Prospective comparison of admission computed tomographic scan and plain films of the upper cervical spine in trauma patients with altered mental status

PECARN prediction rule for cervical spine imaging of children presenting to the emergency department with blunt trauma: a multicentre prospective observational study

BACKGROUND

Cervical spine injuries in children are uncommon but potentially devastating; however, indiscriminate neck imaging after trauma unnecessarily exposes children to ionising radiation. The aim of this study was to derive and validate a paediatric clinical prediction rule that can be incorporated into an algorithm to guide radiographic screening for cervical spine injury among children in the emergency department.

METHODS

In this prospective observational cohort study, we screened children aged 0-17 years presenting with known or suspected blunt trauma at 18 specialised children's emergency departments in hospitals in the USA affiliated with the Pediatric Emergency Care Applied Research Network (PECARN). Injured children were eligible for enrolment into derivation or validation cohorts by fulfilling one of the following criteria: transported from the scene of injury to the emergency department by emergency medical services; evaluated by a trauma team; and undergone neck imaging for concern for cervical spine injury either at or before arriving at the PECARN-affiliated emergency department. Children presenting with solely penetrating trauma were excluded. Before viewing an enrolled child's neck imaging results, the attending emergency department clinician completed a clinical examination and prospectively documented cervical spine injury risk factors in an electronic questionnaire. Cervical spine injuries were determined by imaging reports and telephone follow-up with guardians within 21-28 days of the emergency room encounter, and cervical spine injury was confirmed by a paediatric neurosurgeon. Factors associated with a high risk of cervical spine injury (>10%) were identified by bivariable Poisson regression with robust error estimates, and factors associated with non-negligible risk were identified by classification and regression tree (CART) analysis. Variables were combined in the cervical spine injury prediction rule. The primary outcome of interest was cervical spine injury within 28 days of initial trauma warranting inpatient observation or surgical intervention. Rule performance measures were calculated for both derivation and validation cohorts. A clinical care algorithm for determining which risk factors warrant radiographic screening for cervical spine injury after blunt trauma was applied to the study population to estimate the potential effect on reducing CT and x-ray use in the paediatric emergency department. This study is registered with ClinicalTrials.gov, NCT05049330.

FINDINGS

Nine emergency departments participated in the derivation cohort, and nine participated in the validation cohort. In total, 22 430 children presenting with known or suspected blunt trauma were enrolled (11 857 children in the derivation cohort; 10 573 in the validation cohort). 433 (1·9%) of the total population had confirmed cervical spine injuries. The following factors were associated with a high risk of cervical spine injury: altered mental status (Glasgow Coma Scale [GCS] score of 3-8 or unresponsive on the Alert, Verbal, Pain, Unresponsive scale [AVPU] of consciousness); abnormal airway, breathing, or circulation findings; and focal neurological deficits including paresthesia, numbness, or weakness. Of 928 in the derivation cohort presenting with at least one of these risk factors, 118 (12·7%) had cervical spine injury (risk ratio 8·9 [95% CI 7·1-11·2]). The following factors were associated with non-negligible risk of cervical spine injury by CART analysis: neck pain; altered mental status (GCS score of 9-14; verbal or pain on the AVPU; or other signs of altered mental status); substantial head injury; substantial torso injury; and midline neck tenderness. The high-risk and CART-derived factors combined and applied to the validation cohort performed with 94·3% (95% CI 90·7-97·9) sensitivity, 60·4% (59·4-61·3) specificity, and 99·9% (99·8-100·0) negative predictive value. Had the algorithm been applied to all participants to guide the use of imaging, we estimated the number of children having CT might have decreased from 3856 (17·2%) to 1549 (6·9%) of 22 430 children without increasing the number of children getting plain x-rays.

INTERPRETATION

Incorporated into a clinical algorithm, the cervical spine injury prediction rule showed strong potential for aiding clinicians in determining which children arriving in the emergency department after blunt trauma should undergo radiographic neck imaging for potential cervical spine injury. Implementation of the clinical algorithm could decrease use of unnecessary radiographic testing in the emergency department and eliminate high-risk radiation exposure. Future work should validate the prediction rule and care algorithm in more general settings such as community emergency departments.

FUNDING

The Eunice Kennedy Shriver National Institute of Child Health and Human Development and the Health Resources and Services Administration of the US Department of Health and Human Services in the Maternal and Child Health Bureau under the Emergency Medical Services for Children programme.

Diagnostic accuracy of deep learning for evaluation of C-spine injury from lateral neck radiographs

Background

Traumatic spinal cord injury (TSI) is a leading cause of morbidity and mortality worldwide, with the cervical spine being the most affected. Delayed diagnosis carries a risk of morbidity and mortality. However, cervical spine CT scans are time-consuming, costly, and not always available in general care. In this study, deep learning was used to assess and improve the detection of cervical spine injuries on lateral radiographs, the most widely used screening method to help physicians triage patients quickly and avoid unnecessary CT scans.

Materials and methods

Lateral neck or lateral cervical spine radiographs were obtained for patients who underwent CT scan of cervical spine. Ground truth was determined based on CT reports. CiRA CORE, a codeless deep learning program, was used as a training and testing platform. YOLO network models, including V2, V3, and V4, were trained to detect cervical spine injury. The diagnostic accuracy, sensitivity, and specificity of the model were calculated.

Results

A total of 229 radiographs (129 negative and 100 positive) were selected for inclusion in our study from a list of 625 patients with cervical spine CT scans, 181 (28.9%) of whom had cervical spine injury. The YOLO V4 model performed better than the V2 or V3 (AUC = 0.743), with sensitivity, specificity, and accuracy of 80%, 72% and 75% respectively.

Conclusion

Deep learning can improve the accuracy of lateral c-spine or neck radiographs. We anticipate that this will assist clinicians in quickly triaging patients and help to minimize the number of unnecessary CT scans.

Anterior-posterior view by full-body digital X-ray to rule out severe spinal injuries in Polytraumatized patients

BACKGROUND

Spinal injuries are present in 16-31% of polytraumatized patients. Rapid identification of spinal injuries requiring immobilization or operative treatment is essential. The Lodox-Statscan (LS) has evolved into a promising time-saving diagnostic tool to diagnose life-threatening injuries with an anterior-posterior (AP)-full-body digital X-ray.

