-
Pediatric Radiology May 2024Human factors engineering involves the study and development of methods aimed at enhancing performance, improving safety, and optimizing user satisfaction. The focus of... (Review)
Review
Human factors engineering involves the study and development of methods aimed at enhancing performance, improving safety, and optimizing user satisfaction. The focus of human factors engineering encompasses the design of work environments and an understanding of human mental processes to prevent errors. In this review, we summarize the history, applications, and impacts of human factors engineering on the healthcare field. To illustrate these applications and impacts, we provide several examples of how successful integration of a human factors engineer in our pediatric radiology department has positively impacted various projects. The successful integration of human factors engineering expertise has contributed to projects including improving response times for portable radiography requests, deploying COVID-19 response resources, informing the redesign of scheduling workflows, and implementation of a virtual ergonomics program for remote workers. In sum, the integration of human factors engineering insight into our department has resulted in tangible benefits and has also positioned us as proactive contributors to broader hospital-wide improvements.
Topics: Ergonomics; Humans; Pediatrics; Radiology Department, Hospital; Radiology; COVID-19; SARS-CoV-2
PubMed: 38483592
DOI: 10.1007/s00247-024-05903-x -
AJR. American Journal of Roentgenology Sep 2013In this article, we describe some of the cognitive and system-based sources of detection and interpretation errors in diagnostic radiology and discuss potential... (Review)
Review
OBJECTIVE
In this article, we describe some of the cognitive and system-based sources of detection and interpretation errors in diagnostic radiology and discuss potential approaches to help reduce misdiagnoses.
CONCLUSION
Every radiologist worries about missing a diagnosis or giving a false-positive reading. The retrospective error rate among radiologic examinations is approximately 30%, with real-time errors in daily radiology practice averaging 3-5%. Nearly 75% of all medical malpractice claims against radiologists are related to diagnostic errors. As medical reimbursement trends downward, radiologists attempt to compensate by undertaking additional responsibilities to increase productivity. The increased workload, rising quality expectations, cognitive biases, and poor system factors all contribute to diagnostic errors in radiology. Diagnostic errors are underrecognized and underappreciated in radiology practice. This is due to the inability to obtain reliable national estimates of the impact, the difficulty in evaluating effectiveness of potential interventions, and the poor response to systemwide solutions. Most of our clinical work is executed through type 1 processes to minimize cost, anxiety, and delay; however, type 1 processes are also vulnerable to errors. Instead of trying to completely eliminate cognitive shortcuts that serve us well most of the time, becoming aware of common biases and using metacognitive strategies to mitigate the effects have the potential to create sustainable improvement in diagnostic errors.
Topics: Cognition; Diagnosis, Computer-Assisted; Diagnostic Errors; Fatigue; Humans; Peer Review; Radiology; Risk Factors; Workload
PubMed: 23971454
DOI: 10.2214/AJR.12.10375 -
The British Journal of Radiology Nov 2021The pandemic caused by SARS-CoV-2 (severe adult respiratory distress syndrome Coronavirus-2) and its most severe clinical syndrome, COVID-19, has dramatically impacted... (Review)
Review
The pandemic caused by SARS-CoV-2 (severe adult respiratory distress syndrome Coronavirus-2) and its most severe clinical syndrome, COVID-19, has dramatically impacted service delivery in many radiology departments. Radiology (primarily chest radiography and CT) has played a pivotal role in managing the pandemic in countries with well-developed healthcare systems, enabling early diagnosis, triage of patients likely to require intensive care and detection of arterial and venous thrombosis complicating the disease. We review the lessons learned during the early response to the pandemic, placing these in the wider context of the responsibility radiology departments have to mitigate the impact of hospital-acquired infection on clinical care and staff wellbeing. The potential long-term implications for design and delivery of radiology services are considered. The need to achieve effective social distancing and ensure continuity of service during the pandemic has brought about a step change in the implementation of virtual clinical team working, off-site radiology reporting and postgraduate education in radiology. The potential consequences of these developments for the nature of radiological practice and the education of current and future radiologists are discussed.
Topics: COVID-19; Humans; Radiology; Radiology Department, Hospital; SARS-CoV-2
PubMed: 34538092
DOI: 10.1259/bjr.20210632 -
Radiation Protection Dosimetry 2008The EU Council Directive 97/43/EURATOM (MED) states that Member States shall ensure that adequate theoretical and practical training is provided for dental practitioners... (Review)
Review
The EU Council Directive 97/43/EURATOM (MED) states that Member States shall ensure that adequate theoretical and practical training is provided for dental practitioners working with ionising radiation; this also includes the provision of continuing education and training programmes, post-qualification. The area of dental radiology is specifically mentioned in this legally binding document. The Department of Medical Physics and Bioengineering, St James's Hospital, Dublin, is particularly interested in the area of radiation protection training and routinely provides educational courses both at national and international levels. A recent review of their dental radiation protection course was undertaken in conjunction with a number of Principal Dental Surgeons within the Health Service Executive in Ireland. The revised course was delivered to over 200 dental staff members at two separate meetings during 2006. The response from attendees was very positive. It is proposed to extend this course to other dental professionals, working both in the Irish private and public health sectors in the future.
