Development and Validation of a Machine Learning Algorithm to Predict the Risk of Blood Transfusion after Total Hip Replacement in Patients with Femoral Neck Fractures: A Multicenter Retrospective Cohort Study.

OBJECTIVE: Total hip arthroplasty (THA) remains the primary treatment option for femoral neck fractures in elderly patients. This study aims to explore the risk factors associated with allogeneic blood transfusion after surgery and to develop a dynamic prediction model to predict post-operative blood transfusion requirements. This will provide more accurate guidance for perioperative humoral management and rational allocation of medical resources. METHODS: We retrospectively analyzed data from 829 patients who underwent total hip arthroplasty for femoral neck fractures at three third-class hospitals between January 2017 and August 2023. Patient data from one hospital were used for model development, whereas data from the other two hospitals were used for external validation. Logistic regression analysis was used to screen the characteristic subsets related to blood transfusion. Various machine learning algorithms, including logistic regression, SVA (support vector machine), K-NN (k-nearest neighbors), MLP (multilayer perceptron), naive Bayes, decision tree, random forest, and gradient boosting, were used to process the data and construct prediction models. A 10-fold cross-validation algorithm facilitated the comparison of the predictive performance of the models, resulting in the selection of the best-performing model for the development of an open-source computing program. RESULTS: BMI (body mass index), surgical duration, IBL (intraoperative blood loss), anticoagulant history, utilization rate of tranexamic acid, Pre-Hb, and Pre-ALB were included in the model as well as independent risk factors. The average area under curve (AUC) values for each model were as follows: logistic regression (0.98); SVA (0.91); k-NN (0.87) MLP, (0.96); naive Bayes (0.97); decision tree (0.87); random forest (0.96); and gradient boosting (0.97). A web calculator based on the best model is available at: (https://nomo99.shinyapps.io/dynnomapp/). CONCLUSION: Utilizing a computer algorithm, a prediction model with a high discrimination accuracy (AUC > 0.5) was developed. The logistic regression model demonstrated superior differentiation and reliability, thereby successfully passing external validation. The model's strong generalizability and applicability have significant implications for clinicians, aiding in the identification of patients at high risk for postoperative blood transfusion.

[Feasibility analysis and nail planning ofS2 iliac crest screw placement in children].

OBJECTIVE: To evaluate the feasibility of S2 alar iliac screw insertion in Chinese children using computerized three-dimension reconstruction and simulated screw placement technique, and to optimize the measurement of screw parameters. METHODS: A total of 83 pelvic CT data of children who underwent pelvic CT scan December 2018 to December 2020 were retrospectively analyzed, excluding fractures, deformities, and tumors. There were 44 boys and 39 girls, with an average age of (10.66±3.52) years, and were divided into 4 groups based on age (group A:5 to 7 years old;group B:8 to 10 years old;group C:11-13 years old;group D:14 to 16 years old). The original CT data obtained were imported into Mimics software, and the bony structure of the pelvis was reconstructed, and the maximum and minimum cranial angles of the screws were simulated in the three-dimensional view with the placement of 6.5 mm diameter S2 alar iliac screws. Subsequently, the coronal angle, sagittal angle, transverse angle, total length of the screw, length of the screw in the sacrum, width of the iliac, and distance of the entry point from the skin were measured in 3-Matic software at the maximum and minimum head tilt angles, respectively. The differences among the screw parameters of S2 alar iliac screws in children of different ages and the differences between gender and side were compared and analyzed. RESULTS: In all 83 children, 6.5 mm diameter S2 iliac screws could be placed. There was no significant difference between the side of each screw placement parameter. The 5 to 7 years old children had a significantly smaller screw coronal angle than other age groups, but in the screw sagittal angle, the difference was more mixed. The 5 to 7 years old children could obtain a larger angle at the maximum head tilt angle of the screw, but at the minimum cranial angle, the larger angle was obtained in the age group of 11 to 13 years old. There were no significant differences among the age groups. The coronal angle and sagittal angle under maximum cephalic angle and minimum cranial angle of 5 to 7 years old male were (40.91±2.91)° and (51.85±3.75)° respectively, which were significantly greater than in female. The coronal angle under minimum cranial angle was significantly greater in girls aged 8-10 years old than in boys. For the remaining screw placement angle parameters, there were no significant differences between gender. The differences in the minimum iliac width, the screw length, and the length of the sacral screws showed an increasing trend with age in all age groups. The distance from the screw entry point to the skin in boys were significantly smaller than that of girls. The minimum width of the iliac in boys at 14 to 16 years of age were significantly wider than that in girls at the same stage. In contrast, in girls aged 5 to 7 years and 11 to 13 years, the screw length was significantly longer than that of boys at the same stage. CONCLUSION: The pelvis of children aged 5 to 16 years can safely accommodate the placement of 6.5 mm diameter S2 alar iliac screws, but the bony structures of the pelvis are developing and growing in children, precise assessment is needed to plan a reasonable screw trajectory and select the appropriate screw length.

