Improving Radiographic Fracture Recognition Performance and Efficiency Using Artificial Intelligence.

Background Missed fractures are a common cause of diagnostic discrepancy between initial radiographic interpretation and the final read by board-certified radiologists. Purpose To assess the effect of assistance by artificial intelligence (AI) on diagnostic performances of physicians for fractures on radiographs. Materials and Methods This retrospective diagnostic study used the multi-reader, multi-case methodology based on an external multicenter data set of 480 examinations with at least 60 examinations per body region (foot and ankle, knee and leg, hip and pelvis, hand and wrist, elbow and arm, shoulder and clavicle, rib cage, and thoracolumbar spine) between July 2020 and January 2021. Fracture prevalence was set at 50%. The ground truth was determined by two musculoskeletal radiologists, with discrepancies solved by a third. Twenty-four readers (radiologists, orthopedists, emergency physicians, physician assistants, rheumatologists, family physicians) were presented the whole validation data set (n = 480), with and without AI assistance, with a 1-month minimum washout period. The primary analysis had to demonstrate superiority of sensitivity per patient and the noninferiority of specificity per patient at -3% margin with AI aid. Stand-alone AI performance was also assessed using receiver operating characteristic curves. Results A total of 480 patients were included (mean age, 59 years ± 16 [standard deviation]; 327 women). The sensitivity per patient was 10.4% higher (95% CI: 6.9, 13.9; P < .001 for superiority) with AI aid (4331 of 5760 readings, 75.2%) than without AI (3732 of 5760 readings, 64.8%). The specificity per patient with AI aid (5504 of 5760 readings, 95.6%) was noninferior to that without AI aid (5217 of 5760 readings, 90.6%), with a difference of +5.0% (95% CI: +2.0, +8.0; P = .001 for noninferiority). AI shortened the average reading time by 6.3 seconds per examination (95% CI: -12.5, -0.1; P = .046). The sensitivity by patient gain was significant in all regions (+8.0% to +16.2%; P < .05) but shoulder and clavicle and spine (+4.2% and +2.6%; P = .12 and .52). Conclusion AI assistance improved the sensitivity and may even improve the specificity of fracture detection by radiologists and nonradiologists, without lengthening reading time. Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Link and Pedoia in this issue.

Diagnosis of Concussion on the Sidelines.

The forthcoming discussion will review the current state of the literature surrounding best practice guidelines for diagnosis of sports-related concussions on the sidelines. A sports-related concussive event is a complex process to define, which further increases its diagnostic process. At present there is no singular, gold-standard assessment tool available for the diagnosis of sports-related concussions on the sideline. Current best-practice recommendations suggest the utilization of a multifactorial examination process in a controlled environment. Sideline evaluations must include assessments of symptoms, physical and neurologic status, cognitive function, balance capabilities, and clinical assessments for the presence of cervical spine injuries, skull fractures, and intracranial bleeds. Clinical utility is emerging for involvement of assessments of oculomotor and reaction time function, medical spotters/replay technology, and equipment-based motion/impact sensors. The diagnostic process of sports-related concussions can be enhanced when performed by a sports medicine professional with specific experience with the patient at hand due to increased familiarity with premorbid patient disposition and function. Larger scale research studies with sound methodological processes is needed to further bolster best practice recommendations, with specific attention to the youth demographic.

Myofascial Pain.

Myofascial pain syndromes arise from acute and chronic musculoskeletal pain and often have a referred neuropathic component. It affects more than three quarters of the world's population and is one of the most important and overlooked causes of disability. The origins of pain are thought to reside anywhere between the motor end plate and the fibrous outer covering of the muscle, with involvement of microvasculature and neurotransmitters at the cellular level. Diagnosis is made by clinical examination for the presence of myofascial trigger points, though some ancillary tests may provide supportive evidence. The mainstay of treatment is regular physical therapy with the goal of restoration of normal muscle laxity and range of motion. Adjunct therapies including pharmacologic and nonpharmacologic interventions provide varying degrees of benefit in refractory cases, and onabotulinum toxin A injection has the most evidence of efficacy for these patients. Here, we discuss the epidemiology, pathophysiology, and diagnostic and therapeutic options for the evaluation and treatment of myofascial pain syndrome.

Cervical radiculopathy.

Cervical radiculopathy is the result of irritation and/or compression of nerve root as it exits the cervical spine. Pain is a common presenting symptom and may be accompanied by motor or sensory deficits in areas innervated by the affected nerve root. Diagnosis is suggested by history and corresponding physical examination findings. Confirmation is achieved with MRI. A multimodal approach to treatment helps patients improve. Medications may be used to alleviate symptoms and manage pain. Physical therapy and manipulation may improve neck discomfort. Guided corticosteroid injections and selected nerve blocks may help control nerve root pain. Most patients improve with a conservative, nonoperative treatment course.

Skin conditions in the athlete.

Dermatologic conditions are a common presenting complaint in the athletic training room. There are many different causes for rashes, and treatment options vary depending on the condition and the severity. Bacterial infections of the skin have a variety of different appearances and can spread rapidly among individuals. Healthcare providers need to be aware of the increasing prevalence of methicillin-resistant Staphylococcus aureus when making the choice of antibiotics. Other infectious rashes, including tinea and herpes, are well-described conditions in wrestlers; however, these rashes can be seen in any athlete, especially those engaged in contact sports. Early recognition and appropriate treatment are important to clear the rash and reduce the spread to others. In addition to infectious rashes, athletes are prone to mechanical rashes and skin conditions due to friction and tight-fitting equipment. Sports medicine providers must not only diagnose and treat these conditions but also be aware of the return-to-play guidelines set forth by the governing bodies under which he or she operates.