The use of whole-body computed tomography in major trauma: variations in practice in UK trauma hospitals

A SWOT analysis of artificial intelligence in diagnostic imaging in the developing world: making a case for a paradigm shift

Diagnostic imaging (DI) refers to techniques and methods of creating images of the body’s internal parts and organs with or without the use of ionizing radiation, for purposes of diagnosing, monitoring and characterizing diseases. By default, DI equipment are technology based and in recent times, there has been widespread automation of DI operations in high-income countries while low and middle-income countries (LMICs) are yet to gain traction in automated DI. Advanced DI techniques employ artificial intelligence (AI) protocols to enable imaging equipment perceive data more accurately than humans do, and yet automatically or under expert evaluation, make clinical decisions such as diagnosis and characterization of diseases. In this narrative review, SWOT analysis is used to examine the strengths, weaknesses, opportunities and threats associated with the deployment of AI-based DI protocols in LMICs. Drawing from this analysis, a case is then made to justify the need for widespread AI applications in DI in resource-poor settings. Among other strengths discussed, AI-based DI systems could enhance accuracies in diagnosis, monitoring, characterization of diseases and offer efficient image acquisition, processing, segmentation and analysis procedures, but may have weaknesses regarding the need for big data, huge initial and maintenance costs, and inadequate technical expertise of professionals. They present opportunities for synthetic modality transfer, increased access to imaging services, and protocol optimization; and threats of input training data biases, lack of regulatory frameworks and perceived fear of job losses among DI professionals. The analysis showed that successful integration of AI in DI procedures could position LMICs towards achievement of universal health coverage by 2030/2035. LMICs will however have to learn from the experiences of advanced settings, train critical staff in relevant areas of AI and proceed to develop in-house AI systems with all relevant stakeholders onboard.

Use of tranexamic acid in major trauma: a sex-disaggregated analysis of the Clinical Randomisation of an Antifibrinolytic in Significant Haemorrhage (CRASH-2 and CRASH-3) trials and UK trauma registry (Trauma and Audit Research Network) data

BACKGROUND

Women are less likely than men to receive some emergency treatments. This study examines whether the effect of tranexamic acid (TXA) on mortality in trauma patients varies by sex and whether the receipt of TXA by trauma patients varies by sex.

METHODS

First, we conducted a sex-disaggregated analysis of data from the Clinical Randomisation of an Antifibrinolytic in Significant Haemorrhage (CRASH)-2 and CRASH-3 trials. We used interaction tests to determine whether the treatment effect varied by sex. Second, we examined data from the Trauma and Audit Research Network (TARN) to explore sex differences in the receipt of TXA. We used logistic regression models to estimate the odds ratio for receipt of TXA in females compared with males. Results are reported as n (%), risk ratios (RR), and odds ratios (OR) with 95% confidence intervals.

RESULTS

Overall, 20 211 polytrauma patients (CRASH-2) and 12 737 patients with traumatic brain injuries (CRASH-3) were included in our analysis. TXA reduced the risk of death in females (RR=0.69 [0.52-0.91]) and in males (RR=0.80 [0.71-0.90]) with no significant heterogeneity by sex (P=0.34). We examined TARN data for 216 364 patients aged ≥16 yr with an Injury Severity Score ≥9 with 98 879 (46%) females and 117 485 (54%) males. TXA was received by 7198 (7.3% [7.1-7.4%]) of the females and 19 697 (16.8% [16.6-17.0%]) of the males (OR=0.39 [0.38-0.40]). The sex difference in the receipt of TXA increased with increasing age.

CONCLUSIONS

Administration of TXA to patients with bleeding trauma reduces mortality to a similar extent in women and men, but women are substantially less likely to be treated with TXA.

Artificial intelligence in diagnostic imaging: impact on the radiography profession

The arrival of artificially intelligent systems into the domain of medical imaging has focused attention and sparked much debate on the role and responsibilities of the radiologist. However, discussion about the impact of such technology on the radiographer role is lacking. This paper discusses the potential impact of artificial intelligence (AI) on the radiography profession by assessing current workflow and cross-mapping potential areas of AI automation such as procedure planning, image acquisition and processing. We also highlight the opportunities that AI brings including enhancing patient-facing care, increased cross-modality education and working, increased technological expertise and expansion of radiographer responsibility into AI-supported image reporting and auditing roles.

Royal College of Radiologists national audit evaluating the provision of imaging in the severely injured patient and compliance with national guidelines

AIM

To evaluate the provision of imaging in severely injured patients and com pliance with national guidelines.