METHODS

We aimed to analyze the diagnostic accuracy and the interrater reliability of AP-LS to detect spinal injuries in polytraumatized patients. Therefore, within 3 years, AP-LS of polytraumatized patients (ISS ≥ 16) were retrospectively analyzed by three independent observers. The sensitivity and specificity of correct diagnosis with AP-LS compared to CT scan were calculated. The diagnostic accuracy was evaluated by using the area under the ROC (receiver operating characteristic curve) for sensitivity and specificity. Interrater reliability between the three observers was calculated using Fleiss' Kappa. The sensitivity of AP-LS was further analyzed by the severity of spinal injuries.

RESULTS

The study group included 320 patients (48.5 years ±19.5, 89 women). On CT scan, 207 patients presented with a spinal injury (65%, total of 332 injuries). AP-LS had a low sensitivity of 9% (31 of 332, range 0-24%) and high specificity of 99% (range 98-100%). The sensitivity was highest for thoracic spinal injuries (14%). The interrater reliability was slight (κ = 0.02; 95% CI: 0.00, 0.03). Potentially unstable spinal injuries were more likely to be detected than stable injuries (sensitivity 18 and 6%, respectively).

CONCLUSION

This study demonstrated high specificity with low sensitivity of AP-LS in detecting spinal injuries compared to CT scan. In polytraumatized patients, AP-LS, implemented in the Advanced Trauma Life Support-algorithm, is a helpful tool to diagnose life-threatening injuries. However, if spinal injuries are suspected, performing a full-body CT scan is necessary for correct diagnosis.

The 100 Most-Cited Papers in Traumatic Injury of the Spine

Background

Traumatic injury to the spine can be a complex diagnostic and therapeutic entity often with devastating consequences. Outside of the isolated vertebral column injury costs; annual costs associated with spinal cord injury (SCI) are estimated to exceed $9.7 billion.

Objective

To identify the 100 most-cited articles on spine trauma.

Methods

The Thomson Reuters Web of Science citation indexing service was queried. The articles were sorted by times cited in descending order. Two independent reviewers reviewed the article titles and abstracts to identify the top 100 most-cited articles.

Results

The top 100 articles were found to be cited between 108 (articles #99-100) and 1595 times (article #1). The most-cited basic science article was cited 340 times (#12 on the top 100 list). The oldest article on the top 100 list was from 1953 and most recent from 2012. The number of patients, when applicable, in a study ranged from 9 (article #34) to 34,069 (article #5). Top 100 articles were published in 41 different journals with a wide range of specialities and fields most commonly multidisciplinary. Basic science research encompassed 34 of the 100 articles on the list.

Conclusions

We present the 100 most-cited articles in spinal trauma with emphases on important contributions from both basic science and clinical research across a wide range of authors, specialties, patient populations, and countries. Recognizing some of the most important contributions in the field of spinal trauma may provide insight and guide future work.

Evaluation of Cervical Spine Fracture in the Elderly: Can We Trust Our Physical Examination?

The purpose of this trial was to compare National Emergency X-Radiography Utilization Study (NEXUS) criteria (NC) with computed tomography (CT) as the gold standard to evaluate cervical spine (C-spine) fractures in elderly blunt trauma patients. We prospectively compared adult blunt trauma patients 65 years or older (E) with younger than 65 years (NE), evaluating the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of NC compared with CT in these two cohorts. A total of 2785 blunt trauma patients were included of whom 320 were E (average age, 75 years) and 2465 were NE (average age, 36 years). Incidence of C-spine fracture was 12.8 per cent (E) versus 7.4 per cent (NE) ( P = 0.002). Age was an independent predictor of fracture ( P = 0.01). NC had a sensitivity of 65.9 per cent in E and PPV of 19.3 per cent in E ( P = 0.001) versus a sensitivity of 84.2 per cent in NE and PPV of 10.6 per cent ( P < 0.0001). The specificity was 59.5 per cent for E versus 42.6 per cent for NE (NPV, 92.2% E vs 97.1% NE). This study suggests that NEXUS criteria are not an appropriate assessment tool when applied to severe blunt trauma patients, particularly in the elderly population who had more missed injures than their younger counterparts. CTshould be used in all blunt trauma patients regardless of whether they meet NEXUS criteria.

A Review on the Etiology and Management of Pediatric Traumatic Spinal Cord Injuries

CONTEXT

Pediatric traumatic spinal cord injury (SCI) is an uncommon presentation in the emergency department. Severe injuries are associated with devastating outcomes and complications, resulting in high costs to both the society and the economic system.

EVIDENCE ACQUISITION

The data on pediatric traumatic spinal cord injuries has been narratively reviewed.

RESULTS

Pediatric SCI is a life-threatening emergency leading to serious outcomes and high mortality in children if not managed promptly. Pediatric SCI can impose many challenges to neurosurgeons and caregivers because of the lack of large studies with high evidence level and specific guidelines in terms of diagnosis, initial management and of in-hospital treatment options. Several novel potential treatment options for SCI have been developed and are currently under investigation. However, research studies into this field have been limited by the ethical and methodological challenges.

CONCLUSION

Future research is needed to investigate the safety and efficacy of the recent uprising neurodegenerative techniques in SCI population. Owing to the current limitations, there is a need to develop novel trial methodologies that can overcome the current methodological and ethical limitations.

Functional Outcomes of Subaxial Spine Injuries Managed With 2-Level Anterior Cervical Corpectomy and Fusion: A Prospective Study

Objective

To evaluate the results of operative management of subaxial spine injuries managed with 2-level anterior cervical corpectomy and fusion with a cervical locking plate and autologous bone–filled titanium mesh cage.

Methods

This study included 23 patients with a subaxial spine injury who matched the inclusion criteria, underwent 2-level anterior cervical corpectomy and fusion at our institution between 2013 and 2016, and were followed up for neurological recovery, axial pain, fusion, pseudarthrosis, and implant failure.

Results

According to Allen and Ferguson classification, there were 9 cases of distractive extension; 4 of compressive extension; 3 each of compressive flexion, vertical compression, and distractive flexion; and 1 of lateral flexion. Sixteen patients had a score of 6 on the Subaxial Injury Classification system, and the rest had a score of more than 6. The mean follow-up period was 19 months (range, 12–48 months). Neurological recovery was observed in most of the patients (78.21%). All patients experienced relief of axial pain. None of the patients received a blood transfusion. Twenty-one patients (91.3%) showed solid fusion and 2 (8.69%) showed possible pseudarthrosis, with no complications related to the cage or plate.

