Accuracy of radiographer preliminary clinical evaluation of skeletal trauma radiographs, in clinical practice at a district general hospital

Artificial intelligence and radiographer preliminary image evaluation: What might the future hold for radiographers providing x-ray interpretation in the acute setting?

In a stretched healthcare system, radiographer preliminary image evaluation in the acute setting can be a means to optimise patient care by reducing error and increasing efficiencies in the patient journey. Radiographers have shown impressive accuracies in the provision of these initial evaluations, however, barriers such as a lack of confidence and increased workloads have been cited as a reason for radiographer reticence in engagement with this practice. With advances in Artificial Intelligence (AI) technology for assistance in clinical decision-making, and indication that this may increase confidence in diagnostic decision-making with reporting radiographers, the author of this editorial wonders what the impact of this technology might be on clinical decision-making by radiographers in the provision of Preliminary Image Evaluation (PIE).

Medical Image sharing: What do the public see when reviewing radiographs? A pilot study

INTRODUCTION

Policymakers wish to extend access to medical records, including medical imaging. Appreciating how patients might review radiographs could be key to establishing future training needs for healthcare professionals and how image sharing could be integrated into practice.

METHOD

A pilot study in the UK using a survey was distributed to adult participants via the online research platform Prolific. All subjects were without prior professional healthcare experience. Participants reviewed ten radiographs (single projection only) and were asked a two-stage question. Firstly, if the radiograph was 'normal' or 'abnormal' and secondly, if they had answered 'abnormal', to identify the abnormality from a pre-determined list featuring generic terms for pathologies.

RESULTS

Fifty participants completed the survey. A mean of 65.8 % of participants were able to correctly identify if radiographs were normal or abnormal. Results in relation to the identification of a pathology were not as positive, but still notable with a mean of 46.4 % correctly identifying abnormalities. Qualitative data demonstrated that members of the public are enthralled with reviewing radiographs and intrigued to understand their performance in identifying abnormalities.

CONCLUSION

In the pilot, members of the public could identify if a radiograph is normal or abnormal to a reasonable standard. Further detailed interpretation of images requires supportive intervention. This pilot study suggests that patients can participate in image sharing as part of their care. Image sharing may be beneficial to the therapeutic relationship, aiding patient understanding and enhancing consultations between healthcare professional and patient. Further research is indicated.

Preliminary image evaluation performance of radiographers in one New Zealand District: a 6-month prospective study

INTRODUCTION

Preliminary image evaluation (PIE) is a system where radiographers alert emergency department referrers to the presence or absence of abnormalities on acute extremity X-ray examinations. PIE and similar systems have been utilised in the United Kingdom (UK) and Australia due to a shortage of radiologists to provide a timely report. As New Zealand (NZ) faces a similar shortage, PIE should be considered to address the negative impact this has on patients. The aim of this study was to determine the effect of regular feedback and education on radiographers' performance when detecting and describing acute abnormalities on extremity X-ray examinations in ED.

METHODS

A prospective longitudinal study design was utilised for this study. The sensitivity, specificity, accuracy, and accuracy of PIEs performed by seven radiographers at a public provincial district in NZ were assessed over a 6-month period, with the participants provided monthly results along with regular e-mailed feedback on common errors.

RESULTS

The mean for sensitivity, specificity, and accuracy calculated with a 95% confidence interval over the 6-month period were 92.8% (89.9, 95.8), 94.9 (93.1, 96.8), and 94.2 (91.9, 96.5), respectively. When the month-to-month results were analysed, the results demonstrated an improvement in participants' sensitivity, specificity, and accuracy over the 6-month period.

CONCLUSION

The results of this study demonstrated that radiographers who participated in the study can perform PIE to a high standard that is comparable with the findings from international studies and demonstrated an improvement over 6 months. Therefore, PIE may be useful in NZ to aid ED clinicians in their clinical decisions when a radiology report is unavailable.

Operational challenges and collaborative solutions in radiology image interpretation: perspectives from imaging departments in a low-resource setting

INTRODUCTION

Medical imaging's critical role in diagnosis requires prompt and precise image interpretation. Numerous radiology departments, especially in low-resourced settings, encounter challenges such as a shortage of radiologists in their operational setup. This study explored the perceptions of radiographers and radiologists from low-resourced departments in a single country regarding operational challenges and potential solutions in image interpretation.

