INTRODUCTION: Radiology plays an integral role in fracture detection in the emergency department (ED). After hours, when there are fewer reporting radiologists, most radiographs are interpreted by ED physicians. A minority of these interpretations may miss diagnoses, which later require the callback of patients for further management. Artificial intelligence (AI) has been viewed as a potential solution to augment the shortage of radiologists after hours. We explored the efficacy of an AI solution in the detection of appendicular and pelvic fractures for adult radiographs performed after hours at a general hospital ED in Singapore, and estimated the potential monetary and non-monetary benefits. METHODS: One hundred and fifty anonymised abnormal radiographs were retrospectively collected and fed through an AI fracture detection solution. The radiographs were re-read by two radiologist reviewers and their consensus was established as the reference standard. Cases were stratified based on the concordance between the AI solution and the reviewers' findings. Discordant cases were further analysed based on the nature of the discrepancy into overcall and undercall subgroups. Statistical analysis was performed to evaluate the accuracy, sensitivity and inter-rater reliability of the AI solution. RESULTS: Ninety-two examinations were included in the final study radiograph set. The AI solution had a sensitivity of 98.9%, an accuracy of 85.9% and an almost perfect agreement with the reference standard. CONCLUSION An AI fracture detection solution has similar sensitivity to human radiologists in the detection of fractures on ED appendicular and pelvic radiographs. Its implementation offers significant potential measurable cost, manpower and time savings.
Humans ; Singapore ; Emergency Service, Hospital ; Fractures, Bone/diagnostic imaging* ; Artificial Intelligence ; Retrospective Studies ; Adult ; Male ; Female ; Cost Savings ; Middle Aged ; Pelvic Bones/diagnostic imaging* ; Reproducibility of Results ; Aged ; Sensitivity and Specificity ; Radiography

BACKGROUND: The importance of identifying osteoporotic vertebral endplate or/and cortex fracture (ECF), which primarily includes endplate fracture (EPF) and vertebral anterior cortex buckling, has been recognized. However, some old traumatic ECFs with healing process in the elderly may be mistaken as osteoporotic. This study analyzes the radiological features of traumatic EPF. METHODS: This was a retrospective analysis of 194 spine trauma patients with 263 vertebral fractures (mean age: 42.11 ± 9.82 years, 118 males and 76 females). All patients had traumatic EPF identified by X-ray/CT/MRI. RESULTS: The involved vertebra was mostly L1 (29.7%), followed by T12 and L2. Except EPFs involved both superior and inferior endplates (12.6%), only 1.9% involved inferior endplate alone, with the majority involved superior endplate. If each endplate was divided into five segments of equal lengths (from anterior to posterior: a1, a2, m, p2, p1), the most depressed point of superior EPFs was mostly at segment-a2 (approximately 45%), followed by segment-a1 (approximately 20%) or segment-m (approximately 20%), and very rarely at segment-p1. The upper 1/3 of anterior vertebral wall was more likely to fracture, followed by middle 1/3 of anterior wall. For posterior vertebral wall fracture, 68.5% broke the bony wall surrounding the basivertebral vain. 58.6%, 30.0%, and 11.4% of vertebral fractures had <1/5, 1/5-1/3, and >1/3 vertebral body height loss. As the extent of vertebral height loss increased, the chance of having both superior and inferior EPFs also increased; however, the chance of having inferior EPF alone did not increase. CONCLUSION Traumatic EPF features are characterized, which may help the differentiation of traumatic and osteoporotic EPFs.
Adult ; Aged ; Female ; Fractures, Bone ; Humans ; Lumbar Vertebrae/diagnostic imaging* ; Male ; Middle Aged ; Osteoporotic Fractures/diagnostic imaging* ; Radiography ; Retrospective Studies ; Spinal Fractures/diagnostic imaging* ; Thoracic Vertebrae

OBJECTIVE: To evaluate the clinical effect of bridge combined internal fixation system in the treatment of periprosthesis fracture of femur after hip replacement. METHODS: From October 2016 to June 2018, 5 patients of periprosthesis fractures of femur classified type B1 and type C in Vancouver were treated by open reduction and bridging combined with internal fixation, including 2 males and 3 females, with ages of 68, 70, 74, 75, 79 years;type B1 fractures in 4 and type C fractures in 1. Causes of injury:1 case of traffic injury, 4 cases of fall. After the operation, the patients were followed up for complications and fracture healing time by clinical and imaging examination, and Parker activity score was performed. RESULTS: The wounds of 5 patients healed without infection. One case of DVT was confirmed by venography. Five patients were followed up, and the durations were 2, 8, 9, 10, 15 months. One patient died of myocardial infarction 2 months after operation. The average healing time was 12.5 weeks. No loss of reduction or failure of internal fixation was found. Two patients could walk without protection and 1 patient needed to rely on single crutch. One case of periprosthetic fracture had to walk with a single crutch before operation and move indoors with two crutches after operation. The average Parker activity score was 51.8% before operation. CONCLUSION The bridge combined internal fixation system can be used to fix the fracture after hip replacement with stable femoral prosthesis.
Aged ; Arthroplasty, Replacement, Hip ; Bone Plates ; Female ; Femoral Fractures ; surgery ; Fracture Fixation, Internal ; Fracture Healing ; Humans ; Male ; Periprosthetic Fractures ; surgery ; Radiography ; Reoperation ; Retrospective Studies ; Treatment Outcome

Adult ; Bone and Bones ; diagnostic imaging ; injuries ; Femoral Fractures ; surgery ; therapy ; Foot Deformities, Acquired ; diagnosis ; etiology ; therapy ; Fracture Fixation, Intramedullary ; adverse effects ; methods ; Fractures, Ununited ; diagnostic imaging ; etiology ; surgery ; Humans ; Intra-Articular Fractures ; diagnostic imaging ; surgery ; Male ; Radiography ; methods ; Reoperation ; methods ; Treatment Outcome

PURPOSE: Isolated greater trochanteric (GT) fractures are often identified using plain radiography of patients with post-traumatic hip pain. In many cases, the fracture extends to form an occult intertrochanteric fracture. We conducted a study to determine the frequency of occult intertrochanteric fractures in patients diagnosed with isolated GT fractures using plain radiographs. MATERIALS AND METHODS: Among 3,017 individuals who visited our emergency department with a trauma-induced pertrochanteric femur fracture between July 2004 and March 2018, 100 patients diagnosed with isolated GT fractures using plain radiographs were retrospectively analyzed. Patients were divided into two groups, those with: i) isolated GT fractures (group A) and ii) occult intertrochanteric fractures (group B). In addition, plain radiographs, magnetic resonance imaging results, and treatment methods were further analyzed in each group. If surgery treatment was needed, it was performed by one surgeon, and in all cases, a 2-hole dynamic hip screw was used. RESULTS: Among the 100 cases of isolated GT fractures diagnosed using plain radiograph, additional examinations revealed that 10 (10.0%) were suffering from isolated GT fractures alone, while the remaining 90 (90.0%) were further diagnosed with occult intertrochanteric fracture. Gender, age, mechanism of injury, and bone mineral density did not correlate with fracture type. CONCLUSION: In our analysis, 90% of injuries initially diagnosed as isolated GT fractures were found to extend into occult intertrochanteric fractures upon further examination with additional imaging modalities. Therefore, additional evaluation should be performed to test for the potential presence of occult intertrochanteric fractures and to establish appropriate treatment plans.
Bone Density ; Emergency Service, Hospital ; Femur ; Fractures, Closed ; Hip ; Hip Fractures ; Humans ; Magnetic Resonance Imaging ; Radiography ; Retrospective Studies

BACKGROUND: This study was conducted to determine the effect of the distributional relationship between dental roots and the mandibular bone on single mandibular bone fractures, which are common craniofacial fractures. METHODS: This was a retrospective, single-center study in Seoul, Korea. Patients with single mandibular fractures in the symphysis, parasymphysis, body, and angle area, with tooth structure involvement were included. The control group included patients with simple, bone-level lacerations without fractures. In total, 94 patients (72 males and 22 females) were included in the treatment group, and 125 (71 males and 54 females) were included in the control group. The height of the mandibular bone and the dental root were measured with panoramic radiography. The central incisor represented the symphysis area, the canine represented the parasymphysis area, the first molar represented the body area, and the second molar represented the angle area. RESULTS: In the treatment group, symphysis fractures occurred in 16 patients (17%), parasymphysis fractures in 36 patients (38%), body fractures in 17 patients (18%), and angle fractures in 25 patients (27%). The ratios of the dental roots to the total height of the mandibular bone in the treatment group were 30.35%, 39.75%, 39.53%, and 36.27% for symphysis, parasymphysis, body, and angle areas, respectively, whereas in the control group, they were 27.73%, 39.70%, 36.76%, and 35.48%. The ratios of the treatment group were significantly higher than those of the control group. CONCLUSION: The results show that the higher ratio of the dental root to the height of the mandibular bone increases the fracture risk.
Fractures, Bone* ; Humans ; Incisor ; Korea ; Lacerations ; Male ; Mandible ; Mandibular Fractures ; Molar ; Radiography, Panoramic ; Retrospective Studies ; Seoul ; Tooth ; Tooth Root

INTRODUCTION: The cross Kirschner wire (K-wire) configuration in closed reduction and percutaneous pinning of paediatric supracondylar humeral fracture affords superior stability. However, medial pin placement presents a risk of iatrogenic ulnar nerve injury. This study describes, in step-by-step detail, another safe method of percutaneous medial pin insertion. METHODS: The technique involved placing the patient's arm in external rotation, with elbow flexed no more than 45° after closed reduction. The surgeon held the K-wire close to its sharp end to pass it percutaneously onto the medial epicondyle, then adjusted his grip toward the blunt end. After fluoroscopy check, the wire driver was engaged and an anteriorly directed force was applied to the distal humerus fragment using the thumb of the surgeon's free hand. The K-wire was inserted at a 45° angle to the longitudinal axis of the humerus shaft. Clinical notes and radiographs of patients who underwent surgery with this technique from 2006 to 2008 were reviewed. RESULTS: A total of 125 patients (84 boys, 41 girls) were included, with a mean age of 7.1 (range 2-14) years. Most injuries were left-sided (72.8%, n = 91, vs. right: 27.2%, n = 34). 72 (57.6%) patients had two-pin cross K-wire configuration, while 53 (42.4%) patients had an additional lateral pin inserted. No patient had postoperative ulnar neuropathy. There were no complications of non-union, malunion or infection. CONCLUSION This safe method of medial pin placement for surgical stabilisation of paediatric supracondylar humeral fractures is easily learnt and reproducible, and produces excellent results.
Adolescent ; Bone Nails ; Child ; Child, Preschool ; Female ; Fluoroscopy ; Fracture Fixation, Intramedullary ; methods ; Humans ; Humeral Fractures ; surgery ; Humerus ; injuries ; Iatrogenic Disease ; Male ; Pediatrics ; Radiography ; Retrospective Studies ; Ulnar Nerve

An 82-year-old woman presented with neck pain and bilateral upper limb paraesthesia after sustaining an unwitnessed fall at home the day before. Physical examination revealed tenderness over the C4-6 region but no evidence of step deformity or neurological deficit. Magnetic resonance imaging of the cervical spine revealed multiple small fractures at the anteroinferior endplate corners of the C3, C5 and C6 vertebrae with focal kyphosis and marrow oedema at these levels, as well as associated disruption of the anterior longitudinal ligament and central spinal canal stenosis. The diagnosis of multiple flexion teardrop fractures was made based on these imaging findings, and the patient subsequently received conservative management. This paper illustrates the radiological features of flexion teardrop fractures and highlights the importance of prompt diagnosis and management of such cases.
Accidental Falls ; Aged, 80 and over ; Cervical Vertebrae ; diagnostic imaging ; Female ; Fracture Fixation, Internal ; methods ; Fractures, Bone ; diagnostic imaging ; Humans ; Neck Pain ; Radiography ; Range of Motion, Articular ; Spinal Fractures ; diagnostic imaging ; Treatment Outcome

Accidents, Traffic ; statistics & numerical data ; Adolescent ; Age Distribution ; Bicycling ; injuries ; Child ; Child, Preschool ; Cohort Studies ; Emergency Service, Hospital ; statistics & numerical data ; Female ; Follow-Up Studies ; Fracture Fixation ; methods ; statistics & numerical data ; Fractures, Bone ; diagnosis ; epidemiology ; surgery ; Humans ; Injury Severity Score ; Male ; Prevalence ; Radiography ; methods ; Registries ; Retrospective Studies ; Risk Assessment ; Sex Distribution ; Singapore ; epidemiology ; Tomography, X-Ray Computed ; methods ; Trauma Centers ; Treatment Outcome ; Wounds and Injuries ; diagnostic imaging ; epidemiology ; therapy

OBJECTIVES: To explore the injury mechanism of ankle fracture inferred by the Lauge-Hansen classification with the application of medical imageology and its application value in forensic medicine. METHODS: A total of 32 ankle fracture cases with known injury mechanism were collected from January 2013 to May 2018, which were identified in Yongkang Public Security Bureau, Zhejiang Province. The Lauge-Hansen classification of ankle fracture was performed by three forensic experts based on the data of X-ray and CT image. Fisher's exact test and Kappa consistency analysis were performed by SPSS 20.0 statistical software to compare the results of the Lauge-Hansen classification with the injury mechanism of ankle fracture obtained through the criminal evidence. RESULTS: In 32 cases, 84.4% （27/32） ankle fractures were classified according to the Lauge-Hansen classification based on medical imaging. The mechanism of ankle fracture identified by the Lauge-Hansen classification was consistent with that obtained through the criminal evidence. CONCLUSIONS Based on medical imaging, the Lauge-Hansen classification can be well applied to infer the injury mechanism of ankle fracture in part cases, and provide objective evidence for the crime scene reconstruction of criminal cases.
Ankle Fractures/diagnostic imaging* ; Ankle Injuries ; Forensic Medicine ; Fractures, Bone ; Humans ; Radiography