Conclusion

Two-level anterior cervical corpectomy and fusion, along with stabilization with a cervical locking plate and autologous bone graft-filled titanium mesh cage, can be considered a feasible and safe method for treating specific subaxial spine injuries, with the benefits of high primary stability, anatomical reduction, and direct decompression of the spinal cord.

Triage tools for detecting cervical spine injury in pediatric trauma patients

BACKGROUND

Pediatric cervical spine injury (CSI) after blunt trauma is rare. Nonetheless, missing these injuries can have severe consequences. To prevent the overuse of radiographic imaging, two clinical decision tools have been developed: The National Emergency X-Radiography Utilization Study (NEXUS) criteria and the Canadian C-spine Rule (CCR). Both tools are proven to be accurate in deciding whether or not diagnostic imaging is needed in adults presenting for blunt trauma screening at the emergency department. However, little information is known about the accuracy of these triage tools in a pediatric population.

OBJECTIVES

To determine the diagnostic accuracy of the NEXUS criteria and the Canadian C-spine Rule in a pediatric population evaluated for CSI following blunt trauma.

SEARCH METHODS

We searched the following databases to 24 February 2015: CENTRAL, MEDLINE, MEDLINE Non-Indexed and In-Process Citations, PubMed, Embase, Science Citation Index, ProQuest Dissertations & Theses Database, OpenGrey, ClinicalTrials.gov, World Health Organization (WHO) International Clinical Trials Registry Platform (ICTRP), Cochrane Database of Systematic Reviews, the Database of Abstracts of Reviews of Effects, the Health Technology Assessment, and the Aggressive Research Intelligence Facility.

SELECTION CRITERIA

We included all retrospective and prospective studies involving children following blunt trauma that evaluated the accuracy of the NEXUS criteria, the Canadian C-spine Rule, or both. Plain radiography, computed tomography (CT) or magnetic resonance imaging (MRI) of the cervical spine, and follow-up were considered as adequate reference standards.

DATA COLLECTION AND ANALYSIS

Two review authors independently assessed the quality of included studies using the QUADAS-2 checklists. They extracted data on study design, patient characteristics, inclusion and exclusion criteria, clinical parameters, target condition, reference standard, and the diagnostic two-by-two table. We calculated and plotted sensitivity, specificity and negative predictive value in ROC space, and constructed forest plots for visual examination of variation in test accuracy.

MAIN RESULTS

Three cohort studies were eligible for analysis, including 3380 patients ; 96 children were diagnosed with CSI. One study evaluated the accuracy of the Canadian C-spine Rule and the NEXUS criteria, and two studies evaluated the accuracy of the NEXUS criteria. The studies were of moderate quality. Due to the small number of included studies and the diverse outcomes of those studies, we could not describe a pooled estimate for the diagnostic test accuracy. The sensitivity of the NEXUS criteria of the individual studies was 0.57 (95% confidence interval (CI) 0.18 to 0.90), 0.98 (95% CI 0.91 to 1.00) and 1.00 (95% CI 0.88 to 1.00). The specificity of the NEXUS criteria was 0.35 (95% CI 0.25 to 0.45), 0.54 (95% CI 0.45 to 0.62) and 0.2 (95% CI 0.18 to 0.21). For the Canadian C-spine Rule the sensitivity was 0.86 (95% CI 0.42 to 1.00) and specificity was 0.15 (95% CI 0.08 to 0.23). Since the quantity of the data was small we were not able to investigate heterogeneity.

AUTHORS' CONCLUSIONS

There are currently few studies assessing the diagnostic test accuracy of the NEXUS criteria and CCR in children. At the moment, there is not enough evidence to determine the accuracy of the Canadian C-spine Rule to detect CSI in pediatric trauma patients following blunt trauma. The confidence interval of the sensitivity of the NEXUS criteria between the individual studies showed a wide range, with a lower limit varying from 0.18 to 0.91 with a total of four false negative test results, meaning that if physicians use the NEXUS criteria in children, there is a chance of missing CSI. Since missing CSI could have severe consequences with the risk of significant morbidity, we consider that the NEXUS criteria are at best a guide to clinical assessment, with current evidence not supporting strict or protocolized adoption of the tool into pediatric trauma care. Moreover, we have to keep in mind that the sensitivity differs among several studies, and individual confidence intervals of these studies show a wide range. Our main conclusion is therefore that additional well-designed studies with large sample sizes are required to better evaluate the accuracy of the NEXUS criteria or the Canadian C-spine Rule, or both, in order to determine whether they are appropriate triage tools for the clearance of the cervical spine in children following blunt trauma.

Yield of computed tomography of the cervical spine in cases of simple assault

BACKGROUND

Computed tomography (CT) of the cervical spine (C-spine) is routinely ordered for low-impact, non-penetrating or "simple" assault at our institution and others. Common clinical decision tools for C-spine imaging in the setting of trauma include the National Emergency X-Radiography Utilization Study (NEXUS) and the Canadian Cervical Spine Rule for Radiography (CCR). While NEXUS and CCR have served to decrease the amount of unnecessary imaging of the C-spine, overutilization of CT is still of concern.

METHODS

A retrospective, cross-sectional study was performed of the electronic medical record (EMR) database at an urban, Level I Trauma Center over a 6-month period for patients receiving a C-spine CT. The primary outcome of interest was prevalence of cervical spine fracture. Secondary outcomes of interest included appropriateness of C-spine imaging after retrospective application of NEXUS and CCR. The hypothesis was that fracture rates within this patient population would be extremely low.

RESULTS

No C-spine fractures were identified in the 460 patients who met inclusion criteria. Approximately 29% of patients did not warrant imaging by CCR, and 25% by NEXUS. Of note, approximately 44% of patients were indeterminate for whether imaging was warranted by CCR, with the most common reason being lack of assessment for active neck rotation.

CONCLUSIONS

Cervical spine CT is overutilized in the setting of simple assault, despite established clinical decision rules. With no fractures identified regardless of other factors, the likelihood that a CT of the cervical spine will identify clinically significant findings in the setting of "simple" assault is extremely low, approaching zero. At minimum, adherence to CCR and NEXUS within this patient population would serve to reduce both imaging costs and population radiation dose exposure.