Topics: Education, Dental, Continuing; Humans; Information Dissemination; Program Development; Radiation Protection; Radiology
PubMed: 18283059
DOI: 10.1093/rpd/ncn045 -
Journal of Nuclear Medicine Technology Jun 2013Receiver operating characteristic (ROC) analysis has been successfully used in radiology to help determine the combined success of system and observer. There is great... (Review)
Review
Receiver operating characteristic (ROC) analysis has been successfully used in radiology to help determine the combined success of system and observer. There is great value in these methods for assessing new and existing techniques to see if diagnostic accuracy can be improved. Within all aspects of radiology there should be compliance with the as-low-as-reasonably-achievable principle, which requires optimization of the diagnostic suitability of the image. Physical measures of image quality have long been used in the assessment of system performance, but these alone are not sufficient to assess diagnostic capability. It is imperative that the observer be included in any assessment of diagnostic performance. The free-response ROC paradigm has been developed as a statistically powerful advancement of traditional ROC analysis that allows a precise interpretation of complex images by adding location information to the level of observer confidence. The following review of free-response ROC methodology will explain how observer performance methods can be valuable in image optimization, including examples of how these have already been successful in hybrid imaging.
Topics: Area Under Curve; Humans; Observer Variation; ROC Curve; Radiation Dosage; Radiology
PubMed: 23625536
DOI: 10.2967/jnmt.112.116566 -
Clinical Cancer Research : An Official... Feb 2018Artificial intelligence (AI), especially deep learning, has the potential to fundamentally alter clinical radiology. AI algorithms, which excel in quantifying complex...
Artificial intelligence (AI), especially deep learning, has the potential to fundamentally alter clinical radiology. AI algorithms, which excel in quantifying complex patterns in data, have shown remarkable progress in applications ranging from self-driving cars to speech recognition. The AI application within radiology, known as radiomics, can provide detailed quantifications of the radiographic characteristics of underlying tissues. This information can be used throughout the clinical care path to improve diagnosis and treatment planning, as well as assess treatment response. This tremendous potential for clinical translation has led to a vast increase in the number of research studies being conducted in the field, a number that is expected to rise sharply in the future. Many studies have reported robust and meaningful findings; however, a growing number also suffer from flawed experimental or analytic designs. Such errors could not only result in invalid discoveries, but also may lead others to perpetuate similar flaws in their own work. This perspective article aims to increase awareness of the issue, identify potential reasons why this is happening, and provide a path forward. .
Topics: Data Science; Humans; Radiology
PubMed: 29097379
DOI: 10.1158/1078-0432.CCR-17-2804 -
AJR. American Journal of Roentgenology May 2002The purpose of our study was to model the supply and demand for diagnostic radiologists over the next 30 years under alternative scenarios.
OBJECTIVE
The purpose of our study was to model the supply and demand for diagnostic radiologists over the next 30 years under alternative scenarios.
MATERIALS AND METHODS
We used responses from the American College of Radiology's 2000 Survey of Diagnostic Radiologists and Radiation Oncologists to determine the current age distribution and activity of diagnostic radiologists. The numbers entering the profession were projected using three assumptions: no change in training programs, reduction of residency to 3 years (or otherwise increasing the annual number of graduates by one third), and elimination of most fellowship programs. Demand projections assume a 5% shortage in 2001 and depend on growth rates of the population, aging, scenarios of growth of age-standardized demand, and the effect of possibly productivity-enhancing technologies such as PACS (picture archiving and communication systems).
RESULTS
Only a one-third increase in annual graduates materially increases the work-force relative to current training patterns. In all cases, the growth rate of the demand for radiologists far outstrips the supply over a 30-year horizon. In the shorter term, projections of current trends point to an increasing shortage, but rapid major productivity increases could produce a surplus.
CONCLUSION
Those in the field of diagnostic radiology should consider measures to mitigate the increasing shortage, while monitoring developments that might signal departures from current trends in supply and demand.
Topics: Age Distribution; Career Choice; Data Collection; Humans; Internship and Residency; Models, Statistical; Population Growth; Radiography; Radiology; Time Factors; Workforce
PubMed: 11959704
DOI: 10.2214/ajr.178.5.1781075 -
European Radiology Nov 2023Siamese neural networks (SNN) were used to classify the presence of radiopaque beads as part of a colonic transit time study (CTS). The SNN output was then used as a...
OBJECTIVES
Siamese neural networks (SNN) were used to classify the presence of radiopaque beads as part of a colonic transit time study (CTS). The SNN output was then used as a feature in a time series model to predict progression through a CTS.
METHODS
This retrospective study included all patients undergoing a CTS in a single institution from 2010 to 2020. Data were partitioned in an 80/20 Train/Test split. Deep learning models based on a SNN architecture were trained and tested to classify images according to the presence, absence, and number of radiopaque beads and to output the Euclidean distance between the feature representations of the input images. Time series models were used to predict the total duration of the study.
