ObjectiveTo evaluate the specific application and effect of balance point fixation technique in arthroscopic fixation of avulsion fracture of anterior cruciate ligament.MethodsThe data of 65 patients with anterior cruciate ligament avulsion fracture treated by arthroscopy in Department of Orthopaedics, Panzhihua Central Hospital between June 2012 and June 2018 were analyzed retrospectively. According to whether the balance point fixation technique was used or not, the patients were divided into routine operation group (group A, n=22) and balance point fixation group (group B, n=43). The operation time, Visual Analogue Scale (VAS) pain score, length of hospital stay, intraoperative bone re-fracture rate, incidences of limb swelling and deep venous thrombosis, Lysholm score and knee joint stability of the two groups were analyzed. Chi-square test or Fisher’s exact test was used for nominal data. Independent samples t-test or paired samples t-test was used for measurement data. Rank sum test was used for ordinal data. Repeated measures analysis of variance was used for repeated measurement data. Two-sided statistical significance level was set at α=0.05.ResultsThere was no statistically significant difference in age, sex composition, fracture type, combined injury, time from injury to operation, preoperative VAS score, or Lysholm score between the two groups (P>0.05). The incisions of all patients healed in the first stage without incision complications. After adjustment, the reduction of fracture in group A was basically satisfactory, 4 cases (18.2%) had re-fracture; 1 case (2.3%) in group B had re-fracture due to poor bone condition, and group B was better than group A in re-fracture incidence (P=0.041). The operation time and length of hospital stay in group B were shorter than those in group A [(90.27±34.27) vs. (49.67±10.44) min,P<0.001; (8.09±1.23) vs. (5.35±1.07) d, P<0.001], the postoperative VAS score in group B was lower than that in group A (4.23±0.87 vs. 2.60±0.62, P<0.001), the degree of pain relief in group B was better than that in group A (3.32±1.29 vs. 4.44±1.50, P=0.004), the incidence of postoperative limb swelling in group B was lower than that in group A (22.7% vs. 4.7%, P<0.05); the difference in incidence of postoperative deep venous thrombosis between the two groups was not statistically significant (P>0.05). All patients were followed up for more than one year, the fractures healed completely, and the postoperative VAS score and Lysholm score at one year after operation were significantly improved compared with those before operation, but there was no significant difference in the postoperative 6-month Lysholm score, stability evaluation, or postoperative 1-year Lysholm score between the two groups (P>0.05).ConclusionsThe balance point fixation technique plays a positive role in relieving postoperative pain, shortening operation time and average hospital stay, and reducing the incidence of complications by realizing the quantification of the best fixed point to reduce repeated operation and side injury. It can provide a technical reference for clinical work.
ObjectiveTo construct a machine learning (ML) model incorporating preoperative, intraoperative, and early postoperative variables to predict cardiac surgery-associated acute kidney injury (CSA-AKI), thereby providing decision support for early clinical warning and intervention. MethodsPatients who underwent cardiac surgery at Nanjing Medical University Affiliated Nanjing Hospital from 2020 to 2022 were included in this study. The cohort was randomly divided into a training set and a validation set at a ratio of 7:3. Five ML models were constructed, including random forest (RF), logistic regression (LR), gradient boosted decision tree (GBDT), extreme gradient boosting (XGBoost), and support vector machines (SVM). Model performance was evaluated using metrics such as the area under the receiver operating characteristic curve (AUC), and the SHapley Additive exPlanations (SHAP) method was applied for model interpretation. ResultsA total of 3 679 patients were included, comprising 2 217 males and 1 462 females, with a median age of 64 (56, 70) years. Fifteen feature variables were incorporated: history of heart failure, age, body mass index, smoking history, creatinine, cardiopulmonary bypass time, total blood transfusion volume, total urine output, uric acid, hemoglobin, Acute Physiology and Chronic Health Evaluation Ⅱ (APACHE Ⅱ) score, European System for Cardiac Operative Risk Evaluation (EuroSCORE), postoperative white blood cell count, postoperative lactate, and postoperative lymphocyte count. Among the five ML models, LR, RF, GBDT, and XGBoost showed no statistical differences in performance within the validation set; however, considering the dimensions of performance, model robustness, and clinical interpretability, the LR model was deemed superior. SHAP analysis quantified the predictive weights of each variable (indicating that a history of heart failure and advanced age were high-risk features) and visually demonstrated the underlying causes of personalized risk for individual patients. Based on the optimized LR model, an online web-based risk calculator was successfully developed to output personalized probability of CSA-AKI occurrence. ConclusionA clinical prediction model for CSA-AKI risk is constructed using ML techniques, demonstrating favorable predictive performance and interpretability. This risk assessment tool can provide early warnings for clinicians and assist in optimizing postoperative treatment strategies, thereby reducing the risk of CSA-AKI occurrence.