Subaxial cervical spine trauma

Subaxial cervical spine trauma is common and an often missed diagnosis. Accurate and efficient diagnosis and management is necessary to avoid devastating complications such as spinal cord injury. Several classification schemes have been devised to help categorize fractures of the subaxial spine and define treatment algorithms. The Subaxial Cervical Spine Injury Classification System (SLIC) is widely used and evaluates not only fracture morphology but also considers ligamentous injury and neurological status in surgical decision making. However, interobserver reliability is poor, which proves to be the defining pitfall of this tool. More modern classification systems have been developed, which aim to improve the interobserver reliability; however, further large-scale studies are needed for more definitive evaluation. Overall, treatment of subaxial cervical spine injuries should include a protocol with initial trauma evaluation, leading to expedient operative intervention if indicated. Surgical techniques include both anterior and posterior approaches to the cervical spine depending on fracture classification.

Pediatric spinal injury in the US: epidemiology and disparities

OBJECT

In the US, race and economic status have pervasive associations with mechanisms of injury, severity of injury, management, and outcomes of trauma. The goal of the current study was to examine these relationships on a large scale in the setting of pediatric spinal injury.

METHODS

Admissions for spinal fracture without or with spinal cord injury (SCI), spinal dislocation, and SCI without radiographic abnormality were identified in the Kids' Inpatient Database (KID) and the National Trauma Data Bank (NTDB) registry for 2009. Patients ranged in age from birth up to 21 years. Data from the KID were used to estimate nationwide annual incidences. Data from the NTDB were used to describe patterns of injury in relation to age, race, and payor, with corroboration from the KID. Multiple logistic regression was used to model rates of mortality and spinal fusion.

RESULTS

In 2009, the estimated incidence of hospital admission for spinal injury in the US was 170 per 1 million in the population under 21 years of age. The incidence of SCI was 24 per 1 million. Incidences varied regionally. Adolescents predominated. Patterns of injury varied by age, race, and payor. Black patients were more severely injured than patients of other races as measured by Injury Severity Scale scores. Among black patients with spinal injury in the NTDB, 23.9% suffered firearm injuries; only 1% of white patients suffered firearm injuries. The overall mortality rate in the NTDB was 3.9%. In a multivariate analysis that included a large panel of clinical and nonclinical factors, black race retained significance as a predictor of mortality (p = 0.006; adjusted OR 1.571 [1.141-2.163]). Rates of spinal fusion were associated with race and payor in the NTDB data and with payor in the KID: patients with better insurance underwent spinal fusion at higher rates.

CONCLUSIONS

The epidemiology of pediatric spinal injury in the US cannot be understood apart from considerations of race and economic status.

Assessing Incidence and Risk Factors of Cervical Spine Injury in Blunt Trauma Patients Using the National Trauma Data Bank

Despite the potentially devastating impact of missed cervical spine injuries (CI), there continues to be a large disparity in how institutions attempt to make the diagnosis. To better streamline the approach among institutions, understanding incidence and risk factors across the country is paramount. We evaluated the incidence and risk factors of CI using the National Trauma Databank for 2008 and 2009. We performed a retrospective review of the National Trauma Databank for 2008 and 2009 comparing patients with and without CI. We then performed subset analysis separating injury by patients with and without fracture and ligamentous injury. There were a total of 591,138 patients included with a 6.2 per cent incidence of CI. Regression found that age, Injury Severity Score, alcohol intoxication, and specific mechanisms of motor vehicle crash (MVC), motorcycle crash (MCC), fall, pedestrian stuck, and bicycle were independent risk factors for overall injury ( P < 0.0001). Patients with CI had longer intensive care unit (8.5 12.5 vs 5.1 7.7) and hospital lengths of stay (days) (9.6 14.2 vs 5.3 8.1) and higher mortality (1.2 per cent vs 0.3%), compared with those without injury ( P < 0.0001). There were 33,276 patient with only fractures for an incidence of 5.6 per cent and 1875 patients with ligamentous injury. Just over 6 per cent of patients suffer some form of CI after blunt trauma with the majority being fractures. Higher Injury Severity Score and MVC were consistent risk factors in both groups. This information will assist in devising an algorithm for clearance that can be used nationally allowing for more consistency among trauma providers.

Pediatric Spinal Cord Injury: Recognition of Injury and Initial Resuscitation, in Hospital Management, and Coordination of Care

Spinal cord injury is uncommon in the pediatric population with a lifelong impact for the patient and family. Knowledge of spine embryology, mechanisms of injury that lead to specific injuries, appropriate utilization of radiographic imaging based on suspected injury, prehospital and hospital management of various spinal cord injuries is essential for providers attending to traumatically injured patients. In addition to patients who present with soft tissue and bony injuries diagnosed with clinical examination and confirmed with computed tomography or magnetic resonance imaging, it is important to note that the pediatric population is at a higher risk for spinal cord injury without radiographic abnormality than the adult population. Patients who survive the acute phase of injury face long-term rehabilitation and have an increased risk of depression and mortality. Understanding the long-term sequelae of spinal cord injuries is also an essential management component of traumatically injured children. A program that provides long-term rehabilitation, psychosocial and spiritual support, and adaptive environmental supports gives patients and their families the best opportunity for long-term recovery. A review of the current literature on the diagnosis, management, and follow-up of pediatric spinal cord injury is presented.

Subaxial cervical spine trauma: evaluation and surgical decision-making

Study Design Literature review. Objective To discuss the evaluation and management of subaxial cervical spine trauma (C3-7). Methods A literature review of the main imaging modalities, classification systems, and nonsurgical and surgical treatment performed. Results Computed tomography and reconstructions allow for accurate radiologic identification of subaxial cervical spine trauma in most cases. Magnetic resonance imaging can be utilized to evaluate the stabilizing discoligamentous complex, the nerves, and the spinal cord. The Subaxial Injury Classification (SLIC) is a new system that aids in injury classification and helps guide the decision-making process of conservative versus surgical treatment. Though promising, the SLIC system requires further validation. When the decision for surgical treatment is made, early decompression (less than 24 hours) has been associated with better neurologic recovery. Surgical treatment should be individualized based on the injury characteristics and surgeon's preferences. Conclusions The current state of subaxial cervical spine trauma is one of great progress. However, many questions remain unanswered. We need to continue to account for the individual patient, surgeon, and hospital circumstances that effect decision making and care.

Usefulness of full spine computed tomography in cases of high-energy trauma: a prospective study

INTRODUCTION

At this hospital, computed tomography (CT) of the full spine is performed on all patients who have sustained high-energy trauma because spinal fractures can be overlooked by referring only to clinical findings and plain X-rays of the spine. The goal of this study is to prospectively detect the occurrence of spinal fractures in cases of high-energy trauma using full spine CT and to evaluate the usefulness of it.

