Epidemiology and Management of Pediatric Fractures in Malawi.

BACKGROUND: Pediatric fractures are common in Malawi, and surgical care, when needed, remains inaccessible to many. Understanding which children in Malawi receive surgery or nonsurgical treatment would help set priorities for trauma system development. METHODS: We used multivariate logistic regression to evaluate associations between surgical treatment and age, sex, school enrollment, injury mechanism, fracture type, open fracture, referral status, hospital of presentation, delayed presentation (≥2 days), healthcare provider, and inpatient vs outpatient treatment. RESULTS: From 2016 to 2020, 10,400 pediatric fractures were recorded in the Malawi Fracture Registry. Fractures were most commonly of the wrist (26%), forearm (17%), and elbow (14%). Surgical fixation was performed on 4.0% of patients, and 24 (13.0%) open fractures were treated nonsurgically, without débridement or fixation. Fractures of the proximal and diaphyseal humerus (odds ratio [OR], 3.72; 95% confidence interval [CI], 2.36 to 5.87), knee (OR, 3.16; 95% CI, 1.68 to 5.95), and ankle (OR, 2.63; 95% CI, 1.49 to 4.63) had highest odds of surgery. Odds of surgical treatment were lower for children referred from another facility (OR, 0.62; 95% CI, 0.49 to 0.77). CONCLUSIONS: Most Malawian children with fractures are treated nonsurgically, including many who may benefit from surgery. There is a need to increase surgical capacity, optimize referral patterns, and standardize fracture management in Malawi.

Concomitant Procedures, Black Race, Male Sex, and General Anesthesia Show Fair Predictive Value for Prolonged Rotator Cuff Repair Operative Time: Analysis of the NSQIP Database Using Machine Learning.

PURPOSE: The purpose of this study is to develop machine learning models using the American College of Surgeons National Quality Improvement Program (ACS-NSQIP) database to predict prolonged operative time (POT) for rotator cuff repair (RCR). Furthermore, this study aims to use the trained machine learning (ML) models, cross-referenced with traditional multivariate logistic regression (MLR), to determine the key perioperative variables that may predict POT for RCR. METHODS: Data were obtained from a large, national database (NSQIP) from 2021. Patients with unilateral RCR procedures were included. Demographic, preoperative, and operative variables were analyzed. A multivariable logistic regression (MLR) model and various other machine learning techniques, including random forest (RF) and artificial neural network (ANN), were compared using area under the curve (AUC), calibration, Brier score, and decision curve analysis. Feature importance was identified from the overall best-performing model. RESULTS: A total of 6,690 patients met inclusion criteria. The random forest (RF) ML model had the highest AUC upon internal validation (0.706) and the lowest Brier score (0.15), outperforming the other models. The RF model also demonstrated strong performance upon assessment of the calibration curves (Slope = 0.86, Intercept = 0.08) and decision curve analysis. The model identified concomitant procedure, specifically labral repair and biceps tenodesis, as the most important variable for determining POT, followed by age <30 years, Black or African American race, male sex, and general anesthesia. CONCLUSIONS: Despite the advanced machine learning models used in this study, the NSQIP dataset was only able to fairly predict POT following RCR. The RF model identified concomitant procedures, specifically labral repair and biceps tenodesis, as the most important variables for determining POT. Additionally, demographic factors such as age <30 years, Black race, and general anesthesia were significant predictors. While male sex was identified as important in the RF model, the MLR model indicated that its predictive value is primarily in conjunction with specific procedures like biceps tenodesis and subacromial decompression.