Classification Of Ankle Fractures Research Articles

External validation of an artificial intelligence multi-label deep learning model capable of ankle fracture classification

BackgroundAdvances in medical imaging have made it possible to classify ankle fractures using Artificial Intelligence (AI). Recent studies have demonstrated good internal validity for machine learning algorithms using the AO/OTA 2018 classification. This study aimed to externally validate one such model for ankle fracture classification and ways to improve external validity.MethodsIn this retrospective observation study, we trained a deep-learning neural network (7,500 ankle studies) to classify traumatic malleolar fractures according to the AO/OTA classification. Our internal validation dataset (IVD) contained 409 studies collected from Danderyd Hospital in Stockholm, Sweden, between 2002 and 2016. The external validation dataset (EVD) contained 399 studies collected from Flinders Medical Centre, Adelaide, Australia, between 2016 and 2020. Our primary outcome measures were the area under the receiver operating characteristic (AUC) and the area under the precision-recall curve (AUPR) for fracture classification of AO/OTA malleolar (44) fractures. Secondary outcomes were performance on other fractures visible on ankle radiographs and inter-observer reliability of reviewers.ResultsCompared to the weighted mean AUC (wAUC) 0.86 (95%CI 0.82–0.89) for fracture detection in the EVD, the network attained wAUC 0.95 (95%CI 0.94–0.97) for the IVD. The area under the precision-recall curve (AUPR) was 0.93 vs. 0.96. The wAUC for individual outcomes (type 44A-C, group 44A1-C3, and subgroup 44A1.1-C3.3) was 0.82 for the EVD and 0.93 for the IVD. The weighted mean AUPR (wAUPR) was 0.59 vs 0.63. Throughout, the performance was superior to that of a random classifier for the EVD.ConclusionAlthough the two datasets had considerable differences, the model transferred well to the EVD and the alternative clinical scenario it represents. The direct clinical implications of this study are that algorithms developed elsewhere need local validation and that discrepancies can be rectified using targeted training. In a wider sense, we believe this opens up possibilities for building advanced treatment recommendations based on exact fracture types that are more objective than current clinical decisions, often influenced by who is present during rounds.

Ankle fractures in the athlete: epidemiology, anatomy and management considerations

Ankle fractures are a common injury in both sporting professionals and amateurs, with football and rugby contributing most to these injuries in the UK population. Mechanism of injury varies but commonly involves excess rotational forces around a fixed plantigrade foot. Classification of ankle fractures is discussed along with a description of the anatomy involved. Management of these injuries can be operative or non-operative and is judged based on the stability and displacement of the ankle mortise. Debate persists around optimal methods of fixation, particularly with regards to syndesmotic injury and deltoid ligament repair and the various options are outlined. A return to sport is possible and, in fact, expected in most of these fractures sustained in a sportsperson and, hence, a focus on early mobility and weight-bearing is encouraged in this population. Here we discuss these considerations in the context of athletes.

Patterns of Anterior Inferior Tibiofibular Ligament Avulsion Fracture Accompanied by Ankle Fracture