MATERIALS AND METHODS

Two data collection tools were sent to all Royal College of Radiologist audit leads in radiology departments with an emergency department throughout the UK. The first focused on configuration of radiology departments, number of patients scanned for major trauma and service configuration for major trauma. The second focused on reporting times for 30 patients scanned for major trauma.

RESULTS

Eighty-five out of 191 (45%) eligible departments responded: 16 (19%) from major trauma centres, 52 (61%) from trauma units and 17 (20%) from other hospitals with an emergency department. Data were collected for 2,161 scans: 450 from major trauma centres, 1,400 from trauma units and 311 from emergency departments. Seven hundred and eighty-four (36%) scans were performed in hours and 1361 (63%) out of hours. Two hundred and forty (11%) scans had a primary survey report documented, of which 53 (22%) were unavailable to clinicians after 20 minutes. Time to final consultant report was within 1 hour for 1,033 (48%) scans and within 2 hours for an additional 540 (25%) scans. 34/85 (40%) departments have registrars first on call for major trauma who report scans out of hours and have a consultant final report the next day.

CONCLUSIONS

This study highlights significant deficiencies in care and imaging of severely injured patients within major trauma centres and trauma units. Infrastructure and staffing have been underfunded and under resourced to meet rapidly changing best practice requirements in the management of major trauma.

A case of severe flail chest with several dislocated sterno-chondral fractures

•

Surgical stabilization of flail chest lead to fast weaning from mechanical ventilation.

•

Plates can be used for stabilization of sterno-costal dehiscence.

•

Cartilage reconstruction of a CT scan can reveal the true severity of the trauma.

Introduction

Flail chest is diagnosed clinically by the presence of paradox movement of a segment of the thoracic wall during spontaneous breathing. Radiographic finding confirming a clinical flail chest are fractures of three or more consecutive ribs or costal cartilages in two or more places. Surgical stabilization is associated with a reduced length of hospital stay, time with mechanical ventilation and risk of respiratory complications.

Presentation of case

A trauma patient had a Computed Tomography (CT) scan showing multiple costa fractures, sternal fracture, manubrium fracture, sternal displacement and dehiscence of the sternal-costal attachment. The severity of the trauma was visualized after performing a cartilage reconstruction of the trauma CT scan. The patient underwent surgery, using fixation plates to stabilize the thoracic cage, and was then weaned quickly from mechanical ventilation.

Discussion

This case indicates, that if a patient has a severe flail chest recognized clinically, but not radiologically, a reconstruction of cartilage can reveal the true severity of the trauma. Indeed, the patient in this case experienced a positive outcome from surgery. However, such a procedure demands correct timing and experience in surgical stabilization of the thoracic wall. Furthermore, the injury required accurate planning with the involved personal before surgery.

Conclusion

Surgical stabilization of advanced flail chest with concomitant sternal fracture, seems to be a safe procedure, that might reduce the need of mechanical ventilation and the length of stay at the Intensive Care Unit (ICU). Furthermore, cartilage reconstruction of the trauma CT scan can potentially identify a severe flail chest, that might be missed on regular 3D bone reconstruction.

Predicting orbital fractures in head injury: a preliminary study of clinical findings

Purpose

Patients presenting to emergency departments (EDs) following head injury often undergo computed tomography (CT) of the head to exclude traumatic brain injury. In many cases, this does not show the maxillofacial skeleton. A proportion of these patients also sustain facial fractures, and when fractures involve the orbits, CT imaging is useful in diagnosis and management; obtaining a second scan may cause delay, incur greater cost, and increase radiation dose. The aim of this preliminary study was to examine the value of signs and symptoms of orbital fractures in predicting a fracture on CT.

Methods

The clinical records of 47 patients who underwent CT of the face following facial trauma were retrospectively examined for the presence of signs and symptoms of orbital fractures. Sensitivity, specificity, negative predictive value (NPV) and positive predictive values (PPV) were then calculated for each sign and symptom for the presence of an orbital fracture on CT. We also described a clinical decision instrument and examined the predictive values of this.

Results

Change in the position of the globe, reduced visual acuity, subconjunctival haemorrhage and change in sensation in the maxillary division of the trigeminal nerve were the most specific signs and symptoms for orbital fracture. Our clinical decision instrument had 80.0% sensitivity, 75.0% specificity, 90.3% PPV and 56.3% NPV for predicting the presence of an orbital fracture on CT in this population.

Conclusions

Our results demonstrate that signs and symptoms of orbital fractures may be useful for predicting these injuries, and a decision instrument could be used in the ED to identify patients likely to benefit from extending the radiation field to include the orbits where CT of the head is already planned. This work is however exploratory; and further prospective validation is required before a robust instrument can be recommended for clinical use.