METHODS

A qualitative approach was utilised, involving heads of departments, senior radiographers, and radiologists with a minimum of 5 years of experience, from three major state referral hospitals. Face-to-face, semi-structured interviews were conducted in November 2022, using an interview guide that included questions on the challenges encountered during image interpretation and the proposed solutions. Data analysis was conducted using Atlas.ti version 9.0, following the four-step content analysis method. All participants willingly provided consent to participate in the study.

RESULTS

Ten participants, comprising two radiologists and eight radiographers participated in the study. The research identified three main themes: image interpretation pathways, image interpretation operational challenges and proposed solutions for image interpretation. In addition, a total of 10 subthemes were generated from the three main themes.

CONCLUSION

The study revealed critical challenges and the need to explore the formal inclusion of radiographers in image interpretation, as a way to improve efficiency. However, a comprehensive assessment of the image interpretation system, encompassing radiographers' knowledge and competence, is recommended for context-specific, empirical-based modifications to enhance service provision.

Preliminary clinical evaluation: Where are we? An international scoping review

BACKGROUND

The College of Radiographers' vision was that diagnostic radiographers in the UK would be writing preliminary clinical evaluations (PCE) on images. Their 2013 policy supporting the use of PCE has not been updated in a decade and it might be suggested PCE practices in the UK have not really moved on, though elsewhere it appears to have gained traction. The aim of this scoping review was to establish the current global status of the use of PCE.

METHOD

The Arksey and O'Malley scoping review framework and PRISMA-ScR guidelines were used to develop a protocol to identify studies between January 2013 to January 2024 using six databases. Collated literature was analysed using content analysis to identify themes.

RESULTS

52 relevant studies were identified for inclusion. Studies focused predominantly on evaluating accuracy, education, perceptions, and new initiatives. Themes identified a developing role in the use of PCE internationally, perhaps more than in the UK, and in a range of modalities and clinical settings though projectional radiography remains the mainstay. Barriers and drivers to the use of PCE were identified in addition to some quality mechanisms used to support PCE implementation, though impact of implementation was not well explored.

CONCLUSION

Considering PCE has been an aspiration for more than a decade, it remains relatively infrequently researched. There is growing scope internationally, particularly in Australia, yet there is no real evaluation of the impact and role that PCE may have.

IMPLICATIONS FOR PRACTICE

Until further research into the potential impact of PCE and barriers to its implementation, it is likely practices may not evolve with the risk AI technologies may supersede necessity for the practice.

Workload as a predictor of radiographer preliminary image evaluation accuracy

INTRODUCTION

Despite a demonstrated high accuracy and reported successful implementations, radiographer preliminary image evaluation (PIE) has been slow and infrequent in its rollout across Australia. A key barrier reported to hamper radiographer PIE service implementation is lack of adequate time to review radiographs and provide an accurate interpretation. This study sought to conduct a correlational analysis between radiographer imaging workload and PIE service accuracy.

METHODS

A total of 45,373 exams and 1152 PIE comments evenly distributed each month from January 1, 2022, to December 31, 2022, were reviewed. PIE comments were assessed for consistency with the radiologist's report. The imaging workload (average exams completed per hour) was separated into three, eight-hour 'shifts' based on time of imaging. Correlational analysis was performed using linear regression models and assessed for normality using the Shapiro-Wilks test.

RESULTS

The study reported no significant linear association between increasing average workload and reduced service accuracy (P = 0.136). It was however noted that when the average workload increased beyond 7 exams/hour, average service accuracy for PIE was always below 85%.

CONCLUSION

This study has demonstrated that, although perceived, there is no statistically significant correlation between x-ray imaging workload and radiographer PIE service accuracy. Consideration of this correlation to be a significant barrier to participation in such a service was not reported at this site.

Real-time x-ray abnormality alerts for emergency departments using a radiographer comment model - a multisite pilot study

INTRODUCTION

The timely communication of clinically significant image appearances to Emergency Department (ED) referrers is necessary for optimum patient care. Australian reliance on verbal communication only is time-limited, open to misinterpretation and lacks transparency. A combined radiographer alert and comment model was designed to reliably communicate image abnormalities to ED referrers in real-time.

METHODS

A multidisciplinary steering group designed the model for all ED general imaging. Protocols were developed to document radiographer comments (critical, urgent and clinically significant) in patients' medical records. Critical findings were communicated directly to ED. Five NSW hospitals varying in size, complexity and population demographics piloted the model between three to twelve months during 2021-2022. Site auditors compared comments with the radiology report and designated each as True Positive (TP), False Positive (FP), indeterminate and clinically significant. Indeterminate cases were analysed by an external radiologist. Inter-observer consensus was obtained for all classifications via two independent auditors. The Positive Predictive Value (PPV), or precision of the comment, was calculated for each site.