Category: Ankle; Trauma Introduction/Purpose: The anterior inferior tibiofibular ligament (AITFL) avulsion fracture accompanying an ankle fracture cause compromising ankle stability, and requires accurate evaluation and clarifies pathophysiology. The aim of this study was to investigate the correlation between AITFL avulsion fracture and Lauge–Hansen, Wagstaffe classification. Methods: 128 patients (70 males and 58 females) operated at the present institution between January 2013 and July 2017 were included. AITFL avulsion fractures occurred in 68 patients. Fracture was diagnosed based on the preoperative simple radiographs obtained of the ankle joint in the anteroposterior, lateral and mortise views. In cases wherein diagnosis was difficult using radiographs alone, CT was additionally used. AITFL avulsion fractures were classified based on the fracture site according to the Wagstaffe classification system. The anteroposterior and horizontal lengths as well as the height of the avulsed bone fragment were measured using CT scans in the coronal, sagittal and axial views. Thereafter, the relationship between the Lauge-Hansen classification of ankle fractures and the characteristics of AITFL fracture was statistically analysed using the Fisher exact test. Results: Type II of the modified Wagstaffe classification system was 39 examples, followed by type III (9 examples) and type IV (8 examples). Out of 7 pronation-abduction fractures, 3 were those of AITFL avulsion fracture, while out of the 21 pronation- external rotation fracture examples, 9 were those of AITFL avulsion fracture. Out of the 95 examples of supination-external rotation fracture, there were 56 examples (59%) of AITFL avulsion fracture. Of the pronation fractures, 0% was a fibular avulsion fracture and 43% were a tibial avulsion fracture. Of the supination fractures, 44% were a fibular avulsion fracture and 16% were a tibial avulsion fracture. The difference in the ratio of fibular and tibial avulsion fractures between the pronation and supination fractures was significant. (p < 0.0001) Conclusion: Some of the AITFL avulsion fractures examined in this study may have been caused by collisions with the talus rather than the traction of the AITFL. Although Wagstaffe fractures accompanied by a supination–external rotation-type fracture results from the traction of the AITFL, a tibial avulsion fracture in a patient with a modified Wagstaffe type 4 fracture and a supination fracture appears to result from a continuous external rotation and repeated collisions of the talus with the anterolateral corner of the distal tibia.

Beyond the Malleoli: Part 1—Avulsion Fractures of the Tibia and Fibula

Avulsion fractures of the ankle and hindfoot are a diverse group of injuries occurring at level of retinacular, capsuloligamentous, and tendinous attachments. Even small fracture fragments have the potential to cause serious complications (such as ankle instability and accelerated osteoarthritis in the context of avulsion fractures of the surrounding capsuloligamentous supporting structures), if not treated appropriately. This article describes the relevant anatomy, injury mechanisms, classification, nomenclature, imaging, treatment, and complications of ankle and hindfoot avulsion fractures, with the exception of fractures occurring at and in the vicinity of the medial and lateral malleolar tips. In this part 1 of a two-part series, we provide a review of ankle retinacular and distal tibiofibular syndesmotic avulsion fractures.

Intra- and inter-observer reliability of Dias-Tachdjian classification in pediatric ankle fractures: do clinical experience and expertise matter?

The Dias-Tachdjian classification is the most commonly used system for the classification of pediatric ankle fractures, but its inter- and intra-observer reliability has not been studied in detail. Also, the impact of the clinician's experience and expertise on the reliability of this system is unknown. This study aimed: (1) to determine the intra- and inter-observer reliability of the Dias-Tachdjian classification and (2) to investigate the effect of the clinician's experience and expertise on the reliability of this system. Anteroposterior and lateral ankle radiographs of 56 children (34 male, 22 female) with ankle fractures, aged between 3 and 14 years, with open growth cartilages, were retrospectively identified and included in the study. Each patient radiograph was examined by 10 observers from two different specialties with different levels of clinical experience (two orthopedic surgeons with interest in pediatric orthopedics, three orthopedic surgeons with no interest in pediatric orthopedics, three orthopedic residents, and two radiology specialists) from two different specialties (orthopedics and radiology). All observers were then asked to classify pediatric ankle fractures at 6-week intervals per the Dias-Tachdjian classification system. Overall, intra-observer reliability as substantial to very good (κ = 0.77-0.95, P < 0.01), but inter-observer reliability as fair for both assessments (κ = 0.21, P < 0.01 and κ = 0.20, P < 0.01 for the first and second occasions, respectively). Inter-observer reliability among pediatric orthopedic surgeons as very good (κ = 0.90, 95% CI = 0.86-0.94, P < 0.01 and κ = 0.82, 95% CI = 0.71-0.93, P < 0.01 for the first and second occasions, respectively). Orthopedic surgeons with no special interest in pediatric orthopedics demonstrated substantial agreement in the first occasion (κ = 0.63, 95% CI = 0.53-0.72, P < 0.01) but moderate in the second one. Orthopedic residents exhibited moderate levels of agreement in each assessment period (κ = 0.58, 95% CI = 0.47-0.68, P < 0.01 and κ = 0.44, 95% CI = 0.37-0.51, P < 0.01 for the first and second occasion, respectively). Considering that the specialists dealing with pediatric orthopedics show very good consistency for Dias-Tachdjian classification, both within and between observers, consistency in the identification of the ankle fracture models increases as the interest in the field of pediatric orthopedics intensifies.

