Correlation between shape-closed femoral stem design and bone cement implantation syndrome in osteoporotic elderly femoral neck fracture undergoing cemented hip arthroplasty: A retrospective case-control study in 128 patients.

BACKGROUND: Bone cement implantation syndrome (BCIS) is a serious and potentially fatal complication especially in patients with osteoporotic femoral neck fracture (OFNF) undergoing cemented hip arthroplasty (CHA). Recent studies showed that the shape-closed femoral stem profile could lead to a significant increase of the intramedullary pressure during cementation and prosthesis insertion. This study aimed to (1) correlate the use of shaped-closed femoral stem and other perioperative risk factors with severe grade of BCIS grade 2 or 3: BCIS gr2/3, and (2) identify the prevalence of BCIS in the elderly patients with OFNF and treated with CHA. HYPOTHESIS: Large wedge-shaped (or "shape-closed") femoral stem design would significantly associate with BCIS gr2/3 in the elderly patients who sustained OFNF and underwent CHA. PATIENTS AND METHODS: A total of 128 OFNF patients, who aged over 75years and underwent CHA were retrospectively reviewed and then allocated into 2 groups: SC Group (use shape-closed femoral stem, n=40) and FC Group (use force-closed femoral stem, n=88). BCIS was grading in all patients according to Donaldson classification. Perioperative data between the patients with BCIS-gr2/3 and those with BCIS grade 0 or 1 (BCIS-gr0/1) were compared. Multiple logistic regression analysis was used to identify predictive factors for BCIS-gr2/3. RESULTS: The prevalence of overall BCIS and BCIS-gr2/3 was 32.8% (n=42) and 6.2% (n=8), respectively. The total in-hospital and 1-year mortality rates were 2.3% and 4.7%, respectively. The major perioperative complication in patients with BCIS-gr2/3 was significantly higher compared to those in patients with BCIS-gr0/1 (62.5% vs. 10.0%, p=0.001). Multivariate analysis showed that age>90years (OR=9.4, 95% CI: 1.4-62.9, p=0.02), preinjury Parker mobility score<4 (OR=48.8; 95% CI: 2.7-897.2, p=0.008) and shape-closed femoral stem used (OR=19.1; 95% CI: 1.8-204.5, p=0.01) were the significant independent predictors for BCIS-gr2/3 in these patients. CONCLUSION: BCIS in OFNF patients undergoing CHA is common and associates with a high major perioperative complication rate. Our initial hypothesis is validated as the patients at risk for BCIS-gr2/3 are those whose CHA procedures use a shape-closed femoral stem design and with extreme age, and having poor preinjury ambulatory status. Therefore, we recommended using cementless stem as the first option in OFNF. However, if CHA is needed, strict guideline for cement insertion should be followed with force-closed stem application to avoid the risk of BCIS-gr2/3. LEVEL OF EVIDENCE: III; retrospective case-control study.

Development and internal validation of a machine-learning-developed model for predicting 1-year mortality after fragility hip fracture.

BACKGROUND: Fragility hip fracture increases morbidity and mortality in older adult patients, especially within the first year. Identification of patients at high risk of death facilitates modification of associated perioperative factors that can reduce mortality. Various machine learning algorithms have been developed and are widely used in healthcare research, particularly for mortality prediction. This study aimed to develop and internally validate 7 machine learning models to predict 1-year mortality after fragility hip fracture. METHODS: This retrospective study included patients with fragility hip fractures from a single center (Siriraj Hospital, Bangkok, Thailand) from July 2016 to October 2018. A total of 492 patients were enrolled. They were randomly categorized into a training group (344 cases, 70%) or a testing group (148 cases, 30%). Various machine learning techniques were used: the Gradient Boosting Classifier (GB), Random Forests Classifier (RF), Artificial Neural Network Classifier (ANN), Logistic Regression Classifier (LR), Naive Bayes Classifier (NB), Support Vector Machine Classifier (SVM), and K-Nearest Neighbors Classifier (KNN). All models were internally validated by evaluating their performance and the area under a receiver operating characteristic curve (AUC). RESULTS: For the testing dataset, the accuracies were GB model = 0.93, RF model = 0.95, ANN model = 0.94, LR model = 0.91, NB model = 0.89, SVM model = 0.90, and KNN model = 0.90. All models achieved high AUCs that ranged between 0.81 and 0.99. The RF model also provided a negative predictive value of 0.96, a positive predictive value of 0.93, a specificity of 0.99, and a sensitivity of 0.68. CONCLUSIONS: Our machine learning approach facilitated the successful development of an accurate model to predict 1-year mortality after fragility hip fracture. Several machine learning algorithms (eg, Gradient Boosting and Random Forest) had the potential to provide high predictive performance based on the clinical parameters of each patient. The web application is available at www.hipprediction.com . External validation in a larger group of patients or in different hospital settings is warranted to evaluate the clinical utility of this tool. TRIAL REGISTRATION: Thai Clinical Trials Registry (22 February 2021; reg. no. TCTR20210222003 ).

Bone mineral density response prediction following osteoporosis treatment using machine learning to aid personalized therapy.

Osteoporosis is a global health problem for ageing populations. The goals of osteoporosis treatment are to improve bone mineral density (BMD) and prevent fractures. One major obstacle that remains a great challenge to achieve the goals is how to select the best treatment regimen for individual patients. We developed a computational model from 8981 clinical variables, including demographic data, diagnoses, laboratory results, medications, and initial BMD results, taken from 10-year period of electronic medical records to predict BMD response after treatment. We trained 7 machine learning models with 13,562 osteoporosis treatment instances [comprising 5080 (37.46%) inadequate treatment responses and 8482 (62.54%) adequate responses] and selected the best model (Random Forests with area under the receiver operating curve of 0.70, accuracy of 0.69, precision of 0.70, and recall of 0.89) to individually predict treatment responses of 11 therapeutic regimens, then selected the best predicted regimen to compare with the actual regimen. The results showed that the average treatment response of the recommended regimens was 9.54% higher than the actual regimens. In summary, our novel approach using a machine learning-based decision support system is capable of predicting BMD response after osteoporosis treatment and personalising the most appropriate treatment regimen for an individual patient.