A randomized controlled trial: comparing extracorporeal shock wave therapy versus local corticosteroid injection for the treatment of carpal tunnel syndrome.

PURPOSE: Extracorporeal shock wave therapy (ESWT) has been reported as a new therapy for carpal tunnel syndrome (CTS). However, few studies have compared ESWT with the local corticosteroid injection (LCI). METHODS: In this study, a randomized controlled trial comparing 30 patients with ESWT and 25 patients treated with LCI was conducted. The clinical outcomes were obtained with tests including the visual analog scale (VAS) for pain and paresthesia, the Boston Carpal Tunnel Questionnaire (BQ), and a nerve conduction study, before the study started and at three, nine, and 12 weeks after the start of the treatment. RESULTS: Significantly greater improvement in the VAS and BQ scores was noted for the ESWT group than for the LCI group (P < 0.05). For the nerve conduction study, there was a significant improvement in the median nerve sensory nerve action potential distal latency at the nine and 12-week follow-ups for the ESWT group. CONCLUSIONS: ESWT is a useful noninvasive short-term treatment for mild to moderate carpal tunnel syndrome and elicits a better recovery than LCI does, but more research is needed to test the clinical outcomes of ESWT.

Safe trajectory for an occipital condyle screw: A computer simulation study.

OBJECTIVE: The purpose of this study was to evaluate the feasibility of posterior occipital condyle screw (OCS) placement analysis of the safe trajectory area for screw insertion. METHODS: Computed tomographic angiography scans of patients (46 males and 27 females) with normal occipitocervical structures were obtained consecutively. Vertebral artery (VA)-occiput distance <4.0 mm was defined as "unfeasible" for OCS fixation, and occipital-atlas angulation was measured to assess the feasibility of screw placement. Next, the placement of 3.5 mm diameter OCS was simulated, the probability of breach of structures surrounding occipital condyles was calculated, and placement parameters were analyzed. RESULTS: OCS placement was feasible in 91.1% (133/146) of occipital condyles, and the feasible probability also presented a significant sex-related difference: The probability was higher for males than for females (95.7% vs. 83.3%, p < 0.05). The incidence of anatomical structures injured under screw placement limitation was 18.8% (VA), 81.2% (hypoglossal canal), 59.4% (occipital-atlas joint), and 40.6% (occiput bone surface). There were no significant differences between the left and right condyles in relation to the measured parameters (p > 0.05). The screw range of motion was significantly smaller in females than in males (p < 0.05). The feasibility of OCS placement and OCS range of motion were significantly greater in the kyphosis group (>5°) than in the other two groups (p < 0.05). CONCLUSION: OCS placement is a feasible technique for occipital-cervical fusion. The male group and occipitocervical region kyphosis group had a wider available space for OCS placement. Tangent angulation may be useful for the accurate and safe placement of an OCS.

Modified Broström Repair With and Without Augmentation Using Suture Tape for Chronic Lateral Ankle Instability.

OBJECTIVE: To compare the clinical and radiological outcome between the modified Broström repair with augmentation using suture tape (MBA) and the modified Broström repair (MB) for patients with chronic lateral ankle instability. METHODS: A retrospective study was performed in Ningbo No. 6 Hospital. The study included 53 patients who underwent surgical treatment from March 2014 to July 2016 and were followed for 2 years. A total of 25 patients underwent modified Broström repair with augmentation using suture tape, and 28 patients were treated with modified Broström repair. Patients were evaluated using the American Orthopedic Foot and Ankle Scale (AOFAS) hindfoot scale, the Foot and Ankle Ability Measure (FAAM) score, range of motion (ROM), and the visual analogue scale (VAS). The talar tilt angle (TTA) and anterior talar translation (ATT) were used to evaluate the mechanical stability. All radiological outcomes were measured by two orthopaedic surgeons, with the measurements repeated 3 days later. RESULTS: The mean age of the patients was 26.6 ± 17.8 years in the MBA group and 28.1 ± 19.4 years in the MB group, and no statistical difference in preoperative data was found between two groups. There were significant differences before and after the operation within the groups. Both groups achieved satisfactory outcomes, and significant improvements (VAS, FAAM, AOFAS, TTA, and ATT) were observed between the 1-year follow-up and final follow-up (P < 0.05). The MBA group showed significant improvement in the FAAM Sport (87.1 ± 5.4 vs 78.2 ± 12.0, P = 0.001) and total scores (93.1 ± 2.3 vs 90.5 ± 5.1, P = 0.027) at the final follow-up compared with the MB group, and for the other outcomes, there were no significant differences between the two groups. CONCLUSION: The modified Broström repair with augmentation using suture tap for chronic lateral ankle instability achieves a better outcome; however, further research is necessary.