FRACTURES OF THE BONES IN THE ANKLE JOINT

Introduction: Ankle fractures are usually frequent in emergency departments worldwide, with an incidence of 187/100,000 inhabitants per year. Especially the type B fracture according to Webers classification, which may lead to long-term osteoarthritis in approximately 14%. It is essential to recognize that stability in the ankle joint is the fundamental pillar in the correct treatment strategies in ankle trauma. Objective: to describe current information related to ankle bone fractures, etiology, anatomy, epidemiology, mechanism of action, presentation, classification, evaluation, prognosis, treatment and complications of ankle fractures. Methodology: a total of 38 articles were analyzed in this review, including review and original articles, as well as clinical cases, of which 26 bibliographies were used because the other articles were not relevant to this study. The sources of information were PubMed, Google Scholar and Cochrane; the terms used to search for information in Spanish, Portuguese and English were: ankle fracture, fractura do tornozelo, ankle, tibia, fibula, ankle fracture. Results: Bimalleolar ankle fractures occur in a quarter of the patients and trimalleolar fractures in the remaining 5% to 10%. The incidence of ankle fractures is close to 187 per 100,000 inhabitants per year. Open fractures are infrequent, representing only 2 % of all fractures of the ankle joint. In children, these injuries are also frequent, occupying the second place after hand and wrist injuries, especially in those between 10 and 15 years of age. Likewise, pediatric ankle fractures occur in a 2:1 male to female ratio, representing 5% of all fractures in children and approximately 9% to 18% of all fissure injuries. Conclusions: the ankle joint is complex, in gynglimus, formed by the fibula, the tibia and the talus and also deeply related to the ligamentous complexes. The bony anatomy that provides stability is formed by the distal part of the tibia and fibula, its articulation with the talus and with each other. Generally ankle fractures are caused by different trauma mechanisms such as impact, twisting and crushing injuries. Ankle injury depends on several factors such as mechanism, chronicity, bone quality, patients age, magnitude, direction, impact velocity and foot position. A complete and comprehensive medical history is essential in the medical evaluation. X-rays are the first-line adjunctive tests that aid in the evaluation of an injury that impacts the ankle. The classification system is important for the treatment decision. The treatment of fractures of the ankle bones can be performed conservatively or surgically, depending on certain criteria, and immobilization should be performed afterwards to reduce the risk of complications. It is essential to follow the ATLS scheme in order to define and manage any alteration that may be life-threatening for the patient. Ankle fracture-dislocation requires urgent manipulation to recover the ankle mortise. KEY WORDS: fracture, ankle, tibia, fibula, bones.

Literature review of biomechanics of the ankle/ foot complex: changes in functional activities postoperatively for ankle fractures

The ankle plays an important role in daily life under the functional point of view. It is essential to perform basic movements such as walking, running, etc. The ankle joint complex is a part of the body most frequently injured of the musculoskeletal system. Orthopedic fractures in this joint may be classified as low trauma and high energy, the latter trauma, usually found in traffic accidents and falls from great heights are the most disabling. In the general context often this type of fracture compromises neighboring joints due to misalignment of the loading axis of the involved segment, emerging pain and progressive functional disability. In this context, this study aimed to review the literature of studies that were willing to analyze the biomechanical causes of the functional outcome of fractures of the complex orthopedic foot/ankle trauma generated by high and low energy. For this, a search was made in electronic databases indexing scientific articles, using the keyword search previously created. For better understanding we divided the literature review on topics: classification of ankle fractures, surgical treatment, no surgical indications and contraindications in cases of surgery, types of surgery with open reduction and internal fixation (ORIF), external and hybrid; wounds and complications consequences: amputation, obesity, arthritis and osteoarthritis, early motion, range of motion, gait pathology. From this review study, it is necessary that other publications in the field of physical therapy related biomechanical results of ankle fractures are carried out, since most studies were found in articles reporting on the medical surgeries.