RESULTS

Radiographers (n = 69) provided comments for 1102 cases. The pooled average PPV for TP was 0.96; (0.947-0.971; 95% CI). The weighted mean error (FP comments) was 3.9%; (2.9% - 5.3%.; 95% CI).

CONCLUSION

The Radiographer Comment model provided consistent levels of commenting precision and reproducibility across a range of sites with a pooled average PPV (0.96). The False Positive rate or weighted mean error (FP) of 3.9% (2.9% - 5.3%.; 95% CI) was low.

IMPLICATIONS FOR FUTURE PRACTICE

A strategic, interprofessional approach in the implementation of an image alert combined with a Radiographer Comment can be adapted across a variety of hospital settings for ED and other departments.

A pilot study to assess radiographer preliminary clinical evaluation (PCE) introduced for emergency department adult appendicular X-ray examinations: Comparison of trained and untrained radiographers

INTRODUCTION

Radiographers are transitioning from using "Red Dot" annotations to flag abnormal emergency X-ray images, to providing written preliminary clinical evaluation (PCE) diagnostic comments. This study explored the impact of local training on radiographers' PCE participation and accuracy performance during a trial period.

METHODS

Ten radiographers provided PCE comments for adult appendicular trauma X-ray examinations performed in the Emergency Department of an English public hospital over a 19 week trial period. Five senior radiographers who had received local PCE training and five more recently qualified radiographers, without this local training, participated in the trial. PCE participation rates were recorded and the PCE comments were scored for accuracy compared to the formal radiology report.

RESULTS

There were 796 eligible examinations, of which 528 (66%) had PCE comments. PCE participation was significantly higher (p < 0.001) for the radiographer group who received the training (80%, 253/316) compared to the untrained group (57%, 275/480). Similar levels of PCE accuracy (90% vs. 89%), sensitivity (86% vs. 82%) and specificity (91% vs. 93%) were found for the trained and untrained cohorts respectively, with no statistically significance difference between these scores.

CONCLUSION

Local PCE training was associated with more frequent PCE participation but did not appear to influence PCE accuracy. The accuracy results suggest that radiographers are well equipped to provide PCE comments for adult appendicular X-ray examinations.

IMPLICATIONS FOR PRACTICE

Local PCE training is likely to be important for consistent PCE scheme participation. Both experienced and recently qualified radiographers appear well equipped to provide accurate PCE for adult appendicular trauma X-ray examinations.

Learning from patient experiences of projection imaging through the use of online feedback platforms

INTRODUCTION & BACKGROUND

Projection radiography remains a well-used diagnostic tool in healthcare, and its use is continually increasing. The volume of feedback collected from patients has grown exponentially but is rarely analysed within the service to meaningfully underpin change. Professions such as nursing currently make use of patient feedback during training yet there is comparatively little use in diagnostic radiography. Research exists into the use of social media during radiotherapy treatment, highlighting how it could be embraced in future research. However, there remains a sparsity of publications discussing the experiences of patients with projection radiography despite its prominence within diagnostic imaging. Online platforms for feedback are available to most industries and readily embraced and used. They are also becoming increasingly available to healthcare providers. This study aimed to assess and analyse the patient experience of projection radiography using the stories of patients via an online platform.

METHODOLOGY

Recognising that humans do not experience healthcare in a binary way, the authors selected a narrative method as the most appropriate qualitative methodology to analyse and understand 181 patient stories relating to projection radiography from the Care Opinion UK website. Each story was read three times to establish codes and themes and to ensure author familiarity with the patient's words & descriptions. This resulted in 30 empirical codes with the most frequently used being split into three major themes for discussion RESULTS & CONCLUSION: The three major themes considered the radiography experience, the encounter with professionals and service provision. Online sources of feedback provide valuable data for health researchers and provide access to insights which might otherwise go unconsidered. Patients instinctively perceive radiological examinations to result in delays to their care and report surprise when discovering examinations are delivered swiftly, though it remains that innovations such as radiographer-led discharge could be better utilised to enhance the patient experience. In addition, it is evident that administrative functions in diagnostic radiology departments are considered poor and from the descriptions given in the study by patients, the administrative side of the service does not meet their needs. Patient stories demonstrate that radiography is not perceived as vital to patient care and is frequently devalued through the notion that health professions are limited to medical doctor and nurse. The work of radiographers is not valueless to the patient evidenced by their desire to thank staff for their work, but its value is poorly understood and could be further enhanced by embracing online feedback as part of continuing professional and service development.