Justification of whole-body CT in polytrauma patients, can clinical examination help selecting patients?

Background

Whole-body computed tomography (WBCT) is used indiscriminately in trauma cases, just on the suspicion of them being polytrauma cases. A good clinical examination done pre-emptively could prevent the need for this investigation and its undesirous effects. We did this study with an overall aim to assess, if WBCT can be limited to subgroup of trauma patients without compromising clinical safety.

Methods

Retrospective database analysis of 150 cases of polytrauma who underwent WBCT in 2017 was performed. We recorded age, gender, radiation dose and CT findings in all cases and calculated mean age, number of total patients and female patients less than 25 years of age, number of normal WBCT scans, mean radiation dose in the normal and total scans. We also compared pre-test clinical requests with whole-body CT findings, and categorised them in following seven categories: Category 1-Normal Scans; Category 2-Clinically expected Major Injuries; Category 3-Clinically expected Minor Injuries (low risk injuries with no risk of morbidity or mortality if remained undiagnosed), Category 4-Clinically expected CT findings with unexpected Minor (non-serious) injuries; Category 5-Clinically expected CT findings with unexpected Major (serious) injuries, Category 6-Unexpected Minor (non-serious) injuries; Category 7-Unexpected Major (serious) injuries. Categories 2 &3 of clinically expected major and minor injuries included patients with fewer injuries than expected. On the other hand, Category 4 & 5 consist of clinically expected findings with other unexpected injuries, including minor and major injuries respectively. Body injuries were reported in seven areas as per our institutional reporting protocol- Head (including face), Cervical Spine, Thoracolumbar Spine, Chest, Abdomen, Pelvis and Appendicular Skeleton (if asked for).

Results

Overall, we found statistically significant correlation between clinical suspicion raised and WBCT findings with good clinical correlation noticed in 106 (70.66%) cases (including 61 cases of clinically suspected major injuries, 15 cases of clinically suspected minor injuries and 25 nearly normal scans with no obvious clinical concern). Isolated unexpected serious injury without any clinical suspicion was seen in only 1 case. Surprisingly, 25 scan requests were made due to high risk mechanism of injury with no obvious clinical concern and were found normal in 20 cases and showed very subtle injuries in 5. Notably, 30 cases of expected major and minor injuries showed highly accurate clinical findings with no injury other than the region of concern and in these cases, limited scan requests would have been sufficient. Mean radiation dose of the entire study group was 22.45 mSv and those to normal patients was 21.19 mSv.

Conclusions

This study re-emphasizes the significance of good clinical examination in the era of evidence based medicine, which would reduce the high number of unnecessary high dose WBCT (25 scans with no positive findings on clinical examination were nearly normal and in 30 cases limited CT would have been sufficient), thereby, decreasing radiation exposure and its potential side effects on polytrauma patients without affecting their survival.

Whole-Body Computed Tomography During Initial Management and Mortality Among Adult Severe Blunt Trauma Patients: A Nationwide Cohort Study

BACKGROUND

Whole-body computed tomography (WBCT) is increasingly being incorporated into the initial management of blunt trauma patients. Several observational studies have suggested that, compared to selective CT, WBCT is associated with lower mortality. In contrast, a randomized controlled trial found no significant difference in survival between patients undergoing WBCT compared to selective CT. Our objective was to confirm the association between WBCT and in-hospital mortality among adult severe blunt trauma patients.

METHODS

This was a retrospective cohort study based on Japan Trauma Data Bank 2004-2015 registry data. The study population comprised adult severe blunt trauma patients with at least one abnormal vital sign: systolic blood pressure ≤100 mmHg, heart rate ≥120, respiratory rate ≥30 or ≤10, or Glasgow Coma Score ≤13. The primary outcome was in-hospital mortality. To adjust for both measured and unmeasured confounders, we performed instrumental variable (IV) analysis to compare the in-hospital mortality of patients undergoing WBCT with those undergoing selective CT.

RESULTS

Of 40,435 patients who were eligible for this study, 19,766 (48.9%) patients underwent WBCT. The proportion of patients undergoing WBCT significantly increased during the study period, from 10.7% in 2004 to 59.6% in 2015. Primary IV analysis showed a significant association between WBCT and lower in-hospital mortality (odds ratio 0.84, 95% confidence interval 0.72-0.98).

CONCLUSIONS

WBCT can be beneficial in patients with blunt trauma which has compromised vital signs. These findings from a nationwide study suggest that physicians should consider WBCT for blunt trauma patients when warranted by vital signs.