Weber Ankle Fracture Classification System Yields Greatest Interobserver and Intraobserver Reliability Over AO/OTA and Lauge-Hansen Classification Systems Under Time Constraints in an Asian Population

No previous studies have evaluated the intra- and interobserver reliability between the Weber, Lauge-Hansen and AO Foundation/Orthopaedic Trauma Association (AO/OTA) classification systems under time constraints. This study compares the interobserver and intraobserver reliability of the aforementioned classification systems under simulated time constraints. Anteroposterior and lateral radiographs of ankle malleolar fractures from 80 consecutive patients from 2015 to 2016 were classified by 2 independent observers according to Weber, Lauge-Hansen and AO/OTA. Classifications were conducted over 4 successive weeks under timed (25-seconds) and untimed conditions, with 1-week gaps between each classification. Cohen's kappa and percentage agreement were calculated. Cohen's kappa for interobserver agreement ranged 0.67 to 0.67 and 0.59 to 0.73 for untimed and timed classifications for Weber; 0.38 to 0.47 and 0.44 to 0.50 for Lauge-Hansen; 0.28 to 0.49 and 0.13 to 0.37 for AO/OTA. Intraobserver agreement ranged from 0.83 to 0.85 and 0.78 to 0.79 for untimed and timed classifications for Weber; 0.46 to 0.65 and 0.59 to 0.73 for Lauge-Hansen; 0.42 to 0.63 and 0.40 to 0.51 for AO/OTA. Based on the Landis and Koch's benchmark scale, there was substantial agreement in the inter- and intraobserver variables for Weber; moderate agreement in inter- and intraobserver variables for Lauge-Hansen; fair and moderate agreement in inter- and intraobserver variables respectively for AO/OTA. Interobserver and intraobserver reliability was the most substantial for Weber, followed by Lauge-Hansen and AO/OTA. Time constraint did not have a statistically significant effect on the reliability of classifications. We recommend concurrent usage of the Weber and Lauge-Hansen system, since they demonstrate the greatest reliability and reproducibility, and confer better understanding of the fracture type, respectively.

Classification variability of ankle fractures between physicians with and without the title of specialist in orthopedics and traumatology (TEOT)

Objective: Evaluate the classification variability of ankle fractures among physicians with and without the title of specialist in orthopedics and traumatology (TEOT) from a reference service. Method: The study included 40 physicians who informed the year of training, the period they obtained TEOT, and which ankle fracture classification system(s) they use in their clinical practice. The physicians evaluated ten radiographs of five patients with ankle fractures and classified them based on the three classification systems; Lauge-Hansen, AO/OTA, and Danis-Weber. Result: Most physicians with TEOT between one and five years (n=19, 47.5%), and 15 (48.4%) physicians used the Lauge Hansen and Danis-Weber classifications. Regarding the radiographs evaluated, most (27.5%) physicians obtained correct answers using the Danis-Weber classification. It was also observed that the physicians with the lowest rates of correct answers in the classifications were those without TEOT (44.4%). Conclusion: Most physicians adequately classified the five cases of ankle fracture using the Danis-Weber classification. The highest frequency of correct answers was from the physicians with TEOT. Level of Evidence VI; Observational Descriptive Study.

Development and external validation of automated detection, classification, and localization of ankle fractures: inside the black box of a convolutional neural network (CNN)

