Automatic Hip Fracture Identification and Functional Subclassification with Deep Learning.

PURPOSE: To investigate the feasibility of automatic identification and classification of hip fractures using deep learning, which may improve outcomes by reducing diagnostic errors and decreasing time to operation. MATERIALS AND METHODS: Hip and pelvic radiographs from 1118 studies were reviewed, and 3026 hips were labeled via bounding boxes and classified as normal, displaced femoral neck fracture, nondisplaced femoral neck fracture, intertrochanteric fracture, previous open reduction and internal fixation, or previous arthroplasty. A deep learning-based object detection model was trained to automate the placement of the bounding boxes. A Densely Connected Convolutional Neural Network (or DenseNet) was trained on a subset of the bounding box images, and its performance was evaluated on a held-out test set and by comparison on a 100-image subset with two groups of human observers: fellowship-trained radiologists and orthopedists; senior residents in emergency medicine, radiology, and orthopedics. RESULTS: The binary accuracy for detecting a fracture of this model was 93.7% (95% confidence interval [CI]: 90.8%, 96.5%), with a sensitivity of 93.2% (95% CI: 88.9%, 97.1%) and a specificity of 94.2% (95% CI: 89.7%, 98.4%). Multiclass classification accuracy was 90.8% (95% CI: 87.5%, 94.2%). When compared with the accuracy of human observers, the accuracy of the model achieved an expert-level classification, at the very least, under all conditions. Additionally, when the model was used as an aid, human performance improved, with aided resident performance approximating unaided fellowship-trained expert performance in the multiclass classification. CONCLUSION: A deep learning model identified and classified hip fractures with expert-level performance, at the very least, and when used as an aid, improved human performance, with aided resident performance approximating that of unaided fellowship-trained attending physicians.Supplemental material is available for this article.© RSNA, 2020.

External validation of the clinical indications of computed tomography (CT) of the head in patients with low-energy geriatric hip fractures.

INTRODUCTION: On evaluation of the clinical indications of computed tomography (CT) scan of head in the patients with low-energy geriatric hip fractures, Maniar et al. identified physical evidence of head injury, new onset confusion, and Glasgow Coma Scale (GCS)<15 as predictive risk factors for acute findings on CT scan. The goal of the present study was to validate these three criteria as predictive risk factors for a larger population in a wider geographical distribution. PATIENTS AND METHODS: Patients ≥65 years of age with low-energy hip fractures from 6 trauma centers in a wide geographical distribution in the United States were included in this study. In addition to the relevant patient demographic findings, the above mentioned three criteria and acute findings on head CT scan were gathered as categorical variables. RESULTS: In total 799 patients from 6 centers were included in the study. There were 67 patients (8.3%) with positive acute findings on head CT scan. All of these patients (100%) had at least one criteria positive. There were 732 patients who had negative acute findings on head CT scan with 376 patients (51%) having at least one criteria positive and 356 patients (49%) having no criteria positive. Sensitivity of 100% and negative predictive value of 100% was observed to predict negative acute findings on head CT scan when all the three criteria were negative. CONCLUSION: With the observed 100% sensitivity and 100% negative predictive value, physical evidence of acute head injury, acute retrograde amnesia, and GCS<15 can be recommended as a clinical decision guide for the selective use of head CT scans in geriatric patients with low energy hip fractures. All the patients with positive acute head CT findings can be predicted in the presence of at least one positive criterion. In addition, if these criteria are used as a pre-requisite to order the head CT, around 50% of the unnecessary head CT scans can be avoided.

Fragility fracture programs: are they effective and what is the surgeon's role?

Fragility fractures are occurring at an ever-increasing rate, creating an enormous economic and societal impact. Outpatient-based fragility fracture programs have been developed to identify at-risk patients, initiate effective treatment of metabolic bone disease, and improve coordination between members of the patient's care team with the goal of reducing future fractures. Inpatient programs focus on effective, efficient management of patients presenting with acute fractures. Both have proven successful in reducing the impact of fragility fractures, but many challenges exist. The orthopedic surgeon, as part of an integrated team of providers, is integral in identifying at-risk patients, ensuring appropriate care of acute fractures, and initiating treatment protocols to reduce the risk of further injuries.