Radiographer abnormality flagging systems in the UK - A preliminary updated assessment of practice

INTRODUCTION

Radiographer abnormality flagging systems have been in use in the UK for over 30 years, with the guidance of the Society and College of Radiographers indicated that the preliminary clinical evaluation (PCE), or comment, be the preferred system of choice. This study aimed to provide an updated assessment of current practice based upon a previous 2008 study.

METHODS

A cross-sectional online survey was disseminated via Twitter and aimed at departmental and reporting leads. It requested information on the types of flagging and reporting systems operated, scope of the systems employed, required education of participants, and the role of audit.

RESULTS

Responses were received from 31 Trusts within the UK. Red dot systems were employed in 90% (n = 28) of sites, with 26% (n = 8) undertaking PCE. Skeletal radiographs were most commonly reviewed (90%; n = 28) followed by chest (58%; n = 18) and abdomen (32%; n = 10). Only 13% (n = 4) sites indicated if the image was normal but 71% (n = 22) allowed the radiographer to indicate if they were unsure. There was marked variation in the educational requirements and use of audit.

CONCLUSION

Compared to 2008 there appears to be quite minimal change in practices in the UK. There does appear to be some increase in the use of flagging systems generally and a higher proportion of PCE systems in comparison to red dot but the use of education and audit does not necessarily show much development in the past 15 years.

IMPLICATIONS FOR PRACTICE

Significant conclusions cannot be drawn due to limited sample size, however, it may support further study and consideration in relation to implementation and potentially standardisation of abnormality detection systems may be justified.

Reducing diagnostic errors in the emergency department at the time of patient treatment

OBJECTIVE

The purpose of the present study was to compare and combine the radiographic interpretation accuracy of emergency clinicians and radiographers in clinical practice.

METHODS

A total of 838 radiographic examinations were included for analysis from 1 August to 24 August 2020. The range of examinations reviewed included the appendicular and axial skeleton, chest and abdomen. Both paediatric and adult examinations were reviewed. The emergency clinician's and radiographer's interpretations for each examination were compared to the radiologist's report. This allowed mean sensitivity, specificity and diagnostic accuracy to be calculated.

RESULTS

The radiographer's interpretation demonstrated a mean sensitivity, specificity and accuracy of 80%, 98% and 92%, respectively. The emergency clinician's interpretation demonstrated a mean sensitivity, specificity and accuracy of 82%, 95% and 89%, respectively. When the radiographer's and emergency clinician's interpretations were combined, it yielded a mean sensitivity, specificity and accuracy of 90%, 93% and 92%, respectively.

CONCLUSIONS

This is the first study to directly compare and combine the accuracy of an emergency clinician's radiographic interpretation with a radiographer's interpretation within clinical practice. The present study demonstrated that with the addition of a radiographer's interpretation, an emergency clinician's interpretation can be more accurate than the emergency clinician's interpretation in isolation. This highlights the value of a radiographer's interpretation that can complement an emergency clinician's interpretation when a radiologist's report is unavailable.

The efficacy of preliminary clinical evaluation for emergency department chest radiographs with trauma presentations in pre- and post-training situations

INTRODUCTION

The chest X-ray (CXR) is the most frequently performed radiographic examination. This study evaluates radiographers' ability to localise traumatic CXR pathology and provide a preliminary clinical evaluation (PCE) for these cases.

METHODS

This observer study was performed in a district general hospital in the United Kingdom (UK). A 58-case image bank was used with 20 positive cases. Participants were awarded a maximum of three points, based on abnormality recognition and descriptive accuracy. Localisation data were recorded with ROCView. Training was delivered via short online recorded tutorials covering an introduction of a systematic search strategy for CXR, how to recognise the common abnormalities covered in the tests, how to structure a PCE and multiple practice cases to review at participants' own pace. Pre- and post-training data was recorded.

RESULTS

Nine participants completed the study. Overall, pooled sensitivity remained consistent (78.9%-78.8%) following training, specificity and accuracy showed improvement of 79.0%-89.9% and 78.9%-86.0% respectively. An increase in the number of correct localisations and PCE scores were also evident. Participants performed better at correctly identifying a pneumothorax compared to skeletal abnormalities.

CONCLUSION

Improvements in performance were evident for most participants' abnormality localisations and PCE scores, following the training intervention. The study highlighted areas of CXR PCE that may require further training, such as detecting superimposed or subtle abnormalities.

IMPLICATIONS FOR PRACTICE

This study provides additional support for the development of PCE systems in additional areas of imaging practice.