PurposeConvolutional neural networks (CNNs) are increasingly being developed for automated fracture detection in orthopaedic trauma surgery. Studies to date, however, are limited to providing classification based on the entire image—and only produce heatmaps for approximate fracture localization instead of delineating exact fracture morphology. Therefore, we aimed to answer (1) what is the performance of a CNN that detects, classifies, localizes, and segments an ankle fracture, and (2) would this be externally valid?MethodsThe training set included 326 isolated fibula fractures and 423 non-fracture radiographs. The Detectron2 implementation of the Mask R-CNN was trained with labelled and annotated radiographs. The internal validation (or ‘test set’) and external validation sets consisted of 300 and 334 radiographs, respectively. Consensus agreement between three experienced fellowship-trained trauma surgeons was defined as the ground truth label. Diagnostic accuracy and area under the receiver operator characteristic curve (AUC) were used to assess classification performance. The Intersection over Union (IoU) was used to quantify accuracy of the segmentation predictions by the CNN, where a value of 0.5 is generally considered an adequate segmentation.ResultsThe final CNN was able to classify fibula fractures according to four classes (Danis-Weber A, B, C and No Fracture) with AUC values ranging from 0.93 to 0.99. Diagnostic accuracy was 89% on the test set with average sensitivity of 89% and specificity of 96%. External validity was 89–90% accurate on a set of radiographs from a different hospital. Accuracies/AUCs observed were 100/0.99 for the ‘No Fracture’ class, 92/0.99 for ‘Weber B’, 88/0.93 for ‘Weber C’, and 76/0.97 for ‘Weber A’. For the fracture bounding box prediction by the CNN, a mean IoU of 0.65 (SD ± 0.16) was observed. The fracture segmentation predictions by the CNN resulted in a mean IoU of 0.47 (SD ± 0.17).ConclusionsThis study presents a look into the ‘black box’ of CNNs and represents the first automated delineation (segmentation) of fracture lines on (ankle) radiographs. The AUC values presented in this paper indicate good discriminatory capability of the CNN and substantiate further study of CNNs in detecting and classifying ankle fractures.Level of evidenceII, Diagnostic imaging study.

Evaluation of ankle fracture classification systems in 193 trimalleolar ankle fractures

PurposeDifferent classification systems have been developed for ankle fractures. In recent years, the posterior malleolus has gained in importance and led to computed tomography (CT)-based classification systems. The aim of the study was to analyse their reliability, fracture patterns and influence on treatment strategy.MethodsPatients with a trimalleolar ankle fracture treated between 2011 and 2020 with preoperative radiographs and CT images were included. The blinded images were independently classified by three reviewers according to the AO/OTA, Herscovici, Bartoníček, Mason and Haraguchi classifications. The interobserver reliability was calculated by Fleiss' kappa (κ). CT images were analysed to determine the dimensions of the posterior malleolus fragments. Patient registries were reviewed regarding the treatment data.ResultsA total of 193 patients were included. The AO/OTA classification showed almost perfect inter- and intraobserver reliability (Fleiss’ κ = 0.86, 95% CI 0.82–0.90). Regarding the posterior malleolus, the Bartoníček classification demonstrated the highest reliability (Fleiss’ κ = 0.78, 95% CI 0.73–0.83). The Herscovici classification only reached moderate reliability for medial malleolus fractures (Fleiss' κ = 0.59, 95% CI 0.54–0.65). There was a trend towards direct fixation of the posterior malleolus in the last 3 years of the observation period (OR: 2.49, 95% CI 1.03–5.99).ConclusionIn trimalleolar ankle fractures, the AO/OTA classification is a reliable system to characterize the type of fracture, but it fails to provide solid information about the posterior malleolus. Nowadays, treatment recommendations for trimalleolar ankle fractures focus on the configuration of the posterior malleolus; therefore, the results of this study advocate the use of the Bartoníček classification as a reliable tool to guide treatment.

Does the Lauge-Hansen Injury Mechanism Predict Posterior Malleolar Fracture Morphology?