MATERIALS AND METHODS

Subjects were 179 patients (134 male, 45 female) who were deemed to have sustained high-energy trauma in the 21-month period starting in September 2007. Spinal fractures initially revealed by CT were studied in detail.

RESULTS

Spinal fractures were found in 54 patients (30.2 %); 19 patients had stable fractures, and 41 had unstable fractures. Forty patients had concomitant injuries to organs in addition to spinal injury; these patients had an average Injury Severity Score of 20.2 (4-70). Of 16 patients with a cervical fracture, 6 (37.5 %) had a fracture that did not appear on plain X-rays of the cervical and that was first identified by CT. Of 43 patients with a thoracolumbar fracture, 6 (14.0 %) had a fracture that would have been difficult to detect if a full spine CT had not been done.

CONCLUSION

In patients who have sustained high-energy trauma, spinal fractures may be overlooked during primary care by a diagnosis based only on plain X-rays and clinical manifestations. Therefore, patients who have sustained high-energy trauma should be evaluated with full spine CT during primary care.

[Cervical spine instability: point of view of the anesthesiologist]

The experience in airway management permits the anesthesiologist to participate in cases of cervical spine instability in the operating room when the patient is subjected to surgical procedures, or in cases of difficulty to access or keep the airway open in emergencies. This article reviews the epidemiology, definition, etiology, diagnostic criteria, methods of approach to airway management, and current recommendations on handling cervical instability in different scenarios. There is no approach to the airway that ensures complete immobility of the cervical spine, but there are methods that are better adapted to specific contexts; at the end, the reader will be able to identify the virtues and defects of the various options that the anesthesiologists have to address the airway in cases of cervical instability.

Clinical clearance of the cervical spine in patients with distracting injuries: It is time to dispel the myth

OBJECTIVE

The purpose of this study was to prospectively assess the sensitivity and efficacy of clinical examination for screening of cervical spine (c-spine) injury in awake and alert blunt trauma patients with concomitant "distracting injuries."

METHODS

During the 24-month period from December 2009 to December 2011, all blunt trauma patients older than 13 years were prospectively evaluated with a standard cervical spine examination protocol by the trauma surgery team at a Level 1 trauma center. Awake and alert patients with a Glasgow Coma Score (GCS) ≥14 underwent clinical examination of the cervical spine. Clinical examination was performed regardless of "distracting injuries." Patients without complaints of pain or tenderness on physical exam had their cervical collar removed, and the c-spine was considered clinically cleared of injury. All awake and alert patients with "distracting injuries," including those clinically cleared and those with complaints of c-spine pain or tenderness underwent computerized tomographic (CT) scanning of the entire c-spine. "Distracting injuries" were categorized into three anatomic regions: head injuries, torso injuries and long bone fractures. Patients with minor distracting injuries were not considered to have a "distracting injury."

RESULTS

During the 24-month study period, 761 blunt trauma patients with GCS ≥14 and at least one "distracting injury" had been entered into the study protocol. Two-hundred ninety-six (39%) of the patients with "distracting injuries" had a positive c-spine clinical examination, 85 (29%) of whom were diagnosed with c-spine injury. Four hundred sixty-four (61%) of the patients with "distracting injuries"’ were initially clinically cleared, with one patient (0.2%) diagnosed with a c-spine injury. This yielded an overall sensitivity of 99% (85/86) and negative predictive value greater than 99% (463/464) for cervical spine clinical examination in awake and alert blunt trauma patients with "distracting injuries."

CONCLUSIONS

In the awake and alert blunt trauma patient with "distracting injuries," clinical examination is a sensitive screening method for cervical spine injury. Radiological assessment is unnecessary for safe clearance of the asymptomatic cervical spine in awake and alert blunt trauma patients with "distracting injuries." These findings suggest the concept of "distracting injury" in the context of cervical spine clinical examination is invalid. Expanding the utility of cervical spine clinical examination to patients with "distracting injuries" allows for significant reduction of both healthcare cost and radiation exposure.

Delay in spinal cord injury diagnosis due to sedation: a case report

BACKGROUND

In the United States, the incidence of traumatic spinal cord injury is estimated to be approximately 40 per one million persons per year. The most common causes of traumatic spinal cord injury are motor vehicle collisions, falls, gunshot wounds, and sports accidents.

OBJECTIVE

To report signs, symptoms, clinical presentation, diagnostic modalities, acute management, and treatment of an acute spinal cord injury.

CASE REPORT

A case of traumatic cervical spine injury that was not immediately apparent upon presentation is reported. Diagnostic confirmation was possible after obtaining magnetic resonance imaging and after the sedative effects of medications resolved, allowing for a better physical examination.

CONCLUSION

Neurogenic shock should be considered in patients with hypotension of unknown or unclear etiology. A ground-level fall is sufficient to cause traumatic spinal cord injury in elderly patients, and a cervical spine computed tomography scan without clear fracture does not exclude this pathology.

Association between a single-pass whole-body computed tomography policy and survival after blunt major trauma: a retrospective cohort study

INTRODUCTION

Single-pass, whole-body computed tomography (pan-scan) remains a controversial intervention in the early assessment of patients with major trauma. We hypothesized that a liberal pan-scan policy is mainly an indicator of enhanced process quality of emergency care that may lead to improved survival regardless of the actual use of the method.

METHODS

This retrospective cohort study included consecutive patients with blunt trauma referred to a trauma center prior to (2000 to 2002) and after (2002 to 2007) the introduction of a liberal single-pass pan-scan policy. The overall mortality between the two periods was compared and stratified according to the availability and actual use of the pan-scan. Logistic regression analysis was employed to adjust mortality estimates for demographic and injury-related independent variables.

RESULTS

The study comprised 313 patients during the pre-pan-scan period, 223 patients after the introduction of the pan-scan policy but not undergoing a pan-scan and 608 patients undergoing a pan-scan. The overall mortality was 23.3, 14.8 and 7.9% (P < 0.001), respectively. By univariable logistic regression analysis, both the availability (odds ratio (OR) 0.57, 95% confidence interval (CI): 0.36 to 0.90) and the actual use of the pan-scan (OR 0.28, 95% CI: 0.19 to 0.42) were associated with a lower mortality. The final model contained the Injury Severity Score, the Glasgow Coma Scale, age, emergency department time and the use of the pan-scan. 2.7% of the explained variance in mortality was attributable to the use of the pan-scan. This contribution increased to 7.1% in the highest injury severity quartile.

