Despite the availability of a series of tests, detection of chronic traumatic osteomyelitis is still exhausting in clinical practice. We hypothesized that machine learning based on computed-tomography (CT) images would provide better diagnostic performance for extremity traumatic chronic osteomyelitis than the serological biomarker alone. A retrospective study was carried out to collect medical data from patients with extremity traumatic osteomyelitis according to the criteria of musculoskeletal infection society. In each patient, serum levels of C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), and D-dimer were measured and CT scan of the extremity was conducted 7 days after admission preoperatively. A deep residual network (ResNet) machine learning model was established for recognition of bone lesion on the CT image. A total of 28,718 CT images from 163 adult patients were included. Then, we randomly extracted 80% of all CT images from each patient for training, 10% for validation, and 10% for testing. Our results showed that machine learning (83.4%) outperformed CRP (53.2%), ESR (68.8%), and D-dimer (68.1%) separately in accuracy. Meanwhile, machine learning (88.0%) demonstrated highest sensitivity when compared with CRP (50.6%), ESR (73.0%), and D-dimer (51.7%). Considering the specificity, machine learning (77.0%) is better than CRP (59.4%) and ESR (62.2%), but not D-dimer (83.8%). Our findings indicated that machine learning based on CT images is an effective and promising avenue for detection of chronic traumatic osteomyelitis in the extremity.

Muscular atrophy after limb fracture is a frequently occurring complication with multiple causes. Different treatments and targeted rehabilitation procedures should be carried out based on the causes. However, bedside evaluation methods are invasive in clinical practice nowadays, lacking reliable non-invasive methods. In this study, we propose a non-invasive flexible surface electromyography system with machine learning algorithms to distinguish nerve-injury and limb immobilization-related atrophy. First, a flexible surface electromyography sensor was designed and verified by in vitro tests for its robustness and flexibility. Then, in vivo tests on rats proved the reliability compared with the traditional invasive diagnosis method. Finally, this system was applied for the diagnosis of muscular atrophy in 10 patients. The flexible surface electromyography sensor can achieve a max strain of 12.0%, which ensures close contact with the skin. The in vivo tests on rats show great comparability with the traditional invasive diagnosis method. It can achieve a high specificity of 95.28% and sensitivity of 98.98%. Application on patients reaches a relatively high specificity of 89.44% and sensitivity of 91.94%. The proposed painless surface electromyography system can be an easy and accurate supplementary for bedside muscular atrophy causes evaluation, holding excellent contact with the body.