The Lauge-Hansen ankle fracture classification system is widely accepted and is utilized to describe and predict ankle fracture patterns based on the mechanism of injury. Multiple studies have shown inconsistencies in the Lauge-Hansen's ability to predict fracture patterns based on the mechanism of injury. We set out to determine if the posterior malleolar fracture pattern is associated with the fracture types described by Lauge-Hansen. In this retrospective cohort study, we reviewed 153 patients with trimalleolar ankle fractures as diagnosed using computed tomography scans. Timing of injury was from February 2013 to August 2017. Patient ages ranged between 18 and 89 years old. Each patient had a complete clinical and radiographic workup including a preoperative computed tomographic scan following initial fracture reduction in the emergency room. We classified each ankle fracture based on plain film radiographs using the Lauge-Hansen classification scheme. Each individual posterior malleolar fracture was evaluated on computed tomography imaging and described using both the Haraguchi and Bartonicek-Rammelt classification systems. Of the 153 patients identified with trimalleolar ankle fractures, 70% were female (±20%), the mean age was 51 y (±8 y), and the mean body mass index was 30 kg/m2 (±3 kg/m2). We did not observe a significant association between the Lauge-Hansen injury mechanism and either the Bartonicek-Rammelt or the Haraguchi trimalleolar ankle fracture classification systems (chi-square correlation tests p > .05).

A machine learning‐based method for automatic diagnosis of ankle fracture using X‐ray images

AbstractDue to the complex mechanism of ankle injury, the clinical diagnosis of ankle fracture is extremely difficult. In order to simplify the fracture diagnosis process, this study proposes an automatic diagnosis model of ankle fractures. Firstly, an ankle fracture classification method suitable for machine learning was developed. By dividing six fracture regions, multiple types of fractures were clarified, and a corresponding dataset was created accordingly. Secondly, the random forest model was used to preprocess the X‐ray images and segment the fracture foreground part of the X‐ray images. Finally, the bag of visual words (BoVW) was used for feature extraction, and classifiers were constructed in different regions for classification. The area under the curve (AUC) of XGBoost was 0.92 ± 0.06. The performance of the XGBoost has proved to be better compared with the SVM when training on a small dataset in each region.

A novel classification for medial malleolar fracture based on the 3-D reconstruction CT

BackgroundFracture of the medial malleolus is one of the most frequent injuries treated surgically; however, the classification of the fracture has not attracted much attention and a good classification system is still lacking.MethodsConsecutive cases of medial malleolus fractures were prospectively enrolled. Based on the 3-D reconstruction CT morphology and centered on the posterior colliculus of the medial malleolus, we classified the fractures into 4 types: type 1 with no involvement of the posterior colliculus, type 2 with partial involvement of posterior colliculus, type 3 with the entire involvement of posterior colliculus, and type 4 with the fracture line 4 vertically extended from the intercollicular groove to the comminuted fracture of the posterior malleolus. Statistical analyses were performed to evaluate the clinical significance of the classification.ResultsThere were 273 cases prospectively enrolled. The distribution of the cases was type 1 of 12.1%, type 2 of 41.0%, type 3 of 30.0%, and type 4 of 16.8%. Statistics showed that the new classification had significant associations but did not totally depend on the classical ankle fracture classifications. Results showed that the new classification had implications in the severity of ankle fractures. From type 1 to type 4, the ankle joint was more and more unstable. Furthermore, comminuted medial malleolar fractures could be subdivided, and the new classification could provide useful information for surgical decision-making.ConclusionsThe novel classification was a useful system to describe the 3-D geometry of the fractured medial malleolus.

The Value of CT 3D Reconstruction in the Classification and Nursing Effect Evaluation of Ankle Fracture.

Aim To study the application value of ankle fracture classification and diagnosis. In this paper, the clinical data of 100 cases of ankle fracture patients admitted from May 2020 to May 2021 were analyzed by CT 3D reconstruction. All patients received surgical treatment and underwent spiral CT 3D reconstruction and X-ray examination before surgery. The results showed that 20 cases (20.00%) of the 100 cases were PER, 24 cases (24%) of the 100 cases were PAB, 31 cases (31%) of the 100 cases were SER, and 25 cases (25%) of the 100 cases were SAB, respectively. Conclusion The diagnostic accuracy of CT 3D reconstruction for different types of ankle fracture is higher than that of X-ray, and the differences are statistically significant (P < 0.05). CT 3D reconstruction is applied in the early diagnosis of ankle fracture, which can accurately detect the classification of patients. It has important clinical application value and can be used as the first choice for the early classification diagnosis of ankle fracture.

Lack of Surgeon Standardization on Implant Selection in Ankle Fracture Fixation May Increase Costs and Decrease Contribution Margin.