CONCLUSIONS

In this study, a liberal pan-scan policy was associated with lower trauma mortality. The causal role of the pan-scan itself must be interpreted in the context of improved structural and process quality, is apparently moderate and needs further investigation with regard to the diagnostic yield and changes in management decisions. (The Pan-Scan for Trauma Resuscitation [PATRES] Study Group, ISRCTN35424832 and ISRCTN41462125).

A missed injury leading to delayed diagnosis and postoperative infection of an unstable thoracic spine fracture - case report of a potentially preventable complication

Background

Patients suffering from polytrauma often present with altered mental status and have varying levels of examinability. This makes evaluation difficult. Physicians are often required to rely on advanced imaging techniques to make prompt and accurate diagnoses. Occasionally, injury detection on advanced imaging studies can be challenging given the subtle findings associated with certain conditions, such as diffuse idiopathic skeletal hyperostosis (DISH). Delayed or missed diagnoses in the setting of spinal fracture can lead to catastrophic neurological injury.

Case presentation

A man struck by a motor vehicle suffered multiple traumatic injuries including numerous rib fractures, a mechanically unstable pelvic fracture, and also had suspicion for an aortic injury. Unfortunately, the upper thoracic segment (T1-5) was only visualized with axial images based on the electronic data. Several days later, a contrast CT scan obtained to check the status of suspected aortic injury revealed T3-T4 subluxation indicative of an unstable extension-type fracture in the setting of DISH. Due to the missed injury and delay in diagnosis, surgery was not performed until eight days after the injury. At surgery, the patient was found to have left T3-T4 facet joint infection as well as infected hematoma surrounding a left T4 transverse process fracture and a traumatic T4 costo-transverse joint fracture-subluxation. Despite presence of infection, an instrumented posterior spinal fusion from T1-T6 was performed and the patient recovered well after antibiotic treatment.

Conclusion

A T3-T4 unstable DISH extension-type fracture was initially missed in a polytrauma patient due to inadequate imaging acquisition, which caused a delay in treatment and bacterial seeding of fracture hematoma. Complete imaging is especially needed in obtunded patients that cannot be thoroughly examined.

Canadian Cervical Spine rule compared with computed tomography: a prospective analysis

BACKGROUND

The Canadian cervical spine rule (CCS) has been found to be an effective tool to determine the need for radiographic evaluation of the cervical spine (c-spine) incorporating both clinical findings and mechanism. Previously, it has been validated only through clinical follow-up or selective use of X-rays. The purpose of this study was to validate it using computed tomography (CT) as the gold standard to identify fractures.

METHODS

Prospective evaluation was performed on 3,201 blunt trauma patients who were screened by CCS and were compared with a complete c-spine CT. CSS positive indicated at least one positive clinical or mechanism finding, whereas CT positive indicated presence of a fracture.

RESULTS

There were 192 patients with c-spine fractures versus 3,009 without fracture on CT. The fracture group was older (42.7 ± 19.0 years vs. 37.8 ± 17.5 years, p = 0.0006), had a lower Glasgow Coma Scale score (13.8 ± 4.2 vs. 14.4 ± 4.3, p < 0.0001), and lower systolic blood pressure (133.3 ± 23.8 mm Hg vs. 139.5 ± 23.1 mm Hg, p = 0.0023). The sensitivity of CCS was 100% (192/192), specificity was 0.60% (18/3009), positive predictive value was 6.03% (192/3183), and negative predictive value was 100% (18/18). Logistic regression identified only 8 of the 19 factors included in the CCS to be independent predictors of c-spine fracture.

CONCLUSIONS

CCS is very sensitive but not very specific to determine the need for radiographic evaluation after blunt trauma. Based on this study, the rule should be streamlined to improve specificity while maintaining sensitivity.

Comparative effectiveness of using computed tomography alone to exclude cervical spine injuries in obtunded or intubated patients: meta-analysis of 14,327 patients with blunt trauma

Object

The current standard of practice for clearance of the cervical spine in obtunded patients suffering blunt trauma is to use CT and an adjuvant imaging modality (such as MR imaging). The objective of this study was to determine the comparative effectiveness of multislice helical CT alone to diagnose acute unstable cervical spine injury following blunt trauma.

Methods

The authors performed a meta-analysis of studies comparing modern CT with adjunctive imaging modalities and required that studies present acute traumatic findings as well as treatment for unstable injuries. Study quality, population characteristics, diagnostic protocols, and outcome data were extracted. Positive disease status included all injuries necessitating surgical or orthotic stabilization identified on imaging and/or clinical follow-up.

Results

Seventeen studies encompassing 14,327 patients met the inclusion criteria. Overall, the sensitivity and specificity for modern CT were both > 99.9% (95% CI 0.99–1.00 and 0.99–1.00, respectively). The negative likelihood ratio of an unstable cervical injury after a CT scan negative for acute injury was < 0.001 (95% CI 0.00–0.01), while the negative predictive value of a normal CT scan was 100% (95% CI 0.96–1.00). Global severity of injury, CT slice thickness, and study quality did not significantly affect accuracy estimates.

Conclusions

Modern CT alone is sufficient to detect unstable cervical spine injuries in trauma patients. Adjuvant imaging is unnecessary when the CT scan is negative for acute injury. Results of this meta-analysis strongly show that the cervical collar may be removed from obtunded or intubated trauma patients if a modern CT scan is negative for acute injury.

National Emergency X-Radiography Utilization Study criteria is inadequate to rule out fracture after significant blunt trauma compared with computed tomography

BACKGROUND

EAST guidelines now recommend computed tomography (CT) to evaluate cervical spine (c-spine) fractures after blunt trauma in patients who do not meet National Emergency X-Radiography Utilization Study criteria (NC), yet no imaging is required in those patients who do meet these criteria. NC are based on patients with both minor and severe (trauma team activation [TTA]) trauma. The purpose of this study was to evaluate the NC using CT as the gold standard in TTA patients.

METHODS

We prospectively evaluated 2,606 blunt TTA patients at our Level I trauma center. NC defined as alertness (Glasgow Coma Scale [GCS] score = 15), evidence of intoxication, clinically distracting injury, midline c-spine tenderness, or neurologic deficits were documented. CT was used to determine the accuracy of these criteria.