RESULTS
In total, 568 images of 229 patients (143, 62% female, mean age 57) patients were included. For the classification of the presence of beads, the best performing model (Siamese DenseNET trained with a contrastive loss with unfrozen weights) achieved an accuracy, precision, and recall of 0.988, 0.986, and 1. A Gaussian process regressor (GPR) trained on the outputs of the SNN outperformed both GPR using only the number of beads and basic statistical exponential curve fitting with MAE of 0.9 days compared to 2.3 and 6.3 days (p < 0.05) respectively.
CONCLUSIONS
SNNs perform well at the identification of radiopaque beads in CTS. For time series prediction our methods were superior at identifying progression through the time series compared to statistical models, enabling more accurate personalised predictions.
CLINICAL RELEVANCE STATEMENT
Our radiologic time series model has potential clinical application in use cases where change assessment is critical (e.g. nodule surveillance, cancer treatment response, and screening programmes) by quantifying change and using it to make more personalised predictions.
KEY POINTS
• Time series methods have improved but application to radiology lags behind computer vision. Colonic transit studies are a simple radiologic time series measuring function through serial radiographs. • We successfully employed a Siamese neural network (SNN) to compare between radiographs at different points in time and then used the output of SNN as a feature in a Gaussian process regression model to predict progression through the time series. • This novel use of features derived from a neural network on medical imaging data to predict progression has potential clinical application in more complex use cases where change assessment is critical such as in oncologic imaging, monitoring for treatment response, and screening programmes.
Topics: Humans; Female; Middle Aged; Male; Deep Learning; Retrospective Studies; Time Factors; Neural Networks, Computer; Radiology
PubMed: 37284869
DOI: 10.1007/s00330-023-09769-9 -
European Journal of Dental Education :... Feb 2018To evaluate the impact of audience response systems (ARS) on student participation (SP) during Oral and Maxillofacial Radiology (OMR) undergraduate lectures and on final...
OBJECTIVES
To evaluate the impact of audience response systems (ARS) on student participation (SP) during Oral and Maxillofacial Radiology (OMR) undergraduate lectures and on final examination scores (FES). Furthermore, an analysis of unanimity assessed the influence of ARS on students' responses. Students' perceptions were also assessed.
METHODS
A controlled crossover study was designed. Four lectures covering topics of OMR were each taught with ARS and without ARS (i.e. hand-raising method). SP and FES were compared between ARS and HR groups. Unanimity of answers was analyzed for both groups. Questionnaires assessed students' impressions about ARS.
RESULTS
Mean SP of ARS and HR groups were 97.6% and 47.3%, respectively, and this difference was statistically significant (P<.05). Mean FES for the ARS group (77%) was slightly higher than HR group (75.1%), however, not statistically significant. There was positive correlation between SP and FES. With ARS, only 5.7% of the questions were unanimous, whilst 51.4% were unanimous with HR method. Most students reported that the use of ARS had positive influence on their attention (92%), participation (96%), classmates' participation (82.7%), interest (74.7%), and learning (86.7%). For the five-point scale ratings of the relevance of ARS features, anonymity had an average 3.6, whilst other items received an average 4.6 or higher.
CONCLUSIONS
ARS significantly increased participation in OMR lectures; however, an increase in FES could not be associated with ARS by itself. Not taking into consideration which method was used to answer questions posed during lectures, higher participation correlated with higher scores. ARS is well-accepted and students believe that these devices positively influence their performance. Among the recognized advantages of ARS, anonymity was considered the least relevant.
Topics: Behavior; Cross-Over Studies; Education, Dental; Humans; Mouth; Radiology; Students, Dental
PubMed: 28294484
DOI: 10.1111/eje.12258 -
Journal of Medical Radiation Sciences Jun 2024Diagnostic radiography students experience challenges during clinical placements, which have the potential to impact students' emotional wellbeing. This study aimed to...
INTRODUCTION
Diagnostic radiography students experience challenges during clinical placements, which have the potential to impact students' emotional wellbeing. This study aimed to explore radiography students' perception of the newly developed podcast series as a wellbeing support tool.
METHODS
A mixed methods study was conducted analysing data from listeners, including usage data from the podcast host site, surveys, and focus groups. Usage data was analysed descriptively. A bespoke survey, using a 5-point Likert scale and fixed-response questions was analysed descriptively. Two focus groups consisting of ten participants in total were conducted and data was analysed using thematic analysis.
RESULTS
There were 1201 downloads of the 'Breathe-in Radiography Podcast' series across 20 countries and 17 platforms during the study period. A total of 66 complete survey responses demonstrated an overall positive perception of the podcast series. Five main themes were identified from the focus groups: integrated with other activities, accessed when experiencing emotional challenges, relatability to peers, impact on behaviour and mindset, and future podcast content.
CONCLUSIONS
This study demonstrated students' positive perceptions of a podcast for support during clinical placement. Further studies are needed to maximise the benefits of podcasting to radiography students and to establish a direct effect of podcasts on student wellbeing.
Topics: Humans; Webcasts as Topic; Surveys and Questionnaires; Focus Groups; Students, Medical; Radiography; Radiology
PubMed: 38525902
DOI: 10.1002/jmrs.785