Surgical standardization has been shown to decrease costs without impacting quality; however, there is limited literature on this subject regarding ankle fracture fixation. Methods. Between October 5, 2015 and September 27, 2017, a total of 168 patients with isolated ankle fractures who underwent open reduction, internal fixation (ORIF) were analyzed. Financial data were analyzed across ankle fracture classification type, implant characteristics, and surgeons. Bivariate analyses were conducted. One-way analysis of variance was used to compare hardware costs across all 5 surgeons. Linear regression analysis was used to determine if hardware cost differed by surgeon when accounting for fracture type. The mean contribution margin was $4853 (SD $6446). There was a significant difference in implant costs by surgeon (range, lowest-cost surgeon: $471 [SD $283] to $1609 [SD $819]; P < .001). There was no difference in the use of a suture button or locking plate by fracture type (P = .13); however, the cost of the implant was significantly higher if a suture button or locking plate was used ($1014 [SD $666] vs $338 [SD $176]; P < .001). There was an association between surgeon 3 (β = 200.32 [95% CI 6.18-394.47]; P = .043) and surgeon 4 (β = 1131.07 [95% CI 906.84-1355.30]; P < .001) and higher hardware costs. Even for the same ankle fracture type, a wide variation in implant costs exists. The lack of standardization among surgeons accounted for a nearly 3.5-fold difference, on average, between the lowest- and highest-cost surgeons, negatively affecting contribution margin. Level IV.

Comparison of effectiveness between plate and screw internal fixation in treatment of posterior malleolus fractures through posterolateral approach

To compare the effectiveness of posterior malleolus fractures treated by plate and screw internal fixation through posterolateral approach. The clinical data of 95 patients with posterior malleolus fractures who were admitted between January 2016 and December 2019 and met the selection criteria were retrospectively analysed. They were divided into plate group (44 cases, treated with posterolateral plate internal fixation) and screw group (51 cases, treated with posterolateral screw internal fixation) according to different treatment methods. There was no significant difference in general data between the two groups of patients such as age, gender, cause of injury, side of injury, ankle fracture or injury classification, time from injury to operation, and percentage of posterior ankle fracture area to the distal tibia articular surface ( P>0.05). The operation time, hospital stay, fracture healing time, and surgical complications were compared between the two groups. Imaging examinations (X-ray film, CT scan and reconstruction) were used to assess the reduction quality of ankle fracture, articular congruity, and re-displacement in ankle fracture. At last follow-up, the pain visual analogue scale (VAS) score was used to evaluate the patients' pain, and the American Orthopaedic Foot and Ankle Society (AOFAS) ankle-hindfoot score was used to evaluate ankle joint function. Patients in both groups were followed up 6-30 months, with an average of 18.2 months. The operation time of the plate group was significantly longer than that of the screw group ( U=-2.040, P=0.041); there was no significant difference in hospital stay between the two groups ( U=-1.068, P=0.285). Incision swelling occurred in 2 cases in the plate group, sural nerve injury in 3 cases, and traumatic arthritis in 2 cases during follow-up. In the screw group, there were 1, 2, and 2 cases, respectively. The incidence of complications in the two groups (15.9% vs. 9.8%) was not significantly different ( P=0.372). All patients who underwent tibiofibular screw fixation underwent the removal of the tibiofibular screw before taking full weight bearing at 12 weeks after operation, and there was no screw fracture and retention. During the follow-up, there was no infection, re-displacement of fracture, delayed bone union or nonunion, and there was no significant difference in fracture healing time between the two groups ( t=0.345, P=0.731). There was no significant difference between the two groups of reduction quality of ankle fracture and articular congruity evaluation results ( P>0.05). At last follow-up, there was no significant difference in VAS score, AOFAS ankle-hindfoot score and evaluation grade between the two groups ( P>0.05). Both the plate and screw internal fixation through posterolateral approach can achieve satisfied effectiveness in the treatment of posterior ankle fractures with maintenance of fracture reduction, and recovery of ankle joint function. The screw internal fixation has the advantages of minimal invasion and shorter operation time.