Fractures and dislocations of the midfoot: Lisfranc and Chopart injuries.

The midfoot is a complex association of five bones and many articulations between the forefoot metatarsals and the talus and calcaneus, which make up the hindfoot. These anatomic relationships are connected and restrained by an even more complex network of ligaments, capsules, and fascia, which must function as a unit to provide normal and painless locomotion. The common eponyms of Lisfranc and Chopart refer to the distal and proximal joint relationships of the midfoot, respectively. Midfoot injuries range from single ligament strains to complicated fracture-dislocations involving multiple bones and joints. To provide best outcomes for patients, it is important to understand the anatomy and the mechanical function of the midfoot; to review the epidemiology, mechanism, and classification of injuries encountered in an orthopaedic clinical practice; and to review the principles, indications, and surgical techniques for managing midfoot fractures and dislocations.

Medicolegal information for the young traumatologist: better safe than sorry.

Because every orthopaedic traumatologist will interact with the legal system during their career--either as a treating physician of a patient involved in legal action, an expert witness, or as a defendant in a lawsuit--a basic understanding of the legal process is paramount to successfully serve in these roles. Common truths and misperceptions about medicolegal risk, expectations of care and documentation in the trauma setting, and information about being deposed and giving expert testimony will be discussed.

When things don't work out: finding another job.

It is extremely common for young orthopaedic surgeons find themselves in unsatisfactory practice situations early in their careers. This article highlights several points to bear in mind when considering a change of employment in the first few years of practice. Many factors should be revisited from the candidate's initial job search to fully analyze the situation. If the problems are found to be irreconcilable, then the decision can be made to find a more suitable setting, but the relocation process should be handled judiciously. There are many resources available that can be helpful to make a successful transition.

Incidence of wrong-site surgery among hand surgeons.

BACKGROUND: Until recently, wrong-site surgery had received little attention and had been considered a random, infrequent event. In 1997, the American Academy of Orthopaedic Surgeons (AAOS) Task Force on Wrong-Site Surgery was formed to determine the incidence of wrong-site surgery and to initiate the "Sign Your Site" campaign. The purpose of our study was to determine the incidence of wrong-site surgery among hand surgeons, elucidate surgeons' practice habits and measures taken to prevent its occurrence, and evaluate the effectiveness of the AAOS "Sign Your Site" campaign. METHODS: One thousand, five hundred and sixty active members of the American Society for Surgery of the Hand (ASSH) were polled by mail. Each member received a confidential twenty-nine-question survey. Nonrespondents were sent a second, identical survey. One thousand and fifty (67%) of the surgeons responded. RESULTS: One hundred and seventy-three surgeons (16%) reported that they had prepared to operate on the wrong site but then noticed the error prior to the incision, and 217 (21%) reported performing wrong-site surgery at least once. Of an estimated 6,700,000 surgical procedures, 242 were performed at the wrong site, an incidence of one in 27,686 procedures. The three most common locations of wrong-site surgery were the fingers (153), hands (twenty), and wrists (twenty-one). Permanent disability occurred in twenty-one patients (9%). Ninety-three cases (38%) led to legal action or monetary settlement. Seventy percent of the responding orthopaedic surgeons were aware of the "Sign Your Site" campaign, and 45% had changed their practice habits as a result. CONCLUSIONS: Prior to the AAOS "Sign Your Site" campaign, the issue of wrong-site surgery by hand surgeons had not been addressed. Although wrong-site surgery is rare, 21% of hand surgeons reported performing it at least once during their careers. Since the institution of the "Sign Your Site" campaign, 45% of orthopaedic hand surgeons have changed their practice habits, and almost all routinely take some action to prevent wrong-site surgery.