LENS: a transferable neuromuscular signature of musculoskeletal pain intensity
- 1University of Toronto
Abstract
Self-reported pain remains the clinical standard for assessing musculoskeletal pain severity, but its subjectivity limits objective diagnosis, monitoring, and therapeutic development. We present LENS (Latent sEMG Neuromuscular Signature), which decodes exertion-evoked musculoskeletal pain intensity from surface electromyography (sEMG) alone. LENS was pre-trained via a cross-modal self-supervised objective that reconstructs muscle oxygenation from sEMG in 183 adults. LENS was trained exclusively on healthy muscle physiology and generalized to an independent healthy cohort (Spearman's {rho}=0.52) and discriminated moderate-to-severe pain (AUROC=0.83). Using a label-free test-time adaptation, LENS generalized to an unseen chronic musculoskeletal pain cohort--myogenous temporomandibular disorder (mTMD)--with comparable performance ({rho}=0.61; AUROC=0.86). Reverse transfer, from mTMD to controls, was substantially weaker, an asymmetry attributable to elevated motor variability in chronic pain; excluding highly variable mTMD participants recovered performance, indicating a conserved pain signature masked by pathology-specific motor noise. LENS offers a scalable, physiological correlate of musculoskeletal pain from a single sEMG channel.
Related
- BiomECG: Learning Transferable ECG Representations from Small Cohorts
- Toward a Transferable Representation of Protein Dynamics for Functional Prediction and Mechanistic Discovery
- Climate-driven rodent demography provides a general, transferable basis for predicting arenavirus spillover
- Project-based learning to promote multidisciplinary integration and transferable skills in undergraduate biology students
- 3D Human Neuromuscular Architecture Encoded by Compliant Patterned Hydrogel Scaffolds
BibTeX
@misc{mouseli2026lens,
title = {{LENS: a transferable neuromuscular signature of musculoskeletal pain intensity}},
author = {P. Mouseli and N. W. De Vera and S. Sagheer and W. D. Reid and I. Jurisica and M. S. Angst and N. Aghaeepour and M. Moayedi and I. Cioffi},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.08.750203},
url = {https://www.biorxiv.org/content/10.64898/2026.09.08.750203v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - LENS: a transferable neuromuscular signature of musculoskeletal pain intensity
AU - P. Mouseli
AU - N. W. De Vera
AU - S. Sagheer
AU - W. D. Reid
AU - I. Jurisica
AU - M. S. Angst
AU - N. Aghaeepour
AU - M. Moayedi
AU - I. Cioffi
PY - 2026
DA - 2026/09/08
PB - bioRxiv
DO - 10.64898/2026.09.08.750203
UR - https://www.biorxiv.org/content/10.64898/2026.09.08.750203v1
AB - Self-reported pain remains the clinical standard for assessing musculoskeletal pain severity, but its subjectivity limits objective diagnosis, monitoring, and therapeutic development. We present LENS (Latent sEMG Neuromuscular Signature), which decodes exertion-evoked musculoskeletal pain intensity from surface electromyography (sEMG) alone. LENS was pre-trained via a cross-modal self-supervised objective that reconstructs muscle oxygenation from sEMG in 183 adults. LENS was trained exclusively on healthy muscle physiology and generalized to an independent healthy cohort (Spearman's {rho}=0.52) and discriminated moderate-to-severe pain (AUROC=0.83). Using a label-free test-time adaptation, LENS generalized to an unseen chronic musculoskeletal pain cohort--myogenous temporomandibular disorder (mTMD)--with comparable performance ({rho}=0.61; AUROC=0.86). Reverse transfer, from mTMD to controls, was substantially weaker, an asymmetry attributable to elevated motor variability in chronic pain; excluding highly variable mTMD participants recovered performance, indicating a conserved pain signature masked by pathology-specific motor noise. LENS offers a scalable, physiological correlate of musculoskeletal pain from a single sEMG channel.
ER -