RESULTS

There were 157 patients with c-spine fractures and 2,449 patients without c-spine fractures. The fracture group was older (age, 43.4 years ± 19.3 years fracture group vs. 37.7 years ± 17.5 years no fracture group, p = 0.0003) with a lower GCS score (fracture group 13.7 ± 4.5 vs. no fracture group 14.4 ± 3.6, p = 0.0001) and initial systolic blood pressure (132.5 mm Hg ± 23.4 mm Hg vs. 139.9 mm Hg vs. 23.5 mm Hg, p = 0.0009). The sensitivity and specificity of clinical examination for all patients were 82.8% (130 of 157) and 45.7% (1,118 of 2,449), respectively. The positive predictive value (PPV) and negative predictive value (NPV) were 8.9% (130 of 1,461) and 97.6% (1,118 of 1,145), respectively. Patients with a GCS score of 15 had a sensitivity of 77%, specificity of 52.3%, PPV of 8.5%, and NPV of 97.5% for clinical examination. In those patients with the GCS score of 15, no intoxication or distracting injury, clinical examination had a sensitivity of 59.4%, specificity of 79.5%, PPV of 12.5%, and NPV of 97.5%. Of 26 patients with missed injuries based on NC, 19 (73.1%) required further intervention (16 collars, 2 OR, 1 Halo).

CONCLUSION

As in our previous trial, NC is inaccurate compared with CT to diagnose c-spine fractures in TTA patients. CT should be used in all blunt TTA patients regardless of whether they meet NC.

Computed tomographic artifact suggesting cervical facet subluxation

STUDY DESIGN

A case report with review of the literature on the cause of computed tomographic (CT) artifacts and recommendations for identification of such artifacts.

OBJECTIVE

To describe the presentation of a patient with a CT scan suggesting a cervical facet dislocation that ultimately proved to be artifactual.

SUMMARY OF BACKGROUND DATA

CT scanning is routinely used in the detection of cervical spine injuries. This technique has a reported sensitivity of 98%, although specificity has proved more difficult to estimate. CT artifacts such as the case reported here is a significant cause of a decrease in specificity for this technique.

METHODS

A 30-year-old woman with a history of a cervical fracture developed severe neck pain without neurologic deficit after trauma to the back of her neck. CT scans were obtained and reviewed at a local secondary level hospital. A cervical fracture dislocation was diagnosed and cervical spinal injury protocols were initiated and the patient transferred to authors', tertiary level institution for surgical management. A repeat CT scan showed her cervical spine to be in normal alignment.

RESULTS

A movement artifact in the patient's original CT scans was misinterpreted as a unilateral facet fracture subluxation at C5-C6. There are two clues that in hindsight indicate that this finding was artifactual; an ill-defined tracheal margin in contrast with the sharply defined margin above and below the level of the artifact and a double bone margin seen on axial sections at the level of the artifact.

CONCLUSION

Motion artifacts are an important cause in the reduction in specificity of CT scans and can be easily missed. It is important to be aware of the indicators of motion artifacts to reduce the risk of unnecessary treatments.

Pediatric cervical spine injuries: a comprehensive review

INTRODUCTION

Cervical spine injuries can be life-altering issues in the pediatric population. The aim of the present paper was to review this literature.

CONCLUSIONS

A comprehensive knowledge of the special anatomy and biomechanics of the spine of children is essential in diagnosis and treating issues related to spine injuries.

Full-body radiography (LODOX Statscan) in trauma and emergency medicine: a report from the first European installation site

Lodox Statscan is a whole-body, skeletal and soft-tissue, low-dose X-ray scanner with digital enhancement and enlargement capabilities. Ten years ago it was introduced as a screening device for the examination of trauma patients. Its incorporation into the Emergency Room enabled anterior-posterior and lateral thoraco-abdominal studies to be performed in 3—5 min with only about one-third of the radiation required for conventional radiography. Since its approval by the Food and Drug Administration in the USA, several trauma centres have incorporated this technology into their Advanced Trauma Life Support protocols. This review provides an overview of the system, and reports on the authors’ own experience with the system and that of others over the past 10 years, based on a literature search for all review articles, original articles, conference proceedings, case reports and short reports related to the Lodox Statscan device.

Diagnostic accuracy, biohazard safety, and cost effectiveness-the Lodox/Statscan provides a beneficial alternative for the primary evaluation of patients with multiple injuries

BACKGROUND

Lodox/Statscan is a new digital X-ray machine with a low dose of radiation exposure that provides rapid, whole-body scans. In the setting of acute trauma management, the importance of image study is well recognized. Here, we report the accuracy of diagnoses made using Lodox/Statscan in patients with multiple injuries. We analyze the cost effectiveness, biohazard safety, and detection rate for treatment using the Lodox/Statscan and evaluate whether it is a viable alternative to the conventional trauma X-ray.

METHODS

We retrospectively reviewed patients who received a Lodox/Statscan between November 2007 and January 2009. All patients who had received both a Lodox/Statscan and a computed tomographic (CT) scan were enrolled. The CT scan was used to make the final diagnosis. The detection rate for treatment, sensitivity, and specificity of the Lodox/Statscan in diagnosis was analyzed.

RESULTS

One hundred eighty-four patients were eligible for the study during the 15-month study period. The detection rates for treatment using the Lodox/Statscan for pneumothorax, pelvic fracture, cervical spine injury, and thoracic-lumbar spine injury were 95%, 96.0%, and 57.1%, and 100%, respectively.

CONCLUSION

In our series, the Lodox/Statscan provided similar quality images and conventional series to the CT scans. Although the Lodox/Statscan missed some injuries, most of the subsequent treatments were not changed. Overall, there were several advantages to using this system, including the short interval of study, low-radiation exposure, and low cost. The Lodox/Statscan could therefore be used as an alternative to the traditional trauma X-ray for evaluation of acute trauma patients.

‘Clearing’ the cervical spine in the unconscious trauma patient

This is a systemic review of the published evidence regarding cervical spine management in unconscious trauma patients. We examine the literature in the following sections: use of plain radiography; use of flexion/extenson views; use of computed tomography; use of magnetic resonance imaging. We also review surveys of practice and current guidelines.

In contrast to the conscious trauma patient there have been no large prospective multicentre studies to derive a clinical decision rule for the exclusion of cervical spine injury. This review therefore assesses currently available evidence to reach a logical conclusion regarding the most appropriate imaging strategy to exclude significant injury in the cervical spine, whilst minimising the time that a patient needs to remain immobilised.

