observational scales. These results demonstrate the feasibility of video-based z-score estimation, excess-flexion screening, and longitudinal trajectory tracking as a path toward scalable, objective gait assessment in low-resource clinical settings.

Abstract

Musculoskeletal Modeling

Explore similar work

Quantifying Rodda and Graham Gait Classification from 3D Markerless Kinematics derived from a Single-view Video in a Heterogeneous Pediatric Clinical Cohort

Physiologically Constrained Musculoskeletal Neural Network for Multi-DoF Joint Kinematics Estimation from Partially Observed sEMG

NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception