Diagnosis Of Fracture Research Articles

Diagnosis and detection of bone fracture in radiographic images using deep learning approaches

IntroductionBones are a fundamental component of human anatomy, enabling movement and support. Bone fractures are prevalent in the human body, and their accurate diagnosis is crucial in medical practice. In response to this challenge, researchers have turned to deep-learning (DL) algorithms. Recent advancements in sophisticated DL methodologies have helped overcome existing issues in fracture detection.MethodsNevertheless, it is essential to develop an automated approach for identifying fractures using the multi-region X-ray dataset from Kaggle, which contains a comprehensive collection of 10,580 radiographic images. This study advocates for the use of DL techniques, including VGG16, ResNet152V2, and DenseNet201, for the detection and diagnosis of bone fractures.ResultsThe experimental findings demonstrate that the proposed approach accurately identifies and classifies various types of fractures. Our system, incorporating DenseNet201 and VGG16, achieved an accuracy rate of 97% during the validation phase. By addressing these challenges, we can further improve DL models for fracture detection. This article tackles the limitations of existing methods for fracture detection and diagnosis and proposes a system that improves accuracy.ConclusionThe findings lay the foundation for future improvements to radiographic systems used in bone fracture diagnosis.

Partial Avulsion Patterns in the Pediatric Humeral Medial Epicondyle.

The anterior oblique bundle of the medial ulnar collateral ligament (UCL) inserts on the anteroinferior aspect of the humeral medial epicondyle, while the flexor pronator mass (FPM) originates superficial and proximal to the UCL. With valgus stress, these distinct footprints may produce injury patterns that affect only focal areas of the medial epicondyle. The proximal UCL can act on the medial epicondyle either in isolation or in conjunction with the FPM to form partial avulsion fracture patterns within the pediatric medial epicondyle, and the predominant pattern involves only the proximal UCL footprint. Case series; Level of evidence, 4. A retrospective review was performed of medial epicondyle injuries from a single tertiary care institution documented from 2012 to 2022. Inclusion criteria consisted of (1) patients <18 years of age with a diagnosis of medial epicondyle fracture, (2) availability of radiographs within 3 weeks of injury date, and (3) no history of acute medial epicondyle fracture. Data collection included demographics, imaging, mechanisms of injury, associated injuries, and procedural details if operative notes were available. Of the 1951 patients screened, 709 were diagnosed with any form of medial epicondyle fracture. Of these patients, 15.9% (n = 113; mean ± SD age, 11.15 ± 2.56 years; 70% male; 40% throwing mechanism) had radiographic evidence of fragmentation of the inferior aspect of the medial epicondyle, suggesting a partial avulsion fracture/injury. Seventy-eight patients (69%) were noted to have a small, well-corticated fragment off the inferior pole of the medial epicondyle on radiographs, defined as a "proximal UCL avulsion fracture." Magnetic resonance imaging in 24 patients in this group confirmed attachment of the UCL to the avulsed fragment. This configuration was also confirmed by 2 operative reports. Thirty-five patients had a well-defined cortical shell or an indistinct radio-opaque body off the inferomedial aspect of the medial epicondyle on radiographs, defined as a "cortical sleeve avulsion." Magnetic resonance imaging in 8 patients in this group demonstrated the UCL in addition to the FPM origin still attached to the avulsed cortical sleeve. This was confirmed by 2 operative reports. The 2 injury patterns seen in this study-proximal UCL avulsion fracture and cortical sleeve avulsion-represented 15.9% of the patients with a medial epicondyle fracture. The proximal UCL avulsion fracture pattern was the more common of the 2 injury patterns. Accurate identification of these injury patterns and their underlying pathology is likely to be important in ultimately understanding the natural history of these injuries and the outcomes of different treatment strategies.

Radiography may not be accurate in assessing acute ankle sprains in children

BackgroundAcute ankle sprains are among the most common injuries in children and are often associated with chondral avulsion fractures and ligament injuries. However, radiography may not be sufficiently accurate for assessing cartilage and ligament injuries in children. The primary purpose of this study was to evaluate the necessity of radiography in the diagnosis of acute ankle sprains in children. The secondary purpose was to assess whether ultrasonography can effectively improve the diagnostic accuracy of acute ankle sprains in children.MethodsWe collected medical data from 78 children with acute ankle sprains who underwent both radiological and ultrasound examinations, 59 of whom also had ankle MRI results. The agreement between the radiographic and ultrasonographic findings in these 78 patients was assessed via Cohen’s kappa and McNemar tests. Using MRI results as the gold standard, the sensitivity, specificity, positive predictive value, and negative predictive value of radiography and ultrasonography were evaluated for the 59 patients who had MRI results. Cohen’s kappa and McNemar’s tests were also utilized to assess the reliability of radiography and ultrasonography in comparison to MRI.ResultsAmong the 78 children with acute ankle sprains, 29 did not show fractures on radiological examination, but fractures were detected via ultrasound examination. Among these 29 fractures, 20 were chondral avulsion fractures of the distal fibula, and 9 were avulsion fractures of the lateral talus process. The agreement between radiography and ultrasonography was fair (Kappa = 0.250), and the difference was statistically significant (P < 0.001). Using MRI as the gold standard, radiography resulted in 17 false-negative cases for lateral ankle fractures, with a sensitivity of only 47%. Ultrasonography produced only one false-negative case, achieving a sensitivity of 97%. Ultrasonography showed substantial agreement with MRI (Kappa = 0.797), whereas radiography showed fair agreement with MRI (Kappa = 0.384).ConclusionsAcute ankle sprains in children frequently result in a high incidence of chondral avulsion fractures. However, radiography may be inadequate for accurately diagnosing these fractures. Reliance on radiography alone may lead to a substantial number of false-negative cases. Compared with radiography, ultrasonography is highly accurate in the diagnosis of chondral avulsion fractures and ligament injuries in children. We believe that ultrasonography, as a noninvasive, radiation-free, and cost-effective dynamic diagnostic method, is particularly suitable for the early diagnosis of acute ankle sprains in children.Level of evidenceLevel III; Diagnostic Study.

Preterm birth and risk of bone fractures during childhood and early adulthood.

People born preterm have reduced bone mineral density, subnormal peak bone mass, and an increased risk of osteoporosis. Whether this translates to increased risk of bone fractures is uncertain. We assessed fracture risk from childhood to early adulthood in relation to gestational age and sex by conducting a nationwide register-linkage cohort study comprising all 223 615 liveborn (1/1987- 9/1990) singletons (9161, 4.1%, preterm) in Finland. Cox regression models provided hazard ratios (HR) for fracture diagnosis in public specialty healthcare in both first and recurrent event settings during the whole follow-up (0-29yr), and during different age periods (0-4/5-9/10-29yr). Gestational age was considered categorical (full-term, 39-41weeks, reference). A total of 39 223 (17.5%) children or young adults had at least one fracture. In analyses not stratified by sex, only extremely preterm birth (<28 completed weeks' gestation) was associated with risk of bone fracture at 0-29yr; adjusted HR (aHR) 0.46 (95% CI 0.28-0.74) compared with those born full-term. Among females, gestational age was unrelated to fracture risk at 0-29yr. Among males, extremely and very preterm (28-31weeks) birth was associated with lower risk of fracture at 0-29yr compared with those born full-term: aHR 0.38 (CI 0.21-0.71) and 0.75 (CI 0.59-0.95) respectively. Restricting the analyses to the individuals without severe medical condition(s) attenuated the associations. However, the fracture risk varied according age and sex: at 10-29yr moderately preterm (32-33wk) females, and extremely- and very preterm males had a lower risk: aHR 0.63 (0.43-0.94), 0.35 (0.17-0.69), and 0.74 (0.57-0.95) respectively, while late preterm birth (34-36wk) was associated to 1.6-fold higher risk among females at 0-5yr, and 1.4-fold risk among males at 5-10yr. Analyses on recurrent fractures showed similar pattern. Children and young adults, in particular males, born extremely or very preterm may have less bone fractures, this is partly explained by severe medical conditions in this group.

Risk factors of avascular femoral head necrosis after a pediatric femoral neck fracture: a 15-year follow up and an adjustment to the Delbet classification.

Pediatric femoral neck fractures (PFNF) are rare but associated with a high rate of serious complications such as avascular femoral head necrosis (AVN). Major risk factors and prognostic tools for an AVN are still unclear. As AVN is a devastating complication, this study aims to evaluate the predictors for AVN following a PFNF. All patients that suffered a PFNF or an AVN following a PFNF in the last 15 years that were treated at a university-level hospital with a minimum of 12 months follow-up were included in this retrospective study. Patients with a pathological fracture or closed epiphysis were excluded. Radiological outcome was evaluated based on Ratcliff criteria. The association of possible risk factors such as age, gender, traumatic mechanism, fracture type, degree of dislocation, time to surgery or type of surgical intervention with AVN was analyzed. Since not all fractures could be assigned to an exact fracture type, a new fracture type was included in the subgroup analyses. We included 37 patients in the study population. The mean age at the time of the diagnosis was 11.5 years (ranging 5-16 years). Mean follow-up was 30 months. 75% of the cases were diagnosed on the day of the trauma. Nine patients had a delayed diagnosis of which eight had a previous neurological disease (eg. cerebral palsy). A previous illness was significantly associated with a late diagnosis (p < 0.001). 17 patients suffered a high velocity trauma. 35 patients were treated operatively, the majority with a closed reduction (81%) and an internal fixation with cannulated screws (75%). In 24 patients (65%) an additional puncture of the hip joint was performed. Ten patients developed AVN, two of them ultimately had to be treated with a total hip arthroplasty. Female gender was associated with AVN, though not significantly (p = 0.051). A Delbet type IV injury and a high velocity trauma were significantly associated with an AVN (p = 0.020, p = 0.030 respectively). A type IIR fracture was significantly more likely to develop AVN compared to a Delbet type II fracture. Age, polytrauma, degree of dislocation, time to diagnosis, time to surgery and type of treatment was found were not significantly associated with AVN. Neurologically impaired patients are prone to a late diagnosis of a femoral neck fracture, mainly due to both cognitive and motor impairments. High velocity trauma is a significant risk factor for developing AVN. In contrast to literature, a Delbet type IV fracture was significantly associated with AVN. A type IIR fracture has a higher possibility to develop AVN than a normal Delbet type II fracture. As the incidence of pediatric femoral neck fractures is low, the size of a study population is limited. Nevertheless, AVN is still a life altering complication leading to additional surgical treatments, hospital stays and impairment of daily life activities. Therefore, further research is needed to better understand the mechanisms of underlying risk factors and to develop strategies for the prevention and management of AVN in the pediatric population. Hence multicenter studies with a bigger study population are crucial.

Automatic Vertical Root Fracture Detection on Intraoral Periapical Radiographs With Artificial Intelligence-Based Image Enhancement.

To explore transfer learning (TL) techniques for enhancing vertical root fracture (VRF) diagnosis accuracy and to assess the impact of artificial intelligence (AI) on image enhancement for VRF detection on both extracted teeth images and intraoral images taken from patients. A dataset of 378 intraoral periapical radiographs comprising 195 teeth with fractures and 183 teeth without fractures serving as controls was included. DenseNet, ConvNext, Inception121, and MobileNetV2 were employed with model fusion. Prior to evaluation, Particle Swarm Optimization (PSO) and Deep Learning (DL) image enhancement were applied. Performance assessment included accuracy rate, precision, recall, F1-score, AUC, and kappa values. Intra- and inter-observer agreement, according to the Gold Standard (GS), were assessed using ICC and t-tests. Statistical significance was set at p < 0.05. The DenseNet + Inception fusion model achieved the highest accuracy rate of 0.80, with commendable recall, F1-score, and AUC values, supported by precision (0.81) and kappa (0.60) values. Molar tooth examination yielded an accuracy rate, precision, recall, and F1-score of 0.80, with an AUC of 0.84 and kappa of 0.60. For premolar teeth, the fusion network showed an accuracy rate of 0.78, an AUC of 0.78, and notable metrics, including F1-score (0.80), recall (0.85), precision (0.71), and kappa (0.55). ICC results demonstrated acceptable agreement (≥ 0.57 for molars, ≥ 0.52 for premolars). TL methods have demonstrated significant potential in enhancing diagnostic accuracy for VRFs in radiographic imaging. TL is emerging as a valuable tool in the development of robust, automated diagnostic systems for VRF identification, ultimately supporting clinicians in delivering more accurate diagnoses.

Scaphoid Fat Stripe Sign: Is It a Reliable Radiological Sign of Scaphoid Fracture in Children?

The scaphoid fat pad stripe (SFS) is a radiological sign first described in 1975 as a line of relative lucency lying parallel to the lateral border of the scaphoid, with slight convexity toward it, and it is optimally demonstrated on postero-anterior and oblique views with ulnar deviation of the carpus. The obliteration or displacement of this line is commonly present in acute fractures of the scaphoid, radial styloid process, and proximal first metacarpus. The aim of this observational study is to investigate the supportive value of the fat stripe sign (SFS) in the diagnosis of scaphoid fractures in the pediatric population. This is a monocentric, retrospective study of all patients referred to the Pediatric Traumatology Unit of a tertiary hospital from the Emergency Department with clinical suspicion of scaphoid fracture without visible fracture in the initial X-ray. Radiological reports for CT and MRIs were recorded, and the initial X-rays were blindly reviewed by a pediatric orthopedic fellowship-accredited surgeon for the presence of an abnormal scaphoid fat pad stripe sign and the presence of a fracture line in the initial X-rays. The results of the blind interpretation of the initial X-rays for the fat stripe sign showed 86% sensitivity and 58% specificity, with the negative predictive value reaching 92%. The scaphoid fat stripe sign can be used as an adjacent in the diagnosis of an occult scaphoid fracture in children or adolescents. Its high negative predictive value, if confirmed in larger studies, can be an element used to exclude scaphoid fracture and consequently avoid unnecessary immobilizations and health costs.

Automated diagnosis and classification of metacarpal and phalangeal fractures using a convolutional neural network: a retrospective data analysis study.

Hand fractures are commonly presented in emergency departments, yet diagnostic errors persist, leading to potential complications. The use of artificial intelligence (AI) in fracture detection has shown promise, but research focusing on hand metacarpal and phalangeal fractures remains limited. We aimed to train and evaluate a convolutional neural network (CNN) model to diagnose metacarpal and phalangeal fractures using plain radiographs according to the AO/OTA classification system and custom classifiers. A retrospective analysis of 7,515 examinations comprising 27,965 images was conducted, with datasets divided into training, validation, and test datasets. A CNN architecture was based on ResNet and implemented using PyTorch, with the integration of data augmentation techniques. The CNN model achieved a mean weighted AUC of 0.84 for hand fractures, with 86% sensitivity and 76% specificity. The model performed best in diagnosing transverse metacarpal fractures, AUC = 0.91, 100% sensitivity, 87% specificity, and tuft phalangeal fractures, AUC = 0.97, 100% sensitivity, 96% specificity. Performance was lower for complex patterns like oblique phalangeal fractures, AUC = 0.76. Our study demonstrated that a CNN model can effectively diagnose and classify metacarpal and phalangeal fractures using plain radiographs, achieving a mean weighted AUC of 0.84. 7 categories were deemed as acceptable, 9 categories as excellent, and 3 categories as outstanding. Our findings indicate that a CNN model may be used in the classification of hand fractures.

Erroneous Classification and Coding as a Limitation for Big Data Analyses: Causes and Impacts Illustrated by the Diagnosis of Clavicle Injuries.

Background/Objectives: Clavicle injuries are common and seem to be frequently subject to diagnostic misclassification. The accurate identification of clavicle fractures is essential, particularly for registry and Big Data analyses. This study aims to assess the frequency of diagnostic errors in clavicle injury classifications. Methods: This retrospective study analyzed patient data from two Level 1 trauma centers, covering the period from 2008 to 2019. Included were cases with ICD-coded diagnoses of medial, midshaft, and lateral clavicle fractures, as well as sternoclavicular and acromioclavicular joint dislocations. Radiological images were re-evaluated, and discharge summaries, radiological reports, and billing codes were examined for diagnostic accuracy. Results: A total of 1503 patients were included, accounting for 1855 initial injury diagnoses. In contrast, 1846 were detected upon review. Initially, 14.4% of cases were coded as medial clavicle fractures, whereas only 5.2% were confirmed. The misclassification rate was 82.8% for initial medial fractures (p < 0.001), 42.5% for midshaft fractures (p < 0.001), and 34.2% for lateral fractures (p < 0.001). Billing codes and discharge summaries were the most error-prone categories, with error rates of 64% and 36% of all misclassified cases, respectively. Over three-quarters of the cases with discharge summary errors also exhibited errors in other categories, while billing errors co-occurred with other category errors in just over half of the cases (p < 0.001). The likelihood of radiological diagnostic error increased with the number of imaging modalities used, from 19.7% with a single modality to 30.5% with two and 40.7% with three. Conclusions: Our findings indicate that diagnostic misclassification of clavicle fractures is common, particularly between medial and midshaft fractures, often resulting from errors in multiple categories. Further prospective studies are needed, as accurate classification is foundational for the reliable application of Big Data and AI-based analyses in clinical research.

Management of a Right Tibial Proximal Third Open Comminuted Fracture: Surgical Disarticulation of Right Stifle Joint in a 1-Year-Old Hen Pigeon (Columba livia domestica)

Traumatic pelvic limb fractures in pet birds are rare and primarily result from trauma. Avian bones are fragile and prone to fragmentation due to various natural and anthropogenic events. This case report describes the diagnosis, anesthesia protocol, surgical management, post-operative care, and remarkable outcome of a right tibial comminuted fracture in a one-year-old hen pigeon (Columba livia domestica). A one-year-old hen pigeon was presented to the Veterinary Teaching Hospital, University of Jos, Nigeria, with a broken right pelvic limb after being attacked by a young lad. The attack occurred 30 minutes prior to presentation. Clinical examination revealed extensive tissue damage including an open wound with a complete fracture and bone fragment at the proximal third of the right tibia, accompanied by hemorrhages, tenderness, pale ocular mucous membranes, and lethargy. The impact of the attack was the primary cause of the comminuted fracture. Due to logistical constraints and the patient's critical condition, pre-operative radiographic imaging was not feasible. A definitive diagnosis of right tibial proximal third open comminuted fracture was readily made based on the gross tissue damage. Following standard aseptic protocol, stifle disarticulation was performed under local anesthesia to alleviate the bird's excruciating pain. Local anesthesia was achieved with 10mg lidocaine hydrochloride via local infiltration at the stifle. Due to the bird's critical condition, local anesthesia was preferred over general anesthesia. A 5mm stab skin incision was made distal to the right stifle, followed by blunt dissection of the musculature and disarticulation at the tibiofemoral joint. 5mm musculature distal to the stifle was transected and the skin was routinely sutured with size 3/0 silk suture. Post-operative care included injectable amoxicillin, piroxicam, and iron dextran administration, along with alternative-day wound dressing. Skin sutures were removed eight days post-surgery. The pigeon made a remarkable recovery, regaining balance and flying comfortably. Post-recovery imaging was not feasible as all arrangements made with the client following the bird's recovery ultimately fell through. To our knowledge, this case represents the first reported instance of a comminuted tibial fracture in a pigeon managed with stifle disarticulation. The successful outcome of this case proves stifle disarticulation to be an effective treatment option for complex fractures in birds, underscoring the importance of innovative strategies, prompt surgical intervention and addressing a significant gap in the literature. At the time of this report, the pet bird is currently nesting and brooding its eggs. Keywords: Hen pigeon, Comminuted tibial fracture, Proximal third, Stifle disarticulation.

Comparative characteristics of radiological examination and magnetic resonance imaging in the diagnosis of limb fractures in horses

Comparative characteristics of radiological examination and magnetic resonance imaging in the diagnosis of limb fractures in horses

Le Fort I-II Fracture Management: Case Based Literature Review

Introduction: Midfacial fractures are among the most severe injuries encountered in emergency settings due to the risk of functional impairment and facial deformities. The Le Fort classification remains the most commonly used system for categorizing these fractures. Treating Le Fort II fractures is particularly complex due to the involvement of the orbital and nasal bones, along with the critical need to restore proper occlusion. Achieving pre-trauma occlusion is often the most difficult aspect of treating facial fractures. Case Presentation: This study reported a 28-year-old Asian male was brought to the Emergency Room of Bali Mandara General Hospital by a bystander following a motorcycle accident in which he struck a pedestrian. He was diagnosed with Le Fort I-II and a right orbital floor fracture. The patient underwent surgery, including open reduction and internal fixation using miniplates and screws. The procedure successfully restored the patient’s occlusion, and no reported postoperative complications. Discussion: The diagnosis of Le Fort fractures is based on patient history, physical examination, and imaging studies. Identifying a pterygoid fracture is essential for diagnosing all types of Le Fort fractures. Prompt definitive treatment is critical to prevent long-term facial deformities. Conclusion: Achieving proper occlusion is a marker of accurate alignment in managing facial fractures. Emphasizing functional restoration and deformity prevention significantly improves patient recovery and results.

Evaluating the effectiveness of cone-beam computed tomography reverse contrast images in the diagnosis of vertical root fractures: An in vitro pilot study

Abstract Introduction: The aim of this study is to investigate the effectiveness of cone-beam computed tomography (CBCT) reverse contrast images in the diagnosis of vertical root fractures (VRFs). Materials and Methods: In this study, 20 single-canal premolar teeth without cracks and internal resorption were selected and after root canal treatment, divided into two: experimental and control groups. In each of the teeth in the experimental group, an artificial fracture was created with the SANTAM device, then the teeth of both groups were randomly placed in the dental sockets of a dry mandible, and after preparing CBCT images of the teeth, the images were processed by reverse contrast software. Initial and reverse contrast images were examined by two radiologists and two endodontists. The data were analyzed by SPSS software version 22. Results: Observers reported higher sensitivity and positive and negative predictive value in normal contrast images than in reverse contrast images, but the specificity reported by endodontists in reverse contrast images was slightly higher than in normal contrast images. In comparing the results of radiologists and endodontists, there was a significant agreement in the review of the initial images (κ =0/59), but there was no significant agreement in the images with reverse contrast (κ = −0/1). There was not any notable distinction observed in the assessment of normal and reverse contrast images among the observers, nor in the comparison between radiologists and endodontists, except for the examination of normal contrast images by the two groups of radiologists and endodontists (P = 0.00). From this, it can be inferred that the diagnostic power of reverse contrast images in identifying VRFs is inferior to that of normal contrast images (P &gt; 0.05). Conclusion: According to the obtained results, it was concluded that reverse contrast CBCT images are not effective in diagnosing VRFs and cause error in diagnosis.

Incidence and Outcomes of Vertebral Compression Fracture Among Patients Infected with COVID-19.

Background/Objectives: Early studies have suggested that the SARS-CoV-2 virus has a deleterious effect on bone mineral density and may increase the risk of pathological fractures. This study characterized vertebral compression fractures in patients with and without a prior diagnosis of COVID-19. Methods: Using a nationwide claims database, this retrospective study used ICD-10 billing codes to identify patients with a diagnosis of vertebral compression fracture from January 2020 to April 2022. Two cohorts were created based on whether the patients had a concurrent diagnosis of COVID-19. Patient demographics, comorbidities, and outcome measures were characterized by descriptive analysis. Results: In total, 413,425 patients met the inclusion criteria. Among them, a total of 23,148 patients (5.60%) had a diagnosis of COVID-19 at the time of their compression fracture. Among the COVID-19 patients, the incidences of vertebral compression fracture were 0.42% in 2020 and 0.33% in 2021, in comparison to the historical average yearly incidence of 0.17% across all patients. The patients with COVID-19 at the time of compression fracture diagnosis had a higher rate of vitamin D deficiency (OR: 1.25) and a lower rate of routine healing (OR: 0.61). The patients without COVID-19 were more likely to be osteoporotic (OR: 0.88), experience additional compression fractures (OR: 0.38), and have kyphoplasty or vertebroplasty (OR: 0.73). Conclusions: Despite lower rates of osteoporosis, patients with a concomitant COVID-19 diagnosis exhibited a higher incidence of compression fractures. Although more research is needed, these results support increasing bone health surveillance in patients with a history of COVID-19 infection.

How Is Preoperative Opioid Use Associated With Readmissions and Outcomes in Lower Extremity Trauma?

Opioid use disorder (OUD) has been implicated as a potential risk factor for adverse outcomes and readmissions in various surgical procedures. Patients admitted with an open fracture of the lower extremity often have multifarious pain needs, require surgical procedures, and have prolonged rehabilitation; previous OUD complicates this process. Our goal was to describe at a national level how OUD is associated with readmission, complications, and healthcare expenditure for patients admitted with open lower extremity fractures. (1) Do patients with OUD who were treated for open lower extremity fractures have higher odds of readmission compared with patients without OUD? (2) Do patients with OUD who were treated for open lower extremity fractures have higher healthcare utilization (specifically, length of stay and hospitalization charges and costs)? This was a retrospective, comparative study using the Nationwide Readmissions Database, which is the largest nationally representative readmissions database in the United States. Patients were included if they had an ICD-10-CM principal diagnosis of open lower extremity fracture. Between January 1, 2019, and September 30, 2019, a total of 17,811 patients were admitted for open lower extremity fractures and entered in the National Readmissions Database. Of the 17,811 patients, 2.3% (410) had a secondary diagnosis of OUD and 97.7% (17,401) did not. The mean age was 46 years for both groups. The most common operative procedure was debridement, and 1.5% of patients received a flap for reconstruction. Opioid disorders were identified using ICD-10-CM codes. Ninety-day complications and readmissions were characterized for the calendar year. Patients undergoing flap-based reconstructions were identified with ICD-10-PR codes. Confounders (patient demographic and hospital characteristics) were adjusted for using multivariable regression analysis models. After controlling for potentially confounding variables such as primary payer, Charlson comorbidity index, Gustillo type, and bone density, we found that patients with OUD had greater odds of readmission after open lower extremity fractures (adjusted OR 1.45 [95% confidence interval (CI) 1.0 to 2.0]; p = 0.03). The 90-day infection occurrence was higher in patients with OUD (adjusted OR 1.96 [95% CI 1.0 to 3.8]; p = 0.049) and was the primary reason for readmission in both groups. Moreover, 11% (11 of 103) of patients with OUD were readmitted with opioid-induced complications, which was exclusively observed in this cohort. Patients with OUD also had longer hospital stays (adjusted mean difference 2.2 days [95% CI 0.5 to 3.8]; p = 0.01) and higher hospitalization charges (adjusted mean difference in USD 34,000 [95% CI 1000 to 66,000]; p = 0.04) and costs (adjusted mean difference in USD 7000 [95% CI 2000 to 13,000]; p = 0.007) than those without OUD. These findings suggest that mitigating infection and opioid overdose, addiction, and constipation in patients with OUD could reduce readmissions in lower extremity fracture patients. Future research should focus on antibiotic and wound care compliance and the early and frequent engagement of postoperative opioid addiction support services. Level III, therapeutic study.

Artificial intelligence in risk prediction and diagnosis of vertebral fractures

With the increasing prevalence of vertebral fractures, accurate diagnosis and prognostication are essential. This study assesses the effectiveness of AI in diagnosing and predicting vertebral fractures through a systematic review and meta-analysis. A comprehensive search across major databases selected studies utilizing AI for vertebral fracture diagnosis or prognosis. Out of 14,161 studies initially identified, 79 were included, with 40 undergoing meta-analysis. Diagnostic models were stratified by pathology: non-pathological vertebral fractures, osteoporotic vertebral fractures, and vertebral compression fractures. The primary outcome measure was AUROC. AI showed high accuracy in diagnosing and predicting vertebral fractures: predictive AUROC = 0.82, osteoporotic vertebral fracture diagnosis AUROC = 0.92, non-pathological vertebral fracture diagnosis AUROC = 0.85, and vertebral compression fracture diagnosis AUROC = 0.87, all significant (p < 0.001). Traditional models had the highest median AUROC (0.90) for fracture prediction, while deep learning models excelled in diagnosing all fracture types. High heterogeneity (I² > 99%, p < 0.001) indicated significant variation in model design and performance. AI technologies show considerable promise in improving the diagnosis and prognostication of vertebral fractures, with high accuracy. However, observed heterogeneity and study biases necessitate further research. Future efforts should focus on standardizing AI models and validating them across diverse datasets to ensure clinical utility.

Epidemiology of talus fractures in Finland: a nationwide register study from 1997 to 2020

BackgroundThe aim of this study was to estimate the nationwide incidence of talus fractures (per 100 000 person-years) and to determine the incidence of operative treatment in the Finnish population.MethodsBased on Finnish Care Register for Health Care data, all patients 18 years and older admitted to hospital with talar fractures between 1997 and 2020 were included.ResultsDuring the 24-year study period, 5247 patients with primary or secondary diagnoses of talar fracture were identified. The mean incidence during the whole study period was 50.4 per 100 000 person-years. There was a clear increase starting from the year 2009 (61.4 per 100 000 person-years), that continued and the incidence in 2018 raised up to 106.8 person-years. The total incidence of operations performed on talar fractures remained almost the same during the study period (9.1 per 100 000 person-years from 1997 to 2020).ConclusionsWhile the incidence of performed operations had remained stable, the incidence of talar fractures in Finland has increased during the last decades. The increase was more prominent in men. The observed change is possibly due to the progress and availability of computer tomography.Level of EvidenceIII

Diagnostic performance of neural network algorithms in skull fracture detection on CTscans: a systematic review and meta-analysis.

The potential intricacy of skull fractures as well as the complexity of underlying anatomy poses diagnostic hurdles for radiologists evaluating computed tomography (CT) scans. The necessity for automated diagnostic tools has been brought to light by the shortage of radiologists and the growing demand for rapid and accurate fracture diagnosis. Convolutional Neural Networks (CNNs) are a potential new class of medical imaging technologies that use deep learning (DL) to improve diagnosis accuracy. The objective of this systematic review and meta-analysis is to assess how well CNN models diagnose skull fractures on CT images. PubMed, Scopus, and Web of Science were searched for studies publishedbefore February 2024 that used CNN models to detect skull fractures on CT scans. Meta-analyses were conducted for area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Egger's and Begg's tests were used to assess publication bias. Meta-analysis was performed for 11 studies with 20,798 patients. Pooled average AUC for implementing pre-training for transfer learning in CNN models within their training model's architecture was 0.96 ± 0.02. The pooled averages of the studies' sensitivity and specificity were 1.0 and 0.93, respectively. The accuracy was obtained 0.92 ± 0.04. Studies showed heterogeneity, which was explained by differences in model topologies, training models, and validation techniques. There was no significant publication bias detected. CNN models perform well in identifying skull fractures on CT scans. Although there is considerable heterogeneity and possibly publication bias, the results suggest that CNNs have the potential to improve diagnostic accuracy in the imaging of acute skull trauma. To further enhance these models' practical applicability, future studies could concentrate on the utility of DL models in prospective clinical trials.

Computed tomography versus radiography for the detection of rib and skull fractures in paediatric suspected physical abuse: a systematic review.

The diagnosis of suspected physical abuse (SPA) remains a continuous challenge to paediatric healthcare. Several studies have reported that computed tomography (CT) improves the evaluation of SPA. This study aims to systematically review the diagnostic performance of CT compared to radiography in investigating skull and chest fractures for SPA. Multiple databases were searched, using PRISMA methods, from 2008 to August 2024 for relevant studies in English. Two reviewers independently screened and selected relevant studies using Covidence software. The QUADAS-2 tool was used for the quality assessment of the included papers. Sensitivity, specificity and the effective radiation dose of CT and radiography from the included studies were extracted. Pooled sensitivity and specificity were calculated with their respective 95% confidence intervals (CI). GRADE criteria were used to appraise the overall quality of the synthesis. Of the 4057 identified papers, 10 met the inclusion criteria; all 10 included skull and/or chest. The overall sensitivity and specificity of CT were 96.5% (95% CI, 94.9-97.7%) and 99.5% (95% CI, 99.1-99.8%), respectively. Compared to the sensitivity and specificity of radiography, 59.8% (95% CI, 56.2-63.3%) and 99.7% (95% CI, 99.3-99.8%), respectively. Conclusion: CT sensitivity is significantly higher than radiography in detecting rib and skull fractures for SPA. The effective dose for chest LDCT is comparable to that of radiography. Therefore, LDCT should be considered a potential replacement to radiography in SPA investigations for the chest and skull. What is Known • CT shows higher diagnostic performance than radiography in detecting skull and rib fractures in the diagnosis of SPA. What is New • When a head CT scan is acquired for SPA diagnosis at any age, the two-view skull radiograph can be safely eliminated from the Skeletal Survey protocol, likewise, Chest CT can replace chest radiography for SPA diagnosis of rib fractures. • The effective dose and image quality of low-dose chest CT is comparable to that of two-view chest radiography for SPA diagnosis.

Experience with artificial intelligence algorithms for the diagnosis of vertebral compression fractures based on computed tomography: from testing to practical evaluation

BACKGROUND: Osteoporosis is often diagnosed at the stage with complications, i.e., low-energy fractures. Vertebral compression fractures, which are complications of osteoporosis and predictors of subsequent fractures, are often asymptomatic. Compression fractures can be found by computed tomography performed for other indications with vertebral morphometry. Approaches to using artificial intelligence algorithms designed for diagnosing vertebral compression fractures were analyzed. AIM: Testing artificial intelligence algorithms to conduct morphometric analysis of vertebrae on chest computed tomography scans and assess the possibility of their implementation in medical organizations of the Moscow Healthcare Department. MATERIALS AND METHODS: To set a clinical task for artificial intelligence algorithms, basic diagnostic requirements in the area of “vertebral compression fractures (osteoporosis)” were formulated. The testing of the artificial intelligence algorithms included the following stages: self-testing, functional and calibration testing, practical evaluation, and operation testing. The first three stages of testing were performed using previously generated datasets. At practical evaluation and operation testing, artificial intelligence algorithms analyzed the data from computed tomography performed in medical organizations. The expert group of radiologists assessed the diagnostic accuracy and functional capacity of the AI algorithms at all stages. The resulting quantitative metrics of the accuracy of artificial intelligence algorithms were compared with the required target values. RESULTS: From June 2021 to June 2022, two artificial intelligence algorithms (Nos. 1 and 2) with different methods of detecting compression fractures were tested. Both artificial intelligence algorithms successfully passed the self-testing (6 tests), functional (5 tests), and calibration (100 tests) stages. The area under the ROC curve for artificial intelligence algorithm No. 1 was 0.99 (95% CI, 0.98–1), and for artificial intelligence algorithm No. 2, it was 0.91 (95% CI, 0.85–0.96). Artificial intelligence algorithm No. 1 passed the practical evaluation stage without any significant remarks, whereas algorithm No. 2 was sent for fine-tuning. After the operation testing stage, the following accuracy metrics were obtained: the areas under the ROC curve for artificial intelligence algorithm Nos. 1 and 2 were 0.93 (95% CI, 0.89–0.96) and 0.92 (95% CI, 0.90–0.94), respectively. At all stages, both artificial intelligence algorithms demonstrated sufficient metrics for clinical validation. CONCLUSION: Artificial intelligence algorithms for the automatic diagnosis of vertebral compression fractures have been tested, demonstrating the high quality of their operation. artificial intelligence algorithms can be applied as a supplementary tool in the medical decision support system.