The diagnosis of osteoporosis is made by measuring bone mineral density (BMD) using dual-energy X-ray absorptiometry (DXA). Machine learning, one of the artificial intelligence methods, was used to predict low BMD without using DXA in elderly women. Medical records from 2541 females who visited the osteoporosis clinic were used in this study. As hyperparameters for machine learning, patient age, body mass index (BMI), and blood test data were used. As machine learning models, logistic regression, decision tree, random forest, gradient boosting trees, and lightGBM were used. Each model was trained to classify and predict low-BMD patients. The model performance was compared using a confusion matrix. The accuracy of each trained model was 0.772 in logistic regression, 0.739 in the decision tree, 0.775 in the random forest, 0.800 in gradient boosting, and 0.834 in lightGBM. The area under the curve (AUC) was 0.595 in the decision tree, 0.673 in logistic regression, 0.699 in the random forest, 0.840 in gradient boosting, and 0.961, which was the highest, in the lightGBM model. Important features were BMI, age, and the number of platelets. Shapley additive explanation scores in the lightGBM model showed that BMI, age, and ALT were ranked as important features. Among several machine learning models, the lightGBM model showed the best performance in the present research.

Although electromyography is the routine diagnostic method for cubital tunnel syndrome (CuTS), imaging diagnosis by measuring cross-sectional area (CSA) with ultrasonography (US) has also been attempted in recent years. In this study, deep learning (DL), an artificial intelligence (AI) method, was used on US images, and its diagnostic performance for detecting CuTS was investigated. Elbow images of 30 healthy volunteers and 30 patients diagnosed with CuTS were used. Three thousand US images were prepared per each group to visualize the short axis of the ulnar nerve. Transfer learning was performed on 5000 randomly selected training images using three pre-trained models, and the remaining images were used for testing. The model was evaluated by analyzing a confusion matrix and the area under the receiver operating characteristic curve. Occlusion sensitivity and locally interpretable model-agnostic explanations were used to visualize the features deemed important by the AI. The highest score had an accuracy of 0.90, a precision of 0.86, a recall of 1.00, and an F-measure of 0.92. Visualization results show that the DL models focused on the epineurium of the ulnar nerve and the surrounding soft tissue. The proposed technique enables the accurate prediction of CuTS without the need to measure CSA.

Coronal shear fractures of the distal humerus are rare injuries, and fragmentation of the capitellum and trochlea with posterior comminution is challenging for surgeons. We retrospectively evaluated the functional outcomes of patients with coronal shear fractures managed with open reduction and internal fixation, focusing on the number of trochlea fragments in Dubberley type 3B fractures. The functional outcomes of 25 patients, including 8 patients with type 3B fractures, with a mean age (and standard deviation) of 57 ± 20 years, were evaluated at a mean follow-up duration of 15 ± 9 months. Type 3B fractures were classified into two groups: those with two trochlea fragments or less group (group A) and those with three or more fragments (group B). Patient outcomes were assessed with clinical and radiographic examination, range of motion, and the Mayo Elbow Performance scale (MEPS). Two patients with type 3B in group B experienced nonunion, and two patients with type 3B in group A and 1 patient with type 1B demonstrated avascular necrosis on radiographs. The average MEPS score was 96.3 points (range, 70-100), with 18 excellent, 5 good, and 1 fair results. The average range of motion was 10 ± 8 to 130 ± 12. The MEPS score worsened as Dubberley classification progressed from type 1 to type 3 (98.3 vs. 96.7 vs. 88, P = .014, respectively) and subtypes A to B (97.9 vs. 90, P = .014, respectively). In comparing groups A and B, the MEPS score was significantly worse in group B (93.8 vs. 76.3, P = .006). Our open reduction and internal fixation results were largely good, although functional outcomes were diminished as Dubberley classification progressed from type 1 to type 3 and subtype A to B. Type 3B fractures with three trochlea fragments or more in the elderly were the most difficult to treat with open reduction and internal fixation and possibly 1-term total elbow arthroplasty.

Advanced glycation end-products (AGEs) play a critical supportive role during musculoskeletal disorders via glycosylation and oxidative stress. Though apocynin, identified as a potent and selective inhibitor of NADPH oxidase, has been reported to be involved in pathogen-induced reactive oxygen species (ROS), its role in age-related rotator cuff degeneration has not been well clarified. Therefore, this study aims to evaluate the in vitro effects of apocynin on human rotator cuff-derived cells. Twelve patients with rotator cuff tears (RCTs) participated in the study. Supraspinatus tendons from patients with RCTs were collected and cultured. After the preparation of RC-derived cells, they were divided into four groups (control group, control + apocynin group, AGEs group, AGEs + apocynin group), and gene marker expression, cell viability, and intracellular ROS production were evaluated. The gene expression of NOX, IL-6, and the receptor for AGEs (RAGE) was significantly decreased by apocynin. We also examined the effect of apocynin in vitro. The results showed that ROS induction and increasing apoptotic cells after treatment of AGEs were significantly decreased, and cell viability increased considerably. These results suggest that apocynin can effectively reduce AGE-induced oxidative stress by inhibiting NOX activation. Thus, apocynin is a potential prodrug in preventing degenerative changes of the rotor cuff.

The triangular fibrocartilage complex (TFCC) is a significant stabilizer of the distal radioulnar joint. Diagnosing TFCC injury is currently difficult, but ultrasonography (US) has emerged as a low-cost, minimally invasive diagnostic tool. We aimed to quantitatively analyze TFCC by performing motion analysis by using US. Twelve healthy volunteers, comprising 24 wrists (control group), and 15 patients with TFCC Palmer type 1B injuries (injury group) participated. The US transducer was positioned between the ulnar styloid process and triquetrum and was tilted ulnarly 30° from the vertical line. The wrist was then actively moved from 10° of radial deviation to 20° of ulnar deviation in a 60-rounds-per-minute rhythm that was paced by a metronome. The articular disc displacement velocity magnitude was analyzed by using particle image velocimetry fluid measurement software. The mean area of the articular discs was larger on ulnar deviation in the control group. The mean articular disc area on radial deviation was larger in the injury group. The average articular disc velocity magnitude for the injury group was significantly higher than that for the control group. The results suggest that patients with TFCC injury lose articular disc cushioning and static stability, and subsequent abnormal motion can be analyzed by using US.