Classifying office workers with and without cervicogenic headache or neck and shoulder pain using posture-based deep learning models: a multicenter retrospective study

TL;DR

This study uses deep learning models to classify office workers with or without cervicogenic headache and neck and shoulder pain based on their sitting posture images.

Contribution

The novel use of posture-based deep learning models for classifying musculoskeletal conditions in office workers.

Findings

ResNet50 achieved the highest performance for cervicogenic headache classification with an AUC of 0.782.

EfficientNet B5 showed the highest AUC of 0.744 for combined cervicogenic headache and neck and shoulder pain classification.

Class Activation Mapping revealed distinct focus areas for different conditions, such as the cervical region for cervicogenic headache.

Abstract

To develop and evaluate deep learning models for classifying office workers with and without cervicogenic headache (CH) and/or neck and shoulder pain (NSP), based on habitual sitting posture images.

This multicenter, retrospective, observational study analyzed 904 digital images of habitual sitting postures of 531 office workers. Three deep learning models (VGG19, ResNet50, and EfficientNet B5) were trained and evaluated to classify the CH, NSP, and combined CH + NSP. Model performance was assessed using 4-fold cross-validation with metrics including area under the curve (AUC), accuracy (ACC), sensitivity (Sen), specificity (Spe), and F1 score. Statistical significance was evaluated using 95% confidence intervals. Class Activation Mapping (CAM) was used to visualize the model focus areas.

Among 531 office workers (135 with CH, 365 with NSP, 108 with both conditions and 139 control group), ResNet50 achieved the highest performance for CH classification with an AUC of 0.782 (95% CI: 0.770–0.793) and an accuracy of 0.750 (95% CI: 0.731–0.768). NSP classification showed more modest results, with ResNet50 achieving an accuracy of 0.677 (95% CI: 0.640–0.713). In the combined CH + NSP classification, EfficientNet B5 demonstrated the highest AUC of 0.744 (95% CI: 0.647–0.841). CAM analysis revealed distinct focus areas for each condition: the cervical region for CH, the lower body for NSP, and broader neck and trunk regions for combined CH + NSP.

Deep learning models show potential for classifying CH and NSP based on habitual sitting posture images, with varying performances across conditions. The ability of these models to detect subtle postural patterns associated with different musculoskeletal conditions suggests their possible applications for early detection and intervention. However, the complex relationship between static posture and musculoskeletal pain underscores the need for a multimodal assessment approach in clinical practice.

Figures