Background: Screening for elbow osteochondritis dissecans (OCD) using ultrasound (US) is essential for early detection and successful conservative treatment. The aim of the study is to determine the diagnostic accuracy of YOLOv8, a deep-learning-based artificial intelligence model, for US images of OCD or normal elbow-joint images. Methods: A total of 2430 images were used. Using the YOLOv8 model, image classification and object detection were performed to recognize OCD lesions or standard views of normal elbow joints. Results: In the binary classification of normal and OCD lesions, the values from the confusion matrix were the following: Accuracy = 0.998, Recall = 0.9975, Precision = 1.000, and F-measure = 0.9987. The mean average precision (mAP) comparing the bounding box detected by the trained model with the true-label bounding box was 0.994 in the YOLOv8n model and 0.995 in the YOLOv8m model. Conclusions: The YOLOv8 model was trained for image classification and object detection of standard views of elbow joints and OCD lesions. Both tasks were able to be achieved with high accuracy and may be useful for mass screening at medical check-ups for baseball elbow.

Most shoulder rotator cuff tears (RCTs) are caused by non-traumatic age-related rotator cuff degeneration, of which hyperglycemia is a risk factor due to its glycation reaction and oxidative stress. We aimed to identify the influence of diabetes-induced glycation and oxidative stress in patients with non-traumatic shoulder RCTs. Twenty patients, aged over 50 years, with non-traumatic shoulder RCTs participated in this study. Patients with a history of diabetes mellitus or preoperative HbA1c ≥ 6.5% were assigned to the diabetic group (n = 10), and the rest to the non-diabetic group (n = 10). Cell proliferation; expression of genes related to oxidative stress, glycation reaction, inflammation, and collagen; intracellular reactive oxygen species (ROS) levels; and apoptosis rates were analyzed. The diabetic group had significantly lower cell proliferation than the non-diabetic group. In the diabetic group, the mRNA expression levels of NOX1, NOX4, IL6, RAGE, type III collagen, MMP2, TIMP1, and TIMP2 were significantly higher; type I collagen expression was significantly lower; and the rate of ROS-positive cells and apoptotic cells, as well as the expression of advanced glycation end-products (AGEs) and the receptor for AGEs (RAGE), was significantly higher. In conclusion, hyperglycemia caused by diabetes mellitus increased AGE and RAGE expression, and led to increased NOX expression, ROS production, and apoptosis in the human rotator cuff. This provides scope to find a preventive treatment for non-traumatic RCTs by inhibiting glycation and oxidative stress.

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.

Purpose: One-stage arthroscopic rotator cuff repair with manipulation has been recently performed for rotator cuff tears with shoulder stiffness, whereas some patients require capsular release due to severe stiffness that is difficult to treat with manipulation. The purpose of this study was to analyze patient backgrounds and related factors of success or failure of manipulation alone for the treatment of shoulder stiffness associated with rotator cuff tears. Methods: This study included 64 patients with rotator cuff tears and shoulder stiffness who underwent arthroscopic rotator cuff repair with manipulation alone or with manipulation and capsular release of the glenohumeral joint at our institution between January 2015 and September 2019. The patients were divided into two groups: those whose shoulder stiffness could be improved by manipulation alone (Manipulation group) and those whose stiffness could not be improved by manipulation alone and required capsular release (Capsular release addition group). Analysis was performed between the two groups regarding patient backgrounds and related factors, including rotator cuff tear morphology and range of motions pre- and postoperatively. Results: Exactly 45 patients and 19 patients were included in Manipulation group and Capsular release addition group, respectively. A comparison between the two groups showed that patient age (p = 0.0040), sex (p = 0.0005), and injury due to trauma (p = 0.0018) were significantly related to the success or failure of manipulation alone. Multivariate logistic regression analysis on these three factors showed that sex (odds ratio, 5.5; p = 0.048) was significantly associated with the success or failure of manipulation alone. In both groups, the passive ROM of all patients improved at the last postoperative follow-up compared to their pre-operative values (p < 0.001), except for internal rotation in the Capsular release addition group (p = 0.49). Conclusion: Young male patients who have shoulder stiffness associated with rotator cuff tears should be considered for arthroscopic capsular release rather than manipulation.