40-Slice Multidetector CT: Is MRI Still Necessary for Cervical Spine Clearance after Blunt Trauma?

We have recently demonstrated that 16-slice multidetector CT (MDCT) is insufficient for cervical spine (CS) clearance in patients with unreliable examinations after blunt trauma. The purpose of this study was to determine if a negative CS CT using 40-slice MDCT is sufficient for ruling out CS injury in unreliable blunt trauma patients or if MRI remains necessary for definitive clearance. In addition, we sought to elucidate the frequency by which MRI alters treatment in patients with a negative CS CT who have a reliable examination with persistent clinical symptoms. The trauma registry was used to identify all patients with blunt trauma who had a negative CS CT on admission using 40-slice MDCT and a subsequent CS MRI during their hospitalization from July 2006 to July 2007. Two hundred thirteen patients were identified. Overall, 24.4 per cent patients had abnormal MRIs. Fifteen required operative repair; 23 required extended cervical collar; and 14 had collars removed. A total of 8.3 per cent of patients with an unreliable examination and 25.6 per cent of reliable patients had management changed based on MRI findings. Overall, MRI changed clinical practice in 17.8 per cent of all patients. Despite newer 40-slice CT technology, MRI continues to be necessary for CS clearance in patients with unreliable examinations or persistent symptoms.

Primary pan-computed tomography for blunt multiple trauma: can the whole be better than its parts?

Single-pass, whole-body computed tomography (pan-CT) was proposed in the late 1990s as a new concept for the diagnostic work-up of severely injured patients. Since its introduction, it has led to considerable debate among clinicians and scientists, triggered by concerns about its immediate safety, questionable therapeutic advantages and exposure to radiation. However, it was recently shown that pan-CT scanning may be associated with a reduction in trauma mortality. In this article, we provide an overview of current knowledge of the value of this compelling concept. The diagnostic accuracy of multidetector row CT (MDCT) for clearing various anatomical regions in trauma patients is, at best, unclear. Little is known about the accuracy of pan-CT as a whole, which weakens statements about its effectiveness and prevents inferences about survival advantages. This last point may be explained by a stage-migration or "Will Rogers" phenomenon: Pan-CT increases injury severity by detecting lesions that would not have been recognized by conventional methods but still do not affect treatment decisions, thus artificially lowering the ratio of observed to expected deaths. In order to maintain the credibility of pan-CT technology for trauma, a rigorous, large-scale evaluation of its accuracy is required. Such an evaluation requires consensus about the definition of true and false positive and negative findings in the setting of blunt multiple trauma. In addition, triage criteria need to be refined to increase specificity and reduce the number of unnecessary scans.

Personal experience with whole-body, low-dosage, digital X-ray scanning (LODOX-Statscan) in trauma

Background

Lodox-Statscan is a whole-body, skeletal and soft-tissue, low-dose X-ray scanner Anterior-posterior and lateral thoraco-abdominal studies are obtained in 3-5 minutes with only about one-third of the radiation required for conventional radiography. Since its approval by the Food and Drug Administration (FDA) in the USA, several trauma centers have incorporated this technology into their Advanced Trauma Life Support protocols. This review provides a brief overview of the system, and describes the authors' own experience with the system.

Methods

We performed a PubMed search to retrieve all references with 'Lodox' and 'Stat-scan' used as search terms. We furthermore used the google search engine to identify existing alternatives. To the best of our knowledge, this is the only FDA-approved device of its kind currently used in trauma.

Results and Conclusion

The intention of our review has been to sensitize the readership that such alternative devices exist. The key message is that low dosage full body radiography may be an alternative to conventional resuscitation room radiography which is usually a prelude to CT scanning (ATLS algorithm). The combination of both is radiation intensive and therefore we consider any reduction of radiation a success. But only the future will show whether LS will survive in the face of low-dose radiation CT scanners and magnetic resonance imaging devices that may eventually completely replace conventional radiography.

Diagnostic imaging of cervical spine injuries following blunt trauma: a review of the literature and practical guideline

Patients with a (potential) cervical spine injury can be subdivided into low-risk and high-risk patients. With a detailed history and physical examination the cervical spine of patients in the "low-risk" group can be "cleared" without further radiographic examinations. X-ray imaging (3-view series) is currently the primary choice of imaging for patients in the "low-risk" group with a suspected cervical spine injury after blunt trauma. For patients in the "high-risk"group because of its higher sensitivity a computed tomography scan is primarily advised or, alternatively, the cervical spine is immobilised until the patient can be reliably questioned and examined again. For the imaging of traumatic soft tissue injuries of the cervical spine magnetic resonance imaging is the technique of choice.

Artificial neural network in predicting craniocervical junction injury: an alternative approach to trauma patients

OBJECTIVE

The aim of this study is to determine the efficiency of artificial intelligence in detecting craniocervical junction injuries by using an artificial neural network (ANN) that may be applicable in future studies of different traumatic injuries.

MATERIALS AND METHODS

Major head trauma patients with Glasgow Coma Scale <or=8 of all age groups who presented to the Emergency Department were included in the study. All patients underwent brain computerized tomography (CT), craniocervical junction CT, and cervical plain radiography. A feedforward with back propagation ANN and a stepwise forward logistic regression were performed to test the performances of all models.

RESULTS

A total of 127 patients fulfilling inclusion criteria were included in the study. The mean age of the study patients was 31+/-17.7, 77.2% (n=98) of them were male, 13.4% of the patients (n=17) had craniocervical junction pathologies. About 64.7% (n=11) of these pathologies were detected only by CT; 23.5% (n=4) of them by both craniocervical CT and cervical plain radiography; and 11.8% (n=2) of them only by cervical plain radiography. A logistic regression model had a sensitivity of 11.8% and specificity of 99.1%. Positive predictive value was 66.7% and negative predictive value was 87.9%. Area under the curve for logistic regression model was 0.794 (P=0.000). ANN had a sensitivity of 82.4% and specificity of 100%. Positive predictive value was 100% and negative predictive value was 97.3%. Area under the curve for ANN model was 0.912 (P=0.000).

CONCLUSION

ANN as an artificial intelligence application seems appropriate for detecting and excluding craniocervical junction injury but it should not replace craniocervical junction CT. However, these findings should lead us to test the applicability of ANN on hard-to-diagnose trauma patients or in constructing clinical decision rules.