Factors influencing traumatic brain injuries in maxillofacial fractures: A 12-year retrospective analysis of 2841 patients.

BACKGROUND/AIM: Results of studies investigating the association between traumatic brain injury (TBI) and maxillofacial fractures (MFs) have varied considerably. The present study aimed to evaluate the correlation between TBIs and MFs, as well as the impact of age, sex, trauma mechanism, and season on TBIs. MATERIALS AND METHODS: This 12-year retrospective study of 2841 patients used univariate and multivariate logistic regression to assess the association between MFs and other factors impacting TBIs. RESULTS: Among 2841 patients, 1978 TBIs occurred in 829 (29.2%), with intracranial injuries (n = 828) is the most common. Of 829 patients with TBIs, 688 were male and 141 were female, corresponding to a male-to-female ratio of 4.9:1.0. The most common age group was 40-49 years (24.6%). Vehicles (including motor vehicles and electric vehicles) accidents were the primary causes of injuries. Multivariate regression analyses revealed an increased risk for TBIs among males (odds ratio [OR] 0.632, p < 0.001). Patients >40 years of age were at higher risk for TBIs, especially those ≥70 years (OR 3.966, p = 0.001). Vehicle accidents were a high-risk factor for TBIs (OR 6.894, p < 0.001), and winter was the most prevalent season for such injuries (OR 1.559, p = 0.002). Risk for TBI increased by 136.4% in combined midfacial and mandibular fractures (p = 0.016) and by 101.6% in multiple midfacial fractures (p = 0.045). TBIs were less common in single mandibular fractures, notably in single-angle fractures, with a risk of only 0.204-fold. CONCLUSION: TBIs in MFs were significantly correlated with sex, age, aetiology, season and fracture location. Maxillofacial surgeons and emergency physicians must be aware of the possible association between TBIs and MFs to assess and manage this complicated relationship in a timely manner.

Epidemiology of maxillofacial fractures in northwest China: an 11-year retrospective study of 2240 patients.

BACKGROUND: The aim of this study was to determine the epidemiological pattern of maxillofacial fractures in northwestern China by retrospectively analysing the demographics, aetiologies, concomitant injuries, fracture sites, and management. METHODS: A 10-year retrospective analysis of 2240 patients with maxillofacial fractures admitted to the General Hospital of Ningxia Medical University was conducted. The extracted data included sex, age, aetiology, fracture site, concomitant injuries, time of treatment, therapeutic approaches and complications. Statistical analyses were performed, including descriptive analysis and the chi-square test. Logistic regression was used to determine the impact factors of maxillofacial fractures and concomitant injuries. P values < 0.05 were considered statistically significant. RESULTS: The age of the included patients ranged from 1 to 85 years, and the mean age was 35.88 ± 15.69 years. The male-to-female ratio was 3.9:1. The most frequent aetiology of maxillofacial fractures was road traffic accidents (RTAs) (56.3%), and the most common fracture sites were the anterior wall of the maxillary sinus, arcus zygomaticus and mandibular body. A total of 1147 patients (51.2%) were affected by concomitant injuries, with craniocerebral injury being the most common. Logistic regression analyses revealed increased risks of mid-facial fractures in elderly individuals (odds ratio (OR) = 1.029, P < 0.001) and females (OR = 0.719, P = 0.005). Younger patients had a higher risk of mandibular fractures (OR = 0.973, P < 0.001). RTAs increased the risk for mid-facial fractures and high falls increased the risk for mandibular fractures. CONCLUSIONS: The maxillofacial fracture pattern is correlated with sex, age and aetiology. Patients were mainly young and middle-aged males, and the main cause of injury was RTAs, mostly causing compound fractures. Medical staff must be systematically educated to comprehensively examine patients with injuries resulting from RTAs. The management of patients with fractures requires thorough consideration of the patient's age, aetiology, fracture site, and concomitant injuries.

Automated detection and classification of mandibular fractures on multislice spiral computed tomography using modified convolutional neural networks.

OBJECTIVE: To evaluate the performance of convolutional neural networks (CNNs) for the automated detection and classification of mandibular fractures on multislice spiral computed tomography (MSCT). STUDY DESIGN: MSCT data from 361 patients with mandibular fractures were retrospectively collected. Two experienced maxillofacial surgeons annotated the images as ground truth. Fractures were detected utilizing the following models: YOLOv3, YOLOv4, Faster R-CNN, CenterNet, and YOLOv5-TRS. Fracture sites were classified by the following models: AlexNet, GoogLeNet, ResNet50, original DenseNet-121, and modified DenseNet-121. The performance was evaluated for accuracy, sensitivity, specificity, and area under the curve (AUC). AUC values were compared using the Z-test and P values <.05 were considered to be statistically significant. RESULTS: Of all of the detection models, YOLOv5-TRS obtained the greatest mean accuracy (96.68%). Among all of the fracture subregions, body fractures were the most reliably detected (with accuracies of 88.59%-99.01%). For classification models, the AUCs for body fractures were higher than those of condyle and angle fractures, and they were all above 0.75, with the highest AUC at 0.903. Modified DenseNet-121 had the best overall classification performance with a mean AUC of 0.814. CONCLUSIONS: The modified CNN-based models demonstrated high reliability for the diagnosis of mandibular fractures on MSCT.