Ankle fracture management using smartphone multimedia messaging service (MMS) imaging — How reliable and to what point?

BackgroundThe use of smartphones and multimedia messaging service (MMS) continues to increase in day to day orthopaedic clinical practice. However, there is limited evidence to support the safe utilisation of MMS. ObjectivesThe aim of this study was to correlate the performance of MMS imaging to picture archiving and communication systems (PACS) imaging within the setting of diagnosis and management of ankle fractures. MethodsThe ankle fracture radiograph series of 82 consecutive patients were evaluated by five orthopaedic consultant specialists. A questionnaire regarding diagnosis and preferred management was completed separately for each patient using smartphone and PACS images. Statistical analysis was performed using Intraclass Correlation Coefficient (ICC). ResultsAnkle fracture diagnosis showed strong to excellent correlation both inter- and intraobserver MMS vs PACS when using the Weber (0.815, 0.988), Anatomical (0.858, 0.988), and AO classification systems (0.855, 0.985). MMS was less reliable than PACS in determining many management options. ConclusionThe reliability of ankle fracture classification using MMS image viewing was not significantly different to interpretation on PACS workstations. Smartphone use in ankle fracture classification is supported by this study. Smartphone use was less accurate than PACS in devising management plans and future use should be limited to making only initial plans that must be corroberated with PACS and intraoperative findings prior to definitive fixation.

Medical Image Analysis and Correlation Between Ankle Fracture Classification and Ankle Computed Tomography

Objective: In this paper, we summarize computed tomography (CT) manifestations and characteristics of ankle fractures, and analyze the relationship between CT images and common ankle fracture classifications. Methods: A retrospective survey of 369 adult ankle fractures was performed. CT images of 1 cm horizontal cross-section above the ankle points and their characteristics were analyzed. Ankle fracture X-ray classification was performed, and the relationship between CT images and fracture X-ray classification was analyzed. Results: There is a correlation between CT images and Danis-Weber classification. The incidence of IOL fractures varies with the severity of Danis-Weber classification. After rank correlation test, the difference is statistically significant (Spearman R = 0.781,P &lt; 0.001). CT images can detect IOL fractures that cannot be judged by X-ray fracture classification, and the incidence rate is 5.9%. Conclusions: The 1 cm horizontal cross-section CT image on the ankle point can clearly determine the combined tibiofibular IOL injury before surgery, and it has a good correlation with the Danis-Weber fracture classification, and can detect unexplainable IOL fractures in some radiographs.

Ankle fracture classification using deep learning: automating detailed AO Foundation/Orthopedic Trauma Association (AO/OTA) 2018 malleolar fracture identification reaches a high degree of correct classification

Background and purpose — Classification of ankle fractures is crucial for guiding treatment but advanced classifications such as the AO Foundation/Orthopedic Trauma Association (AO/OTA) are often too complex for human observers to learn and use. We have therefore investigated whether an automated algorithm that uses deep learning can learn to classify radiographs according to the new AO/OTA 2018 standards. Method — We trained a neural network based on the ResNet architecture on 4,941 radiographic ankle examinations. All images were classified according to the AO/OTA 2018 classification. A senior orthopedic surgeon (MG) then re-evaluated all images with fractures. We evaluated the network against a test set of 400 patients reviewed by 2 expert observers (MG, AS) independently. Results — In the training dataset, about half of the examinations contained fractures. The majority of the fractures were malleolar, of which the type B injuries represented almost 60% of the cases. Average area under the area under the receiver operating characteristic curve (AUC) was 0.90 (95% CI 0.82–0.94) for correctly classifying AO/OTA class where the most common major fractures, the malleolar type B fractures, reached an AUC of 0.93 (CI 0.90–0.95). The poorest performing type was malleolar A fractures, which included avulsions of the fibular tip. Interpretation — We found that a neural network could attain the required performance to aid with a detailed ankle fracture classification. This approach could be scaled up to other body parts. As the type of fracture is an important part of orthopedic decision-making, this is an important step toward computer-assisted decision-making.